A Neural Network Based Bank Cheque Recognition system for Malaysian Cheques

Size: px
Start display at page:

Download "A Neural Network Based Bank Cheque Recognition system for Malaysian Cheques"

Transcription

1 A Neural Network Based Bank Cheque Recognition system for Malaysian Cheques Ahmad Ridhwan Wahap 1 Marzuki Khalid 1 Abd. Rahim Ahmad 3 Rubiyah Yusof 1 1 Centre for Artificial Intelligence and Robotics, Universiti Teknologi Malaysia, Jalan Semarak, Kuala Lumpur Tel : / / Fax : , marzuki@utmkl.utm.my 2 Dept. of Computer Science and IT, College of Engineering, Universiti Tenaga Nasional, Kajang Tel: , Fax: , abdrahim@uniten.edu.my Abstract Automated bank cheque processing is becoming an important technology due to the massive amount of cheques to be processed daily by banks. This paper presents the results from a research to design and develop a bank cheque recognition system for Malaysian banks. The system concentrates on recognizing the courtesy amount and date only. The system consists of 3 modules: detection module, extraction module and recognition module. The first involves locating the required image and the second extracting the required images. The third, the recognition module recognizes the numerical characters by first segmenting the images into individual characters and then recognizing it using a back propagation MLP neural network. The feature extraction technique used were a combination of geometrical and topological feature analysis and an improved moment invariant. The digit recognition module was trained with 6000 training data created from some sample bank cheques and the test data consists of 1000 digits taken from another sample of bank cheques. Results from the digit recognition module were satisfactory. However, recognition rates on actual bank cheques were quite unsatisfactory. We report the actual results and provide the reasons for such cases. Keywords: Automation, Neural Network, Bank Cheque Processing. Introduction There have not been many research done in Malaysia for automating cheque processing by banks. The Centre for Artificial Intelligence and Robotics (CAIRO) of Universiti Teknologi Malaysia have conducted some research towards the design of automated bank cheque processing system. Bank cheque processing is a challenging area for researchers working in document analysis and handwriting recognition. The challenge lies in the fact that bank cheques processing involve recognition of a number of components that are rather complex [1]. The backgrounds of the cheque and the pre-printed information on the bank cheques are further issues that need to be handled. In addition to that, Malaysian cheques allow the use of both Bahasa Melayu and English. Ready made systems from Europe, America or other countries are not suitable since the styles of handwriting of Malaysians differ from the actual target user. With over a million cheques processed daily, designing a Malaysian based bank cheque recognition system would be the best option. This paper reports the result of the design and development of the earlier proposed recognition system. However, it only concentrates on recognizing the courtesy amount and date only. Another research at CAIRO deals with the design of the recognition system for the legal amount. [8] The system developed consists of 3 modules: detection module, extraction module and recognition module. The first involves locating the required images (courtesy amount) and the second extract the required images. The third, the recognition module recognizes the numerical characters by first segmenting the images into individual characters and then recognize it using a back propagation MLP neural network. The feature extraction technique used is a combination of geometrical and topological feature analysis (GF46) and improved moment invariant (IMI). The algorithm for detection, extraction, segmentation and, recognition of the courtesy amount and date are described in this paper. This paper has been organised as follows. The next section presents some physical features of Malaysian bank cheques that have profound impact in the design of the system. Section 3 discusses the overall system design. The approach and methods for the images extraction, feature extraction and digit recognition are discussed in section 4. Section 5 presents some experimental results. Finally, section 6 concludes the paper.

2 Analysis of Malaysian Bank Cheques Malaysian banks use their own cheque template, which vary from one another in terms of their layout, background and format. Figure 1 below shows 2 typical examples: inside the rectangle line, and the date is normally written above the guideline. General locations of the courtesy amount and the date obtained from measurements of different cheques from the image database are also used as a guide. The following are some points that summarises the Malaysian cheques layout: courtesy amount location is always on the right side of the cheque courtesy amount location is also approximately at the centre of the cheque s height date is always located above the courtesy amount type A image A type B Figure 1 - Typical Cheque layout. The two cheques above differ in the layout of rectangles, guidelines and background. Due to that, different detection algorithms are required to detect the required courtesy amount. For this research, layout of type B is used to design the detection algorithms as most of the banks uses this layout though the position and style of the rectangles and the guidelines vary slightly from one bank to another. An appropriate detection strategy is used to overcome the difficulty in handling the variation. Figure 2 shows three different types of rectangle layout used for courtesy amount in Malaysian bank cheques. They can be summarised as follows: rectangle line (see image A and C) rectangle line separated horizontally (image B) rectangle box (image D) The research focussed on cheques of the types in images A, B, and C only. There are also three types of guidelines used in Malaysian bank cheques: single straight line (image C and D) two straight lines (image B) dotted line (image A) In the research, rectangle line and the guideline were used as the marker or cue to detect the location of the courtesy amount and date. The courtesy amount is normally written image B image C image D Figure 2 - Rectangle Layout By using the above three points, a strategy to detect the two subjects was formulated. Two search regions where the courtesy amount and the date reside were determined. The objective of using search region is to help the detection of the rectangle and the guideline by focusing the detection in specific area of the whole cheque.

3 Overall System Design. System Overview The Courtesy Amount and Date Recognition System (CADRS) consists of three main modules; detection module, extraction module, and recognition module. Each module is comprised of several sub-modules that perform specific tasks to complete the objectives of that module. This section discusses the process flow in the CADRS. The following section discusses the operation of each module and the algorithm used in detail. Cheque Image Detection Module CA and date images. The images are binary images where the foreground is set to black and the background is set to white. The CA and date images are then fed into the recognition module for recognition. This module implements several algorithms for the object joining, digit string segmentation, slant estimation and correction, feature extraction, and classification algorithms. The result of the recognition module is the representation of the CA and date in ASCII code. Approach and Methods Image Detection Module The Detection module consists of three sub-modules: the skew detection and correction. the origin and dimension estimation. the rectangle and guideline detection. Extraction Module Input Image Recognition Module Result Figure 3 - Process flow of overall system. Figure 3 shows the process flow in the system. The input image is processed in the detection module to get two sets of co-ordinates for the bounding rectangle and the guideline. The locations of the two markers are then used to clip out the courtesy amount (CA) image and the date image from the skew-corrected image. The result of the detection module is the CA image and the date image with the exact location of the guideline and the co-ordinates of the top-most edge of the rectangle. The guideline location is used in the line removal algorithm to remove the guideline from the date image. The top most edge of the rectangle is used as a control parameter in determining the search region for the date. It is possible that the search region for the date overlap a portion of the rectangle. Therefore, the control parameter will ensure that the search region for date will never overlaps the rectangle as in real cheques where the guideline is always above the rectangle. The extraction module cleans up the rectangle and the date image from noises such as the inner part of the bounding rectangle for the CA image and the guideline for the date image. The output of the extraction module is the noiseless CA Image and Top Edge Location Skew Detection and Correction Origin and Dimension Estimation Search Region Determination Rectangle and Guideline Detection Skew-Corrected Image Search Region Images Date Image and Guideline Location Figure 4 - Process flow in detection module. Figure 4 shows the process flow in the detection module. The input image may not properly aligned. The skew detection and correction sub-module will detect the skewed angle of the input image. Then the input image will be rotated in the opposite direction using the skewed angle detected earlier. The resultant image is then processed by the origin and dimension estimation sub-module to detect the four edges of the cheque image. The left and top edges give the offset of

4 the origin of the cheque with respect to the origin of the skew-corrected image in the horizontal and vertical axes respectively. The top left corner of the skew-corrected image is the origin of the skew-corrected image. The difference between the left and the right edges give the width of the cheque, whereas the difference between the top and the bottom edges give the height of the cheque. The origin`s offset and the dimension of the cheque are important in determining the search region of the CA and the date. The search region determination and the marker detection operations are performed twice. The operations will work on the rectangle followed by the guideline. The rectangular guide and guideline detection sub-module will detect the location of the two markers within the two search regions. The module works by scanning the search region left to right and top to bottom to find the horizontal lines in the regions. In rectangular guide detection, another scanning is performed to detect the two vertical lines in between the two horizontal lines. The CA image and the date image are extracted from the skew-corrected image based on the location of the rectangle and the guideline. Image Extraction Module Extraction module is a noise removal module where the input image is cleaned in four steps. The input image undergoes spatial filtering and binarization operations in the first cleaning step. In spatial filtering, the image is filtered using a median filter and then sharpened followed by smoothing to enhance the image. After performing spatial filtering, the image will be binarized using Otsu algorithm [3]. In the second step, the binary image is then processed using line removal algorithm to remove the preprinted lines such as the rectangular line for the rectangle image and the guideline for the date image. The resultant image then undergoes blob analysis operation to label every blob in the image and obtain the basic information of the blobs in the image. Examples of the basic information are area, height, width and position. The basic information obtained above is used in the subsequent operation for cleaning purposes. The area of the blob is used in the size filtering operation in the third cleaning step. The blobs that are smaller than the predefined ones are removed from the image. The predefined areas of the blobs must be carefully selected in order to avoid removing important information such as decimal point. In the fourth cleaning step, the image undergoes boundary-filtering operation. The blobs that are located at the border of the image are excluded in the next processing. The border blob is defined as the blob that has center point in horizontal and vertical axes located in the border region. Figure 5 shows the process flow in the extraction module, for the extraction operation of the CA and date images. CA/Date Image Spatial Filtering and Binarization Border/Line Removal Size Filtering Boundary Filtering Noise Free CA/Date Image Figure 5 - Process flow in Image extraction module. Feature Extraction and Recognition The Recognition module is the last module in the system that processes the CA/date image to get the results. The Recognition module consists of three main sub-modules that perform their own specific tasks. Figure 6 shows the process flow in the recognition module. CA/Date Image Blob Joining Blob Analysis Digit String Recognition Result Figure 6 - Process flow in recognition module. The Blob joining Sub-Module processes the input image to join broken objects in the image. The output of this sub-module is also an image. Blob analysis sub-module processes the input image to get individual blobs from the image. The blob basic information such as area, height, width, dimensions and location of each blob is extracted and stored for further use. The blobs are then sorted from left to right before proceeding to the next sub-module. The output of this sub-module is a string of blobs.

5 The Digit String Recognition Sub-Module processes the blob string from the Blob Analysis Sub-Module to recognise the digits. The blobs are fed one at a time starting from the left-most blob, to the sub-module for recognition. The process flow in the digit string recognition sub-module is shown in Figure 7. Blob String Load i th blob Identify for comma, dash and dot Yes Another blob? No END Performance of the Detection Module Several hundred samples of Malaysian bank cheques are used in this experiment. The cheques are generated from the more than 400 samples of original cheques. The orientation of the original cheques is varied to create skewed cheques for use in the experiment. The detection module detects the location of the rectangle and the guideline in the cheques. The experiments done have shown that the detection module successfully detects all the rectangles and the guidelines in all the samples. Figure 8 shows some examples of the CA and the date that has been detected by the detection algorithm. Identified? No Digit Recognition Yes Save Result Digit recognized? No Digit string segmentation Yes Figure 7- Process flow in digit string recognition sub-module. The blobs strings are sequentially fed into the digit recognition sub-module one at a time. Firstly, the blob is analysed for comma, dash and dot. If detected, the result is saved and another blob is loaded for analysis. If not, the blob is fed into a digit recogniser. A digit recogniser consists of two operations, which are the feature extraction operation followed by a classification operation by MLP neural network. If the blob is recognised, the result is saved and another blob is loaded if available. If the blob is not recognised, the blob is fed into digit string segmentation algorithm to be segmented and recognised gain. Figure 8 - Some examples of the detected CA and date. Performance of the Extraction Module The task of the extraction module is to remove the markers and other noises such as the border noises and the small blobs that scatter in the region of interest. Results from the experiment have shown that the extraction module has successfully remove all noises mentioned. The line removal algorithm is able to remove the rectangle and the guideline in all image samples used in the experiment. However, some of the noises are unable to be deleted due to their size and location. Figure 9 shows some examples of the CA and date that have been extracted by the extraction module. Experimental Results and Analysis The Determination of the Search Region Parameters Initially the search region parameters are calculated by manually measuring the location of the rectangle and the guideline for some samples using the imaging software. These parameters are then used in the automatic detection of the rectangle and the guideline using the detection algorithm. In both cases, the global search region parameters are set slightly below the calculated values to ensure the coverage of the search region. Figure 9 - Some examples of the extracted CA and date. MLP Training This section discusses the performance of the feature extraction methods for the unconstrained digit recognition system. The feature extraction method is the combination of GF46 and IMI. The training samples consist of 7000 characters where 6000 characters are used as the training

6 samples and the remaining 1000 characters are used as the testing samples. The database consists of 14 character sets that are digit 0 to 9, R, M, RM and slash. The characters are obtained from 15 persons who are asked to write the CA and the date in a form. Each person has to write 54 CAs and 24 dates. Individual characters are then extracted from the form to build the database. Figure 6.3 shows the samples of the characters used in the experiment. Table 2 - Test Set Characters Occurrence R 50 M 50 RM 50 Slash 86 Total = 1000 Slash Figure 10 - Samples of characters used. There are several types of slash that exist in the database. Figure 10 shows three types of slash. The first slash is almost like digit 1 except the size of the slash is bigger than digit 1. However, due to the fact that characters are written without any constraint, the size of the slash sometimes equal to the size of the digit 1 or even smaller. This causes problem to the recognition module to distinguish the slash and the digit 1. Table 1 and Table 2 show the occurrence of each character in the training and the test sets respectively. Table 1- Training Set Characters Occurrence R 150 M 150 RM 150 Slash 594 Total = 6000 The experimental result of the training of the MLP using the GF46+IMI is summarized in Table 3 below. Table 3 - MLP training information and results Feature extraction method GF46 + IMI No. of input neurons 55 No. of hidden neurons 55 No. of output neurons 14 Learning rate, η Momentum, α 0.08 Minimum error reach 0.1 Training epoch Recognition rate(%) Testing the Cursive Handwritten Digit Segmentation Algorithm One hundred and fifty connected digits are used in this experiment. The samples are obtained from the same source as the MLP s training samples. Figure 6.4 shows the examples of the connected digits used in this experiment. Figure 11 - connected digits samples.

7 The result of the experiment gives 108 correct answers out of 150 connected digit samples or 72% of the input samples. There are several causes of the incorrect answers in the experiment. From the results, it is observed that, most of the problems are caused by the failure of the recognition module to properly recognise the digits. This will certainly give incorrect recognition of the input digits. For example, the segmentation algorithm has correctly segmented the input image but the recognition module fails to recognise the slices correctly. Some errors also occur during the slicing mechanism in the segmentation algorithm. The recognition module incorrectly classifies the initial slice of the slicing mechanism. Further slicing might lead to the correct answer but the initial answer is still regarded as the final answer and the change of the recognition output caused the slicing mechanism to stop. Sometimes, the slice also converges to other digit during the slicing mechanism. In some cases, the slice could not be recognised until the end of slicing mechanism or the recognition module recognises the connected digits as a single digit. The small number of the training samples used that is only 6000 samples might also cause the failure of the recognition module. Apart from the failure of the recognition module, the segmentation module also contributes to the misclassification of the input samples. The segmentation algorithm depends mainly on the vertical transition histogram of the connected digit. For this reason, it is possible that the segmentation algorithm gives the wrong segmentation points. For example, the digit 0 that is broken at one part of it will cause the segmentation algorithm concludes that that part is a link. Digit 4 also gives problems to the segmentation algorithm because sometimes it looks like two digits that are connected with a link. However, from the observation, the performance of the segmentation algorithm is considerably good. Analysis of the Overall System The CADRS has been tested on several Malaysian bank cheques to investigate its performance. The CADRS is successful in term of detecting and extracting the CA and the date from the cheques. However, in term of recognition capability, the CADRS performance is not satisfying. In most cases, the CADRS could not recognize all the digits and other characters composing the CA and the date. At least one of the digits or characters is wrong while the others are perfectly recognized. In certain cases, the CA or the date image contains noises that cause the CADRS to give a wrong answer. From the observations during the experiment, there are six main reasons that cause the failure of the CADRS. Those causes of failure are the recognition failure, the segmentation failure, the extraction failure, blurred image, dark image and noisy image. The first and the second causes have been discussed in the previous section. Blurred image causes the important information such as the digit, dot, slash or dash is removed or broken during extraction process. Dark image produces significant noises and some of the noises are overlapped with the CA and the date. Binarizing the dark image causes some of the background objects to be included in the output image and hence cause the recognition module to give incorrect answers. Noisy images such as images with stamping and other significant noises that are overlapped or located near to the CA and the date also contribute to the failure of the CADRS to recognise the CA and the date. The reason is the same as the dark image. Extraction algorithm also sometimes fails to produce proper image for further processing. The broken foreground objects, significant noises and loss of important information are examples of the failure in the extraction module. The binarization algorithm might not be able to cover the wide range of image types. The brightness and the contrast of the input images are different from each other. Therefore, the input images would be sometimes outside the range of the capability of the binarization algorithm. This will produces output images that suffer the previously mention problems. Conclusion In this paper, the design and development of the courtesy amount and date of Malaysian bank cheques was reported. The system has successfully implemented the detection and extraction module of the system but the recognition results were not very satisfactory. Possible causes of failure have been discussed to point out improvements that can be made and pitfalls that should be avoided in future work. References [1] M. N. Sulaiman and M. Khalid Grouping Single Slice Mechanisms to Segment and Recognize Off-line Cursive Handwritten Courtesy Amounts of Malaysian Bank Cheques, CAIRO report. [2] J. Ramesh, K. Rangachar, Schunk B. G Machine Vision, New York: McGraw Hill. [3] N. Otsu A Threshold Selection Method from Gray-Level Histograms, IEEE Transactions on Systems, Man, and Cybernatics, Vol. 9, No. 1, pp [4] G. Dimauro, S. Impedovo, G. Pirlo and A. Sazlo, Automatic Bankcheck Processing: A New Engineered System, Automatic Bankcheck Processing pp5-42, World Scientific Publ. Co. [5] W. N. Lim, Design of an Automated Data Entry System for Hand-Filled Forms, Universiti Teknologi Malaysia: Master Thesis. [6] S. T. Welstead, Neural Networks and Fuzzy Logic Applications in C/C++, New York: John Wiley & Sons, Inc. [7] K. S. Yap, Design of an Intelligent Vehicle License Plate Recognition System, Universiti Teknologi Malaysia: Master Thesis. [8] M. N. Sulaiman and M. Khalid, An Offline Segmentation Technique for the Processing of the Courtesy Amount of Malaysian Bank Cheques, ELEKTRIKA, Journal of Electrical Engineering. Vol. 4, Num. 2, pp 1-13.

Cursive Handwriting Recognition System Using Feature Extraction and Artificial Neural Network

Cursive Handwriting Recognition System Using Feature Extraction and Artificial Neural Network Cursive Handwriting Recognition System Using Feature Extraction and Artificial Neural Network Utkarsh Dwivedi 1, Pranjal Rajput 2, Manish Kumar Sharma 3 1UG Scholar, Dept. of CSE, GCET, Greater Noida,

More information

Design of an Automated Data Entry System for Handwritten Forms

Design of an Automated Data Entry System for Handwritten Forms Design of an Automated Data Entry System for Handwritten Forms Lim Woan Ning, Marzuki Khalid* and Rubiyah Yusof Centre for Artificial Intelligence and Robotics (CAIRO) Faculty of Electrical Engineering,

More information

Automatic Recognition and Verification of Handwritten Legal and Courtesy Amounts in English Language Present on Bank Cheques

Automatic Recognition and Verification of Handwritten Legal and Courtesy Amounts in English Language Present on Bank Cheques Automatic Recognition and Verification of Handwritten Legal and Courtesy Amounts in English Language Present on Bank Cheques Ajay K. Talele Department of Electronics Dr..B.A.T.U. Lonere. Sanjay L Nalbalwar

More information

Character Recognition

Character Recognition Character Recognition 5.1 INTRODUCTION Recognition is one of the important steps in image processing. There are different methods such as Histogram method, Hough transformation, Neural computing approaches

More information

CHAPTER 1 INTRODUCTION

CHAPTER 1 INTRODUCTION CHAPTER 1 INTRODUCTION 1.1 Introduction Pattern recognition is a set of mathematical, statistical and heuristic techniques used in executing `man-like' tasks on computers. Pattern recognition plays an

More information

Optimization of vehicle licence plate segmentation and symbol recognition

Optimization of vehicle licence plate segmentation and symbol recognition Optimization of vehicle licence plate segmentation and symbol recognition R.P. van Heerden and E.C. Botha Department of Electrical, Electronic and Computer engineering University of Pretoria, South Africa

More information

HANDWRITTEN GURMUKHI CHARACTER RECOGNITION USING WAVELET TRANSFORMS

HANDWRITTEN GURMUKHI CHARACTER RECOGNITION USING WAVELET TRANSFORMS International Journal of Electronics, Communication & Instrumentation Engineering Research and Development (IJECIERD) ISSN 2249-684X Vol.2, Issue 3 Sep 2012 27-37 TJPRC Pvt. Ltd., HANDWRITTEN GURMUKHI

More information

LECTURE 6 TEXT PROCESSING

LECTURE 6 TEXT PROCESSING SCIENTIFIC DATA COMPUTING 1 MTAT.08.042 LECTURE 6 TEXT PROCESSING Prepared by: Amnir Hadachi Institute of Computer Science, University of Tartu amnir.hadachi@ut.ee OUTLINE Aims Character Typology OCR systems

More information

Handwritten Devanagari Character Recognition Model Using Neural Network

Handwritten Devanagari Character Recognition Model Using Neural Network Handwritten Devanagari Character Recognition Model Using Neural Network Gaurav Jaiswal M.Sc. (Computer Science) Department of Computer Science Banaras Hindu University, Varanasi. India gauravjais88@gmail.com

More information

Segmentation of Bangla Handwritten Text

Segmentation of Bangla Handwritten Text Thesis Report Segmentation of Bangla Handwritten Text Submitted By: Sabbir Sadik ID:09301027 Md. Numan Sarwar ID: 09201027 CSE Department BRAC University Supervisor: Professor Dr. Mumit Khan Date: 13 th

More information

In this assignment, we investigated the use of neural networks for supervised classification

In this assignment, we investigated the use of neural networks for supervised classification Paul Couchman Fabien Imbault Ronan Tigreat Gorka Urchegui Tellechea Classification assignment (group 6) Image processing MSc Embedded Systems March 2003 Classification includes a broad range of decision-theoric

More information

Siti Norul Huda Sheikh Abdullah

Siti Norul Huda Sheikh Abdullah Siti Norul Huda Sheikh Abdullah mimi@ftsm.ukm.my 90 % is 90 % is standard license plates 10% is in special format Definitions: Car plate recognition, plate number recognition, vision plate, automatic

More information

Hand Written Character Recognition using VNP based Segmentation and Artificial Neural Network

Hand Written Character Recognition using VNP based Segmentation and Artificial Neural Network International Journal of Emerging Engineering Research and Technology Volume 4, Issue 6, June 2016, PP 38-46 ISSN 2349-4395 (Print) & ISSN 2349-4409 (Online) Hand Written Character Recognition using VNP

More information

Design of an Automated Data Entry System for Hand-Filled Forms

Design of an Automated Data Entry System for Hand-Filled Forms Design of an Automated Data Entry System for Hand-Filled Forms Lim Woan Ning,Yap Keem Siah, Marzuki Khalid*, Rubiyah Yusof Centre for Artiflicial ntelligence and Robotics (CARO) Faculty of Electrical Engineering,

More information

Optical Character Recognition (OCR) for Printed Devnagari Script Using Artificial Neural Network

Optical Character Recognition (OCR) for Printed Devnagari Script Using Artificial Neural Network International Journal of Computer Science & Communication Vol. 1, No. 1, January-June 2010, pp. 91-95 Optical Character Recognition (OCR) for Printed Devnagari Script Using Artificial Neural Network Raghuraj

More information

OCR For Handwritten Marathi Script

OCR For Handwritten Marathi Script International Journal of Scientific & Engineering Research Volume 3, Issue 8, August-2012 1 OCR For Handwritten Marathi Script Mrs.Vinaya. S. Tapkir 1, Mrs.Sushma.D.Shelke 2 1 Maharashtra Academy Of Engineering,

More information

OFFLINE SIGNATURE VERIFICATION

OFFLINE SIGNATURE VERIFICATION International Journal of Electronics and Communication Engineering and Technology (IJECET) Volume 8, Issue 2, March - April 2017, pp. 120 128, Article ID: IJECET_08_02_016 Available online at http://www.iaeme.com/ijecet/issues.asp?jtype=ijecet&vtype=8&itype=2

More information

Recognition of Gurmukhi Text from Sign Board Images Captured from Mobile Camera

Recognition of Gurmukhi Text from Sign Board Images Captured from Mobile Camera International Journal of Information & Computation Technology. ISSN 0974-2239 Volume 4, Number 17 (2014), pp. 1839-1845 International Research Publications House http://www. irphouse.com Recognition of

More information

Time Stamp Detection and Recognition in Video Frames

Time Stamp Detection and Recognition in Video Frames Time Stamp Detection and Recognition in Video Frames Nongluk Covavisaruch and Chetsada Saengpanit Department of Computer Engineering, Chulalongkorn University, Bangkok 10330, Thailand E-mail: nongluk.c@chula.ac.th

More information

Neural Network Based Threshold Determination for Malaysia License Plate Character Recognition

Neural Network Based Threshold Determination for Malaysia License Plate Character Recognition Neural Network Based Threshold Determination for Malaysia License Plate Character Recognition M.Fukumi 1, Y.Takeuchi 1, H.Fukumoto 2, Y.Mitsukura 2, and M.Khalid 3 1 University of Tokushima, 2-1, Minami-Josanjima,

More information

DATA EMBEDDING IN TEXT FOR A COPIER SYSTEM

DATA EMBEDDING IN TEXT FOR A COPIER SYSTEM DATA EMBEDDING IN TEXT FOR A COPIER SYSTEM Anoop K. Bhattacharjya and Hakan Ancin Epson Palo Alto Laboratory 3145 Porter Drive, Suite 104 Palo Alto, CA 94304 e-mail: {anoop, ancin}@erd.epson.com Abstract

More information

Fine Classification of Unconstrained Handwritten Persian/Arabic Numerals by Removing Confusion amongst Similar Classes

Fine Classification of Unconstrained Handwritten Persian/Arabic Numerals by Removing Confusion amongst Similar Classes 2009 10th International Conference on Document Analysis and Recognition Fine Classification of Unconstrained Handwritten Persian/Arabic Numerals by Removing Confusion amongst Similar Classes Alireza Alaei

More information

One type of these solutions is automatic license plate character recognition (ALPR).

One type of these solutions is automatic license plate character recognition (ALPR). 1.0 Introduction Modelling, Simulation & Computing Laboratory (msclab) A rapid technical growth in the area of computer image processing has increased the need for an efficient and affordable security,

More information

A Document Image Analysis System on Parallel Processors

A Document Image Analysis System on Parallel Processors A Document Image Analysis System on Parallel Processors Shamik Sural, CMC Ltd. 28 Camac Street, Calcutta 700 016, India. P.K.Das, Dept. of CSE. Jadavpur University, Calcutta 700 032, India. Abstract This

More information

Multi-Layer Perceptron Network For Handwritting English Character Recoginition

Multi-Layer Perceptron Network For Handwritting English Character Recoginition Multi-Layer Perceptron Network For Handwritting English Character Recoginition 1 Mohit Mittal, 2 Tarun Bhalla 1,2 Anand College of Engg & Mgmt., Kapurthala, Punjab, India Abstract Handwriting recognition

More information

A Survey of Problems of Overlapped Handwritten Characters in Recognition process for Gurmukhi Script

A Survey of Problems of Overlapped Handwritten Characters in Recognition process for Gurmukhi Script A Survey of Problems of Overlapped Handwritten Characters in Recognition process for Gurmukhi Script Arwinder Kaur 1, Ashok Kumar Bathla 2 1 M. Tech. Student, CE Dept., 2 Assistant Professor, CE Dept.,

More information

A New Algorithm for Detecting Text Line in Handwritten Documents

A New Algorithm for Detecting Text Line in Handwritten Documents A New Algorithm for Detecting Text Line in Handwritten Documents Yi Li 1, Yefeng Zheng 2, David Doermann 1, and Stefan Jaeger 1 1 Laboratory for Language and Media Processing Institute for Advanced Computer

More information

A System for Automatic Extraction of the User Entered Data from Bankchecks

A System for Automatic Extraction of the User Entered Data from Bankchecks A System for Automatic Extraction of the User Entered Data from Bankchecks ALESSANDRO L. KOERICH 1 LEE LUAN LING 2 1 CEFET/PR Centro Federal de Educação Tecnológica do Paraná Av. Sete de Setembro, 3125,

More information

An Efficient Character Segmentation Based on VNP Algorithm

An Efficient Character Segmentation Based on VNP Algorithm Research Journal of Applied Sciences, Engineering and Technology 4(24): 5438-5442, 2012 ISSN: 2040-7467 Maxwell Scientific organization, 2012 Submitted: March 18, 2012 Accepted: April 14, 2012 Published:

More information

Texture Segmentation by Windowed Projection

Texture Segmentation by Windowed Projection Texture Segmentation by Windowed Projection 1, 2 Fan-Chen Tseng, 2 Ching-Chi Hsu, 2 Chiou-Shann Fuh 1 Department of Electronic Engineering National I-Lan Institute of Technology e-mail : fctseng@ccmail.ilantech.edu.tw

More information

Isolated Handwritten Words Segmentation Techniques in Gurmukhi Script

Isolated Handwritten Words Segmentation Techniques in Gurmukhi Script Isolated Handwritten Words Segmentation Techniques in Gurmukhi Script Galaxy Bansal Dharamveer Sharma ABSTRACT Segmentation of handwritten words is a challenging task primarily because of structural features

More information

CIRCULAR MOIRÉ PATTERNS IN 3D COMPUTER VISION APPLICATIONS

CIRCULAR MOIRÉ PATTERNS IN 3D COMPUTER VISION APPLICATIONS CIRCULAR MOIRÉ PATTERNS IN 3D COMPUTER VISION APPLICATIONS Setiawan Hadi Mathematics Department, Universitas Padjadjaran e-mail : shadi@unpad.ac.id Abstract Geometric patterns generated by superimposing

More information

COMBINING NEURAL NETWORKS FOR SKIN DETECTION

COMBINING NEURAL NETWORKS FOR SKIN DETECTION COMBINING NEURAL NETWORKS FOR SKIN DETECTION Chelsia Amy Doukim 1, Jamal Ahmad Dargham 1, Ali Chekima 1 and Sigeru Omatu 2 1 School of Engineering and Information Technology, Universiti Malaysia Sabah,

More information

MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION

MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION Panca Mudjirahardjo, Rahmadwati, Nanang Sulistiyanto and R. Arief Setyawan Department of Electrical Engineering, Faculty of

More information

Binary Image Processing. Introduction to Computer Vision CSE 152 Lecture 5

Binary Image Processing. Introduction to Computer Vision CSE 152 Lecture 5 Binary Image Processing CSE 152 Lecture 5 Announcements Homework 2 is due Apr 25, 11:59 PM Reading: Szeliski, Chapter 3 Image processing, Section 3.3 More neighborhood operators Binary System Summary 1.

More information

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers A. Salhi, B. Minaoui, M. Fakir, H. Chakib, H. Grimech Faculty of science and Technology Sultan Moulay Slimane

More information

LITERATURE REVIEW. For Indian languages most of research work is performed firstly on Devnagari script and secondly on Bangla script.

LITERATURE REVIEW. For Indian languages most of research work is performed firstly on Devnagari script and secondly on Bangla script. LITERATURE REVIEW For Indian languages most of research work is performed firstly on Devnagari script and secondly on Bangla script. The study of recognition for handwritten Devanagari compound character

More information

II. WORKING OF PROJECT

II. WORKING OF PROJECT Handwritten character Recognition and detection using histogram technique Tanmay Bahadure, Pranay Wekhande, Manish Gaur, Shubham Raikwar, Yogendra Gupta ABSTRACT : Cursive handwriting recognition is a

More information

Segmentation of Kannada Handwritten Characters and Recognition Using Twelve Directional Feature Extraction Techniques

Segmentation of Kannada Handwritten Characters and Recognition Using Twelve Directional Feature Extraction Techniques Segmentation of Kannada Handwritten Characters and Recognition Using Twelve Directional Feature Extraction Techniques 1 Lohitha B.J, 2 Y.C Kiran 1 M.Tech. Student Dept. of ISE, Dayananda Sagar College

More information

1. Introduction. 2. Motivation and Problem Definition. Volume 8 Issue 2, February Susmita Mohapatra

1. Introduction. 2. Motivation and Problem Definition. Volume 8 Issue 2, February Susmita Mohapatra Pattern Recall Analysis of the Hopfield Neural Network with a Genetic Algorithm Susmita Mohapatra Department of Computer Science, Utkal University, India Abstract: This paper is focused on the implementation

More information

[10] Industrial DataMatrix barcodes recognition with a random tilt and rotating the camera

[10] Industrial DataMatrix barcodes recognition with a random tilt and rotating the camera [10] Industrial DataMatrix barcodes recognition with a random tilt and rotating the camera Image processing, pattern recognition 865 Kruchinin A.Yu. Orenburg State University IntBuSoft Ltd Abstract The

More information

Chapter 3 Image Registration. Chapter 3 Image Registration

Chapter 3 Image Registration. Chapter 3 Image Registration Chapter 3 Image Registration Distributed Algorithms for Introduction (1) Definition: Image Registration Input: 2 images of the same scene but taken from different perspectives Goal: Identify transformation

More information

RULE BASED SIGNATURE VERIFICATION AND FORGERY DETECTION

RULE BASED SIGNATURE VERIFICATION AND FORGERY DETECTION RULE BASED SIGNATURE VERIFICATION AND FORGERY DETECTION M. Hanmandlu Multimedia University Jalan Multimedia 63100, Cyberjaya Selangor, Malaysia E-mail:madasu.hanmandlu@mmu.edu.my M. Vamsi Krishna Dept.

More information

Simulation of Zhang Suen Algorithm using Feed- Forward Neural Networks

Simulation of Zhang Suen Algorithm using Feed- Forward Neural Networks Simulation of Zhang Suen Algorithm using Feed- Forward Neural Networks Ritika Luthra Research Scholar Chandigarh University Gulshan Goyal Associate Professor Chandigarh University ABSTRACT Image Skeletonization

More information

A New Approach to Detect and Extract Characters from Off-Line Printed Images and Text

A New Approach to Detect and Extract Characters from Off-Line Printed Images and Text Available online at www.sciencedirect.com Procedia Computer Science 17 (2013 ) 434 440 Information Technology and Quantitative Management (ITQM2013) A New Approach to Detect and Extract Characters from

More information

A Review on Handwritten Character Recognition

A Review on Handwritten Character Recognition IJCST Vo l. 8, Is s u e 1, Ja n - Ma r c h 2017 ISSN : 0976-8491 (Online) ISSN : 2229-4333 (Print) A Review on Handwritten Character Recognition 1 Anisha Sharma, 2 Soumil Khare, 3 Sachin Chavan 1,2,3 Dept.

More information

N.Priya. Keywords Compass mask, Threshold, Morphological Operators, Statistical Measures, Text extraction

N.Priya. Keywords Compass mask, Threshold, Morphological Operators, Statistical Measures, Text extraction Volume, Issue 8, August ISSN: 77 8X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com A Combined Edge-Based Text

More information

NOVATEUR PUBLICATIONS INTERNATIONAL JOURNAL OF INNOVATIONS IN ENGINEERING RESEARCH AND TECHNOLOGY [IJIERT] ISSN: VOLUME 5, ISSUE

NOVATEUR PUBLICATIONS INTERNATIONAL JOURNAL OF INNOVATIONS IN ENGINEERING RESEARCH AND TECHNOLOGY [IJIERT] ISSN: VOLUME 5, ISSUE OPTICAL HANDWRITTEN DEVNAGARI CHARACTER RECOGNITION USING ARTIFICIAL NEURAL NETWORK APPROACH JYOTI A.PATIL Ashokrao Mane Group of Institution, Vathar Tarf Vadgaon, India. DR. SANJAY R. PATIL Ashokrao Mane

More information

Data Hiding in Binary Text Documents 1. Q. Mei, E. K. Wong, and N. Memon

Data Hiding in Binary Text Documents 1. Q. Mei, E. K. Wong, and N. Memon Data Hiding in Binary Text Documents 1 Q. Mei, E. K. Wong, and N. Memon Department of Computer and Information Science Polytechnic University 5 Metrotech Center, Brooklyn, NY 11201 ABSTRACT With the proliferation

More information

International Journal of Advance Research in Engineering, Science & Technology

International Journal of Advance Research in Engineering, Science & Technology Impact Factor (SJIF): 4.542 International Journal of Advance Research in Engineering, Science & Technology e-issn: 2393-9877, p-issn: 2394-2444 Volume 4, Issue 4, April-2017 A Simple Effective Algorithm

More information

Keywords Connected Components, Text-Line Extraction, Trained Dataset.

Keywords Connected Components, Text-Line Extraction, Trained Dataset. Volume 4, Issue 11, November 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Language Independent

More information

Mobile Application with Optical Character Recognition Using Neural Network

Mobile Application with Optical Character Recognition Using Neural Network Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 4, Issue. 1, January 2015,

More information

Varun Manchikalapudi Dept. of Information Tech., V.R. Siddhartha Engg. College (A), Vijayawada, AP, India

Varun Manchikalapudi Dept. of Information Tech., V.R. Siddhartha Engg. College (A), Vijayawada, AP, India Skew Correction and Localisation of Number Plate Using Hough Rectangular Transform Varun Manchikalapudi Dept. of Information Tech., V.R. Siddhartha Engg. College (A), Vijayawada, AP, India Abstract Skew

More information

A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation

A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation K. Roy, U. Pal and B. B. Chaudhuri CVPR Unit; Indian Statistical Institute, Kolkata-108; India umapada@isical.ac.in

More information

Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction

Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction Stefan Müller, Gerhard Rigoll, Andreas Kosmala and Denis Mazurenok Department of Computer Science, Faculty of

More information

Available online at ScienceDirect. Procedia Computer Science 45 (2015 )

Available online at  ScienceDirect. Procedia Computer Science 45 (2015 ) Available online at www.sciencedirect.com ScienceDirect Procedia Computer Science 45 (2015 ) 205 214 International Conference on Advanced Computing Technologies and Applications (ICACTA- 2015) Automatic

More information

Handwritten Hindi Character Recognition System Using Edge detection & Neural Network

Handwritten Hindi Character Recognition System Using Edge detection & Neural Network Handwritten Hindi Character Recognition System Using Edge detection & Neural Network Tanuja K *, Usha Kumari V and Sushma T M Acharya Institute of Technology, Bangalore, India Abstract Handwritten recognition

More information

Handwriting segmentation of unconstrained Oriya text

Handwriting segmentation of unconstrained Oriya text Sādhanā Vol. 31, Part 6, December 2006, pp. 755 769. Printed in India Handwriting segmentation of unconstrained Oriya text N TRIPATHY and U PAL Computer Vision and Pattern Recognition Unit, Indian Statistical

More information

Enhancing the Character Segmentation Accuracy of Bangla OCR using BPNN

Enhancing the Character Segmentation Accuracy of Bangla OCR using BPNN Enhancing the Character Segmentation Accuracy of Bangla OCR using BPNN Shamim Ahmed 1, Mohammod Abul Kashem 2 1 M.S. Student, Department of Computer Science and Engineering, Dhaka University of Engineering

More information

A Hierarchical Pre-processing Model for Offline Handwritten Document Images

A Hierarchical Pre-processing Model for Offline Handwritten Document Images International Journal of Research Studies in Computer Science and Engineering (IJRSCSE) Volume 2, Issue 3, March 2015, PP 41-45 ISSN 2349-4840 (Print) & ISSN 2349-4859 (Online) www.arcjournals.org A Hierarchical

More information

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY A PATH FOR HORIZING YOUR INNOVATIVE WORK HANDWRITTEN DEVANAGARI CHARACTERS RECOGNITION THROUGH SEGMENTATION AND ARTIFICIAL

More information

NOVATEUR PUBLICATIONS INTERNATIONAL JOURNAL OF INNOVATIONS IN ENGINEERING RESEARCH AND TECHNOLOGY [IJIERT] ISSN: VOLUME 2, ISSUE 1 JAN-2015

NOVATEUR PUBLICATIONS INTERNATIONAL JOURNAL OF INNOVATIONS IN ENGINEERING RESEARCH AND TECHNOLOGY [IJIERT] ISSN: VOLUME 2, ISSUE 1 JAN-2015 Offline Handwritten Signature Verification using Neural Network Pallavi V. Hatkar Department of Electronics Engineering, TKIET Warana, India Prof.B.T.Salokhe Department of Electronics Engineering, TKIET

More information

09/11/2017. Morphological image processing. Morphological image processing. Morphological image processing. Morphological image processing (binary)

09/11/2017. Morphological image processing. Morphological image processing. Morphological image processing. Morphological image processing (binary) Towards image analysis Goal: Describe the contents of an image, distinguishing meaningful information from irrelevant one. Perform suitable transformations of images so as to make explicit particular shape

More information

Malaysian License Plate Recognition Artificial Neural Networks and Evolu Computation. The original publication is availabl

Malaysian License Plate Recognition Artificial Neural Networks and Evolu Computation. The original publication is availabl JAIST Reposi https://dspace.j Title Malaysian License Plate Recognition Artificial Neural Networks and Evolu Computation Stephen, Karungaru; Fukumi, Author(s) Minoru; Norio Citation Issue Date 2005-11

More information

Off Line Sinhala Handwriting Recognition with an Application for Postal City Name Recognition

Off Line Sinhala Handwriting Recognition with an Application for Postal City Name Recognition Off Line Sinhala Handwriting Recognition with an Application for Postal City Name Recognition M.L.M Karunanayaka, N.D Kodikara, G.D.S.P Wimalaratne University of Colombo School of Computing, No.35, Reid

More information

An Accurate Method for Skew Determination in Document Images

An Accurate Method for Skew Determination in Document Images DICTA00: Digital Image Computing Techniques and Applications, 1 January 00, Melbourne, Australia. An Accurate Method for Skew Determination in Document Images S. Lowther, V. Chandran and S. Sridharan Research

More information

CHAPTER 8 COMPOUND CHARACTER RECOGNITION USING VARIOUS MODELS

CHAPTER 8 COMPOUND CHARACTER RECOGNITION USING VARIOUS MODELS CHAPTER 8 COMPOUND CHARACTER RECOGNITION USING VARIOUS MODELS 8.1 Introduction The recognition systems developed so far were for simple characters comprising of consonants and vowels. But there is one

More information

Robust line segmentation for handwritten documents

Robust line segmentation for handwritten documents Robust line segmentation for handwritten documents Kamal Kuzhinjedathu, Harish Srinivasan and Sargur Srihari Center of Excellence for Document Analysis and Recognition (CEDAR) University at Buffalo, State

More information

AN EFFICIENT BINARIZATION TECHNIQUE FOR FINGERPRINT IMAGES S. B. SRIDEVI M.Tech., Department of ECE

AN EFFICIENT BINARIZATION TECHNIQUE FOR FINGERPRINT IMAGES S. B. SRIDEVI M.Tech., Department of ECE AN EFFICIENT BINARIZATION TECHNIQUE FOR FINGERPRINT IMAGES S. B. SRIDEVI M.Tech., Department of ECE sbsridevi89@gmail.com 287 ABSTRACT Fingerprint identification is the most prominent method of biometric

More information

An ICA based Approach for Complex Color Scene Text Binarization

An ICA based Approach for Complex Color Scene Text Binarization An ICA based Approach for Complex Color Scene Text Binarization Siddharth Kherada IIIT-Hyderabad, India siddharth.kherada@research.iiit.ac.in Anoop M. Namboodiri IIIT-Hyderabad, India anoop@iiit.ac.in

More information

Handwritten Character Recognition with Feedback Neural Network

Handwritten Character Recognition with Feedback Neural Network Apash Roy et al / International Journal of Computer Science & Engineering Technology (IJCSET) Handwritten Character Recognition with Feedback Neural Network Apash Roy* 1, N R Manna* *Department of Computer

More information

Offline Signature verification and recognition using ART 1

Offline Signature verification and recognition using ART 1 Offline Signature verification and recognition using ART 1 R. Sukanya K.Malathy M.E Infant Jesus College of Engineering And Technology Abstract: The main objective of this project is signature verification

More information

A Real-Time Hand Gesture Recognition for Dynamic Applications

A Real-Time Hand Gesture Recognition for Dynamic Applications e-issn 2455 1392 Volume 2 Issue 2, February 2016 pp. 41-45 Scientific Journal Impact Factor : 3.468 http://www.ijcter.com A Real-Time Hand Gesture Recognition for Dynamic Applications Aishwarya Mandlik

More information

Solving Word Jumbles

Solving Word Jumbles Solving Word Jumbles Debabrata Sengupta, Abhishek Sharma Department of Electrical Engineering, Stanford University { dsgupta, abhisheksharma }@stanford.edu Abstract In this report we propose an algorithm

More information

Handwritten Hindi Numerals Recognition System

Handwritten Hindi Numerals Recognition System CS365 Project Report Handwritten Hindi Numerals Recognition System Submitted by: Akarshan Sarkar Kritika Singh Project Mentor: Prof. Amitabha Mukerjee 1 Abstract In this project, we consider the problem

More information

Pedestrian Detection Using Correlated Lidar and Image Data EECS442 Final Project Fall 2016

Pedestrian Detection Using Correlated Lidar and Image Data EECS442 Final Project Fall 2016 edestrian Detection Using Correlated Lidar and Image Data EECS442 Final roject Fall 2016 Samuel Rohrer University of Michigan rohrer@umich.edu Ian Lin University of Michigan tiannis@umich.edu Abstract

More information

Artifacts and Textured Region Detection

Artifacts and Textured Region Detection Artifacts and Textured Region Detection 1 Vishal Bangard ECE 738 - Spring 2003 I. INTRODUCTION A lot of transformations, when applied to images, lead to the development of various artifacts in them. In

More information

CSE 152 Lecture 7. Intro Computer Vision

CSE 152 Lecture 7. Intro Computer Vision Introduction to Computer Vision CSE 152 Lecture 7 Binary Tracking for Robot Control Binary System Summary 1. Acquire images and binarize (tresholding, color labels, etc.). 2. Possibly clean up image using

More information

Classification of objects from Video Data (Group 30)

Classification of objects from Video Data (Group 30) Classification of objects from Video Data (Group 30) Sheallika Singh 12665 Vibhuti Mahajan 12792 Aahitagni Mukherjee 12001 M Arvind 12385 1 Motivation Video surveillance has been employed for a long time

More information

A Simple Text-line segmentation Method for Handwritten Documents

A Simple Text-line segmentation Method for Handwritten Documents A Simple Text-line segmentation Method for Handwritten Documents M.Ravi Kumar Assistant professor Shankaraghatta-577451 R. Pradeep Shankaraghatta-577451 Prasad Babu Shankaraghatta-5774514th B.S.Puneeth

More information

Character Recognition Using Matlab s Neural Network Toolbox

Character Recognition Using Matlab s Neural Network Toolbox Character Recognition Using Matlab s Neural Network Toolbox Kauleshwar Prasad, Devvrat C. Nigam, Ashmika Lakhotiya and Dheeren Umre B.I.T Durg, India Kauleshwarprasad2gmail.com, devnigam24@gmail.com,ashmika22@gmail.com,

More information

Improvement of SURF Feature Image Registration Algorithm Based on Cluster Analysis

Improvement of SURF Feature Image Registration Algorithm Based on Cluster Analysis Sensors & Transducers 2014 by IFSA Publishing, S. L. http://www.sensorsportal.com Improvement of SURF Feature Image Registration Algorithm Based on Cluster Analysis 1 Xulin LONG, 1,* Qiang CHEN, 2 Xiaoya

More information

Effects Of Shadow On Canny Edge Detection through a camera

Effects Of Shadow On Canny Edge Detection through a camera 1523 Effects Of Shadow On Canny Edge Detection through a camera Srajit Mehrotra Shadow causes errors in computer vision as it is difficult to detect objects that are under the influence of shadows. Shadow

More information

DEVELOPMENT OF VISION-BASED HANDICAPPED LOGO REGONITION SYSTEM FOR DISABLED PARKING

DEVELOPMENT OF VISION-BASED HANDICAPPED LOGO REGONITION SYSTEM FOR DISABLED PARKING DEVELOPMENT OF VISION-BASED HANDICAPPED LOGO REGONITION SYSTEM FOR DISABLED PARKING Mohd Sahdan Bin Abd Ghani, Chee Kiang Lam and Kenneth Sundaraj School of Mechatronic Engineering, Universiti Malaysia

More information

Auto-Digitizer for Fast Graph-to-Data Conversion

Auto-Digitizer for Fast Graph-to-Data Conversion Auto-Digitizer for Fast Graph-to-Data Conversion EE 368 Final Project Report, Winter 2018 Deepti Sanjay Mahajan dmahaj@stanford.edu Sarah Pao Radzihovsky sradzi13@stanford.edu Ching-Hua (Fiona) Wang chwang9@stanford.edu

More information

Visual object classification by sparse convolutional neural networks

Visual object classification by sparse convolutional neural networks Visual object classification by sparse convolutional neural networks Alexander Gepperth 1 1- Ruhr-Universität Bochum - Institute for Neural Dynamics Universitätsstraße 150, 44801 Bochum - Germany Abstract.

More information

Evaluation of Moving Object Tracking Techniques for Video Surveillance Applications

Evaluation of Moving Object Tracking Techniques for Video Surveillance Applications International Journal of Current Engineering and Technology E-ISSN 2277 4106, P-ISSN 2347 5161 2015INPRESSCO, All Rights Reserved Available at http://inpressco.com/category/ijcet Research Article Evaluation

More information

Structural Feature Extraction to recognize some of the Offline Isolated Handwritten Gujarati Characters using Decision Tree Classifier

Structural Feature Extraction to recognize some of the Offline Isolated Handwritten Gujarati Characters using Decision Tree Classifier Structural Feature Extraction to recognize some of the Offline Isolated Handwritten Gujarati Characters using Decision Tree Classifier Hetal R. Thaker Atmiya Institute of Technology & science, Kalawad

More information

A Model-based Line Detection Algorithm in Documents

A Model-based Line Detection Algorithm in Documents A Model-based Line Detection Algorithm in Documents Yefeng Zheng, Huiping Li, David Doermann Laboratory for Language and Media Processing Institute for Advanced Computer Studies University of Maryland,

More information

User s Manual. A Revolution in OCR Software

User s Manual. A Revolution in OCR Software User s Manual A Revolution in OCR Software Microsoft, Windows, Windows NT, Windows 2000, Windows XP, Visual Basic, Microsoft.NET, Visual C++, Visual C#, and ActiveX are either trademarks or registered

More information

Character Segmentation and Recognition Algorithm of Text Region in Steel Images

Character Segmentation and Recognition Algorithm of Text Region in Steel Images Character Segmentation and Recognition Algorithm of Text Region in Steel Images Keunhwi Koo, Jong Pil Yun, SungHoo Choi, JongHyun Choi, Doo Chul Choi, Sang Woo Kim Division of Electrical and Computer Engineering

More information

Fabric Defect Detection Based on Computer Vision

Fabric Defect Detection Based on Computer Vision Fabric Defect Detection Based on Computer Vision Jing Sun and Zhiyu Zhou College of Information and Electronics, Zhejiang Sci-Tech University, Hangzhou, China {jings531,zhouzhiyu1993}@163.com Abstract.

More information

International Journal of Advance Research in Engineering, Science & Technology

International Journal of Advance Research in Engineering, Science & Technology Impact Factor (SJIF): 3.632 International Journal of Advance Research in Engineering, Science & Technology e-issn: 2393-9877, p-issn: 2394-2444 (Special Issue for ITECE 2016) Analysis and Implementation

More information

Character Recognition of High Security Number Plates Using Morphological Operator

Character Recognition of High Security Number Plates Using Morphological Operator Character Recognition of High Security Number Plates Using Morphological Operator Kamaljit Kaur * Department of Computer Engineering, Baba Banda Singh Bahadur Polytechnic College Fatehgarh Sahib,Punjab,India

More information

Automatic License Plate Detection and Character Extraction with Adaptive Threshold and Projections

Automatic License Plate Detection and Character Extraction with Adaptive Threshold and Projections Automatic License Plate Detection and Character Extraction with Adaptive Threshold and Projections DANIEL GONZÁLEZ BALDERRAMA, OSSLAN OSIRIS VERGARA VILLEGAS, HUMBERTO DE JESÚS OCHOA DOMÍNGUEZ 2, VIANEY

More information

BRIEF Features for Texture Segmentation

BRIEF Features for Texture Segmentation BRIEF Features for Texture Segmentation Suraya Mohammad 1, Tim Morris 2 1 Communication Technology Section, Universiti Kuala Lumpur - British Malaysian Institute, Gombak, Selangor, Malaysia 2 School of

More information

Building Multi Script OCR for Brahmi Scripts: Selection of Efficient Features

Building Multi Script OCR for Brahmi Scripts: Selection of Efficient Features Building Multi Script OCR for Brahmi Scripts: Selection of Efficient Features Md. Abul Hasnat Center for Research on Bangla Language Processing (CRBLP) Center for Research on Bangla Language Processing

More information

ABJAD: AN OFF-LINE ARABIC HANDWRITTEN RECOGNITION SYSTEM

ABJAD: AN OFF-LINE ARABIC HANDWRITTEN RECOGNITION SYSTEM ABJAD: AN OFF-LINE ARABIC HANDWRITTEN RECOGNITION SYSTEM RAMZI AHMED HARATY and HICHAM EL-ZABADANI Lebanese American University P.O. Box 13-5053 Chouran Beirut, Lebanon 1102 2801 Phone: 961 1 867621 ext.

More information

Preprocessing of Gurmukhi Strokes in Online Handwriting Recognition

Preprocessing of Gurmukhi Strokes in Online Handwriting Recognition 2012 3rd International Conference on Information Security and Artificial Intelligence (ISAI 2012) IPCSIT vol. 56 (2012) (2012) IACSIT Press, Singapore DOI: 10.7763/IPCSIT.2012.V56.30 Preprocessing of Gurmukhi

More information

Extracting Layers and Recognizing Features for Automatic Map Understanding. Yao-Yi Chiang

Extracting Layers and Recognizing Features for Automatic Map Understanding. Yao-Yi Chiang Extracting Layers and Recognizing Features for Automatic Map Understanding Yao-Yi Chiang 0 Outline Introduction/ Problem Motivation Map Processing Overview Map Decomposition Feature Recognition Discussion

More information