Information Extraction from Signboards

Size: px
Start display at page:

Download "Information Extraction from Signboards"

Transcription

1 Information Extraction from Signboards By Anil Kumar Meena 2014CS10210 Under Prof. M. Balakrishnan Guided by Anupam Sobti and Rajesh Kedia A Report submitted in partial fulfillment of of the requirements for the degree of Bachelor of Technology Computer Science Dept. IIT Delhi India

2 Information Extraction from signboards Arrow detection and OCR Abstract This is the age of information. The future is here. But unfortunately future doesn t come to everyone at the same pace. While cloud services provide scalable, state-of-the-art solutions to vision problems, they are not accessible to everyone. Even today less than 30% of indian population has access to internet which is a highly generous estimate after accounting for double counting. This project is an attempt to OCR signboards locally on a pi and provide results comparable to that on popular cloud services. 1

3 Acknowledgement I am using this opportunity to express my gratitude Prof M. Balakrishnan and everyone else in MAVI team who supported me throughout the course of this project. I am thankful for their aspiring guidance, invaluably constructive criticism and friendy advice during the project work. I am sincerely grateful to them for sharing their truthful and illuminating views on a number of issues related to the project. I express my warm thanks to Mr. Anupam Sobti and Mr. Chetan Arora for their guidance. Thank you, Anil Kumar Meena 2

4 Contents 1 Introduction Signboard detection(prior work) Perspective transform Rescaling Text Extraction Binarization Tesseract parameters Spell fixer Results Arrow Detection Procedure Results Time Analysis Arrow detection Text extraction Final thoughts 11 3

5 1. Introduction Information Extraction from signboards consists of two separate components. Directional information from arrows and textual data from the given text. This project divides the two after some initial pre-processing on the image which are : 1. Signboard detection 2. Perspective transform 3. Rescaling 1.1. Signboard detection(prior work) As my predecessors have worked on this project before me, they built a novel method for detection of signboards in images using white and blue detection and then finding the smallest bounding rectangle. I would not go too deeper in it s working as it s beyond the scope of this report. Results are as shown below. Type Number Percentage True Positive % True Negative % False Positive 4 1.6% False Negative % Table 1: Signboards detection results 1.2. Perspective transform Since the viewer can be looking at the signboard from different angles, the images being sent to tesseract can be rotated. This often results in incorrect results. So I modified the SB detection algorithm to account for such cases and warp before exporting. See Figure 1 for reference Rescaling Tesseract is known to perform poorly on low dpi images and so as a thumb rule, it s a better idea in general to upscale images before passing it on to the OCR. 4

6 Figure 1: Old bounding box(pink) and new one(red) 2. Text Extraction Tesseract is arguably the best open source OCR out there. However, since Google bought it from HP in the 90s and made it open source, there hasn t been much progress. In fact, it s original page segmentation and other image processing algorithms used prior to passing the image to the core OCR were never made public and are owned by HP till date. This hole left in a complete software made incomplete open source was never filled completely even after years of open source contributions. This is why tesseract requires a high level of customization and pre-processing of images to provide readable results Binarization Tesseract takes single channel grayscale images which means we need to binarize our natural images. For binarization, we employ text binarization based on the paper by Kasar[1]. Briefly, the method employs an edge-based connected component approach and automatically determines a threshold for each component. It has several advantages over existing binarization methods. Firstly, the method is applicable to images having text of widely varying degrees of exposure, usually not handled by global binarization methods. Thirdly, the method automatically computes the threshold for binarization and the logic for inverting the output from the image data and does not require any input parameter. Since we don t even have to provide kernel size as in case of local binarization, and all parameters are automatically computed according to each component s individual requirement, this method is particularly useful for our 5

7 use case as it allows signboard images taken from varying distances having varying exposures to be binarized accordingly Tesseract parameters Although tesseract is trained for English and Hindi out of the box, since it has to work universally, it has way too many characters, dictionary bigrams and more. Thus we reduce the overall possibilities for tesseract to provide better results. First, we reduce the scope of tesseract to a much smaller set of characters. This can be done through configurations, explicit alterations in trained data by tesseract, or custom training Configurations are a good way to fine tune tesseract but in some cases tesseract doesn t give enough power to them. Although, custom training sounds great, the trained data by tesseract is very good and works great in our use case once we make the necessary alterations. Secondly, we use an exhaustive custom dictionary of words and provide it as dictionary to tesseract trained data. Then we set penalty for non dictionary words. However, even if the penalty is set to max, it does not mean the result will always be from dictionary. Tesseract only uses dictionary as a hint. This is why we add a spell fixer after getting results from tesseract. As a note to whoever might continue this project, page segmentation is a major problem as described at the beginning of this section. So, we parse the document in sparse text and osd mode to find as much text as possible rather than forcing it. Also, order of languages is important while calling tesseract. tesseract tessdata-dir././testing/bilingual.jpg./testing/bilingual-enghin -l eng+hin (1) tesseract tessdata-dir././testing/bilingual.jpg./testing/bilingual-enghin -l hin+eng (2) Commands 1 and 2 can result in entirely different results. Currently we use hindi as primary even if our motive is to get English only since we get better results that way. 6

8 2.3. Spell fixer After tesseract finishes, we take the text and run a spell fixing script which uses jaro distance to find similarity between the word and words in dictionary. The word with maximum similarity is chosen to replace the word in final result Results In table 3, we can see the OCR results for 4 types of images showing improvements by addition of perspective transform and exhaustive dictionary (this includes dictionary in tesseract and spell fixer both). Type Complete w/d w/p English Hindi English Hindi English Hindi Skew(165) 69.28% 53.14% 48.15% 29.92% 57.32% 40.85% Glare(41) 34.42% 22.56% 25.48% 13.84% 29.31% 18.31% Shadow(162) 71.22% 53.83% 48.94% 31.54% 65.61% 47.42% Blur(27) 23.96% 13.35% 20.61% 11.30% 17.30% 8.01% Full Dataset 70.18% 52.44% 47.85% 30.19% 60.04% 43.81% Table 2: OCR results, Complete, without dictionary, and without perspective transform 3. Arrow Detection This module deals with detecting arrows from signboards and figuring out their orientations. There are multiple possible types of arrows in our dataset 3.1. Procedure Listed below are the steps followed to get the results. 1. Template Matching 2. Thresholding 3. Dilation and erosion 4. Edge detection 5. Hough transform 7

9 (a) Match template (b) Erode and dilate (c) Canny edge detect Figure 2: Steps in arrow detection Firstly, we match the image against templates with iterative scaling to account for unknown size of the arrow, this also cuts down on the amount of area we have to do rest of the processing on. Secondly, we erode and dilate in case the arrow is not a single connected component after binarization. This also helps denoise the image, and since noise can lead to false positives, it is a necessary measure. Thirdly, we do canny edge detection on the arrow, from which we get houghlines. Lastly, we do checks on rho theta values from our known values to find the orientation of the arrow. Type Number Percentage True Positive % True Negative 38 95% False Positive % False Negative 2 5% Table 3: Arrow detection results (a) Blur (b) Glare Figure 3: Failure cases 8

10 3.2. Results As shown in table 2, the used procedure works fairly well but while this approach works in most cases, it often fails with blurry images since houghlines finds too many or too less lines as the figure is a distorted blob after erosion and dilation rather than an arrow. With glare, binarization often ends up giving white for a bigger connected component of a larger and distorted shape. 4. Time Analysis The results have been calculated on an Intel Core i5-4210u 1.70GHz with 8GB memory and 16GB swap which remained unused during the entire process. GPU was disabled during all tests Arrow detection Time taken in arrow detection is shown in Figure 3. As we can see, although it seems to stay under a second for most cases, for over 368 images, it takes more than 2 seconds, which is a considerable amount of time. This is because we have multiple templates and orientations of arrows, using iterative scaling increases time exponentially for increase in input image size Text extraction Text extraction takes time in 4 stages, namely, 1. SB detection 2. Pre-processing 3. OCR 4. Spell fixing As we can see through the graphs, SB detection and spell fixing are not contributing significantly to the total time for text extraction. OCR and Preprocessing on the other hand, can take upto 4.5 and 3.5 seconds respectively. 9

11 Figure 4: Time taken in arrow detection Figure 5: Time taken for text 10

12 5. Final thoughts On a good note, as we realized through open house, even though the accuracy might be low, in real practice, we do not have to give results every time. We can just set a threshold on similarity index below which we do not give results and keep capturing frames. But there are also shortcomings. For example, iterative scaling for template matching takes over 8 seconds at times even on laptops. And in real applications where types of arrows would only increase in number, time taken would go even higher. [1] A. G. R. T Kasar, J Kumar, Font and background color independent text binarization, IISc Bangalore,

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

Mobility Assistant for Visually Impaired(MAVI) on Cloud

Mobility Assistant for Visually Impaired(MAVI) on Cloud Mobility Assistant for Visually Impaired(MAVI) on Cloud A thesis submitted in partial fulfillment of the requirements for the degree of BACHELOR OF TECHNOLOGY & MASTER OF TECHNOLOGY in Computer Science

More information

HCR Using K-Means Clustering Algorithm

HCR Using K-Means Clustering Algorithm HCR Using K-Means Clustering Algorithm Meha Mathur 1, Anil Saroliya 2 Amity School of Engineering & Technology Amity University Rajasthan, India Abstract: Hindi is a national language of India, there are

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

Gesture based PTZ camera control

Gesture based PTZ camera control Gesture based PTZ camera control Report submitted in May 2014 to the department of Computer Science and Engineering of National Institute of Technology Rourkela in partial fulfillment of the requirements

More information

Your Flowchart Secretary: Real-Time Hand-Written Flowchart Converter

Your Flowchart Secretary: Real-Time Hand-Written Flowchart Converter Your Flowchart Secretary: Real-Time Hand-Written Flowchart Converter Qian Yu, Rao Zhang, Tien-Ning Hsu, Zheng Lyu Department of Electrical Engineering { qiany, zhangrao, tiening, zhenglyu} @stanford.edu

More information

Edges and Binary Images

Edges and Binary Images CS 699: Intro to Computer Vision Edges and Binary Images Prof. Adriana Kovashka University of Pittsburgh September 5, 205 Plan for today Edge detection Binary image analysis Homework Due on 9/22, :59pm

More information

OCR and OCV. Tom Brennan Artemis Vision Artemis Vision 781 Vallejo St Denver, CO (303)

OCR and OCV. Tom Brennan Artemis Vision Artemis Vision 781 Vallejo St Denver, CO (303) OCR and OCV Tom Brennan Artemis Vision Artemis Vision 781 Vallejo St Denver, CO 80204 (303)832-1111 tbrennan@artemisvision.com www.artemisvision.com About Us Machine Vision Integrator Turnkey Systems OEM

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

E-BALL Technology Submitted in partial fulfillment of the requirement for the award of

E-BALL Technology Submitted in partial fulfillment of the requirement for the award of A Seminar report on E-BALL Technology Submitted in partial fulfillment of the requirement for the award of Degree of Computer Science SUBMITTED TO: SUBMITTED BY: www.studymafia.org www.studymafia.org Preface

More information

Mobile Camera Based Calculator

Mobile Camera Based Calculator Mobile Camera Based Calculator Liwei Wang Jingyi Dai Li Du Department of Electrical Engineering Department of Electrical Engineering Department of Electrical Engineering Stanford University Stanford University

More information

Advanced Vision System Integration. David Dechow Staff Engineer, Intelligent Robotics/Machine Vision FANUC America Corporation

Advanced Vision System Integration. David Dechow Staff Engineer, Intelligent Robotics/Machine Vision FANUC America Corporation Advanced Vision System Integration David Dechow Staff Engineer, Intelligent Robotics/Machine Vision FANUC America Corporation Advanced Vision System Integration INTRODUCTION AND REVIEW Introduction and

More information

AUTONOMOUS IMAGE EXTRACTION AND SEGMENTATION OF IMAGE USING UAV S

AUTONOMOUS IMAGE EXTRACTION AND SEGMENTATION OF IMAGE USING UAV S AUTONOMOUS IMAGE EXTRACTION AND SEGMENTATION OF IMAGE USING UAV S Radha Krishna Rambola, Associate Professor, NMIMS University, India Akash Agrawal, Student at NMIMS University, India ABSTRACT Due to the

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

Image Processing: Final Exam November 10, :30 10:30

Image Processing: Final Exam November 10, :30 10:30 Image Processing: Final Exam November 10, 2017-8:30 10:30 Student name: Student number: Put your name and student number on all of the papers you hand in (if you take out the staple). There are always

More information

Layout Segmentation of Scanned Newspaper Documents

Layout Segmentation of Scanned Newspaper Documents , pp-05-10 Layout Segmentation of Scanned Newspaper Documents A.Bandyopadhyay, A. Ganguly and U.Pal CVPR Unit, Indian Statistical Institute 203 B T Road, Kolkata, India. Abstract: Layout segmentation algorithms

More information

CS 231A Computer Vision (Fall 2012) Problem Set 3

CS 231A Computer Vision (Fall 2012) Problem Set 3 CS 231A Computer Vision (Fall 2012) Problem Set 3 Due: Nov. 13 th, 2012 (2:15pm) 1 Probabilistic Recursion for Tracking (20 points) In this problem you will derive a method for tracking a point of interest

More information

Credit Card Processing Using Cell Phone Images

Credit Card Processing Using Cell Phone Images Credit Card Processing Using Cell Phone Images Keshav Datta Department of Electrical Engineering Stanford University Stanford, CA keshavd@stanford.edu Abstract A new method to extract credit card information

More information

Automatic License Plate Recognition

Automatic License Plate Recognition Nijad Ashraf, Sajjad KM, Shehzad Abdulla, Saalim Jabir Dept. of CSE, MESCE Guide: Sajith N July 13, 2010 Outline 1 2 3 4 Design Licensing 5 Standardization Image Quality 6 Language Libraries Others 7 Otsu

More information

SKEW DETECTION AND CORRECTION

SKEW DETECTION AND CORRECTION CHAPTER 3 SKEW DETECTION AND CORRECTION When the documents are scanned through high speed scanners, some amount of tilt is unavoidable either due to manual feed or auto feed. The tilt angle induced during

More information

Part-Based Skew Estimation for Mathematical Expressions

Part-Based Skew Estimation for Mathematical Expressions Soma Shiraishi, Yaokai Feng, and Seiichi Uchida shiraishi@human.ait.kyushu-u.ac.jp {fengyk,uchida}@ait.kyushu-u.ac.jp Abstract We propose a novel method for the skew estimation on text images containing

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

Automatic License Plate Recognition

Automatic License Plate Recognition Interim Presentation Nijad Ashraf, Sajjad KM, Shehzad Abdulla, Saalim Jabir Dept. of CSE, MESCE Guide: Sajith N June 22, 2010 Outline 1 Outline 1 2 Outline 1 2 3 Outline 1 2 3 4 Design Licensing Outline

More information

SECTION 5 IMAGE PROCESSING 2

SECTION 5 IMAGE PROCESSING 2 SECTION 5 IMAGE PROCESSING 2 5.1 Resampling 3 5.1.1 Image Interpolation Comparison 3 5.2 Convolution 3 5.3 Smoothing Filters 3 5.3.1 Mean Filter 3 5.3.2 Median Filter 4 5.3.3 Pseudomedian Filter 6 5.3.4

More information

Translation of Text Oriented Signboard Images from Mobile Phone Camera

Translation of Text Oriented Signboard Images from Mobile Phone Camera World Engineering & Applied Sciences Journal 6 (3): 147-151, 2015 ISSN 2079-2204 IDOSI Publications, 2015 DOI: 10.5829/idosi.weasj.2015.6.3.22210 Translation of Text Oriented Signboard Images from Mobile

More information

SPEED OPTIMIZATION OF CT-BASED MICROSTRUCTURE DETERMINATION USING MATRIX DECOMPOSITION

SPEED OPTIMIZATION OF CT-BASED MICROSTRUCTURE DETERMINATION USING MATRIX DECOMPOSITION SPEED OPTIMIZATION OF CT-BASED MICROSTRUCTURE DETERMINATION USING MATRIX DECOMPOSITION Simon Kranzer, Gernot Standfest, Karl Entacher School of Information Technologies and Systems-Management Salzburg

More information

Image Processing Fundamentals. Nicolas Vazquez Principal Software Engineer National Instruments

Image Processing Fundamentals. Nicolas Vazquez Principal Software Engineer National Instruments Image Processing Fundamentals Nicolas Vazquez Principal Software Engineer National Instruments Agenda Objectives and Motivations Enhancing Images Checking for Presence Locating Parts Measuring Features

More information

Perspective Correction Methods for Camera-Based Document Analysis

Perspective Correction Methods for Camera-Based Document Analysis Perspective Correction Methods for Camera-Based Document Analysis L. Jagannathan and C. V. Jawahar Center for Visual Information Technology International Institute of Information Technology Gachibowli,

More information

Carmen Alonso Montes 23rd-27th November 2015

Carmen Alonso Montes 23rd-27th November 2015 Practical Computer Vision: Theory & Applications 23rd-27th November 2015 Wrap up Today, we are here 2 Learned concepts Hough Transform Distance mapping Watershed Active contours 3 Contents Wrap up Object

More information

IMPLEMENTING ON OPTICAL CHARACTER RECOGNITION USING MEDICAL TABLET FOR BLIND PEOPLE

IMPLEMENTING ON OPTICAL CHARACTER RECOGNITION USING MEDICAL TABLET FOR BLIND PEOPLE Impact Factor (SJIF): 5.301 International Journal of Advance Research in Engineering, Science & Technology e-issn: 2393-9877, p-issn: 2394-2444 Volume 5, Issue 3, March-2018 IMPLEMENTING ON OPTICAL CHARACTER

More information

Eyes extraction from facial images using edge density

Eyes extraction from facial images using edge density Loughborough University Institutional Repository Eyes extraction from facial images using edge density This item was submitted to Loughborough University's Institutional Repository by the/an author. Citation:

More information

Technical Arts 101 Prof. Anupam Saxena Department of Mechanical engineering Indian Institute of Technology, Kanpur. Lecture - 7 Think and Analyze

Technical Arts 101 Prof. Anupam Saxena Department of Mechanical engineering Indian Institute of Technology, Kanpur. Lecture - 7 Think and Analyze Technical Arts 101 Prof. Anupam Saxena Department of Mechanical engineering Indian Institute of Technology, Kanpur Lecture - 7 Think and Analyze Last time I asked you to come up with a single funniest

More information

CS 5540 Spring 2013 Assignment 3, v1.0 Due: Apr. 24th 11:59PM

CS 5540 Spring 2013 Assignment 3, v1.0 Due: Apr. 24th 11:59PM 1 Introduction In this programming project, we are going to do a simple image segmentation task. Given a grayscale image with a bright object against a dark background and we are going to do a binary decision

More information

AUTOMATED STUDENT S ATTENDANCE ENTERING SYSTEM BY ELIMINATING FORGE SIGNATURES

AUTOMATED STUDENT S ATTENDANCE ENTERING SYSTEM BY ELIMINATING FORGE SIGNATURES AUTOMATED STUDENT S ATTENDANCE ENTERING SYSTEM BY ELIMINATING FORGE SIGNATURES K. P. M. L. P. Weerasinghe 149235H Faculty of Information Technology University of Moratuwa June 2017 AUTOMATED STUDENT S

More information

Text line Segmentation of Curved Document Images

Text line Segmentation of Curved Document Images RESEARCH ARTICLE S OPEN ACCESS Text line Segmentation of Curved Document Images Anusree.M *, Dhanya.M.Dhanalakshmy ** * (Department of Computer Science, Amrita Vishwa Vidhyapeetham, Coimbatore -641 11)

More information

Finger Print Enhancement Using Minutiae Based Algorithm

Finger Print Enhancement Using Minutiae Based Algorithm 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. 3, Issue. 8, August 2014,

More information

Keywords: Thresholding, Morphological operations, Image filtering, Adaptive histogram equalization, Ceramic tile.

Keywords: Thresholding, Morphological operations, Image filtering, Adaptive histogram equalization, Ceramic tile. Volume 3, Issue 7, July 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Blobs and Cracks

More information

Project Final Report

Project Final Report Project Final Report Automatic Number Plate Recognition BSc (Hons) Software Development Year 4 Student name: Michael Reid Student ID: C00112726 Project supervisor: Mr. Nigel Whyte Table of Contents 1 Introduction...

More information

(Refer Slide Time: 01.26)

(Refer Slide Time: 01.26) Data Structures and Algorithms Dr. Naveen Garg Department of Computer Science and Engineering Indian Institute of Technology, Delhi Lecture # 22 Why Sorting? Today we are going to be looking at sorting.

More information

CS 223B Computer Vision Problem Set 3

CS 223B Computer Vision Problem Set 3 CS 223B Computer Vision Problem Set 3 Due: Feb. 22 nd, 2011 1 Probabilistic Recursion for Tracking In this problem you will derive a method for tracking a point of interest through a sequence of images.

More information

INTELLIGENT transportation systems have a significant

INTELLIGENT transportation systems have a significant INTL JOURNAL OF ELECTRONICS AND TELECOMMUNICATIONS, 205, VOL. 6, NO. 4, PP. 35 356 Manuscript received October 4, 205; revised November, 205. DOI: 0.55/eletel-205-0046 Efficient Two-Step Approach for Automatic

More information

So, coming back to this picture where three levels of memory are shown namely cache, primary memory or main memory and back up memory.

So, coming back to this picture where three levels of memory are shown namely cache, primary memory or main memory and back up memory. Computer Architecture Prof. Anshul Kumar Department of Computer Science and Engineering Indian Institute of Technology, Delhi Lecture - 31 Memory Hierarchy: Virtual Memory In the memory hierarchy, after

More information

imovie 11 Basics Open imovie To start a new project, click on File and select New Project. Type the name of the project. Click Create. Version 9.0.

imovie 11 Basics Open imovie To start a new project, click on File and select New Project. Type the name of the project. Click Create. Version 9.0. Open imovie imovie 11 Basics Version 9.0.3 To start a new project, click on File and select New Project. Type the name of the project. Click Create. 1. Music and Sound Effects 3. Title 5. Map, Background,

More information

Problem Solving through Programming In C Prof. Anupam Basu Department of Computer Science & Engineering Indian Institute of Technology, Kharagpur

Problem Solving through Programming In C Prof. Anupam Basu Department of Computer Science & Engineering Indian Institute of Technology, Kharagpur Problem Solving through Programming In C Prof. Anupam Basu Department of Computer Science & Engineering Indian Institute of Technology, Kharagpur Lecture 18 Switch Statement (Contd.) And Introduction to

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

Cloud Based Framework for Rich Mobile Application

Cloud Based Framework for Rich Mobile Application Cloud Based Framework for Rich Mobile Application by Andrew Williams (ID: 29003739), Krishna Sharma (ID:), and Roberto Fonseca (ID: 51324561) CS 230 Distributed Systems Project Champion: Reza Rahimi Prof.

More information

Image-Based Competitive Printed Circuit Board Analysis

Image-Based Competitive Printed Circuit Board Analysis Image-Based Competitive Printed Circuit Board Analysis Simon Basilico Department of Electrical Engineering Stanford University Stanford, CA basilico@stanford.edu Ford Rylander Department of Electrical

More information

Writing Cover Letters

Writing Cover Letters Writing Cover Letters Communicating with Employers What is a cover letter? A cover letter is a document submitted with a job application explaining the applicant s credentials and interest in the open

More information

FRAGMENTATION OF HANDWRITTEN TOUCHING CHARACTERS IN DEVANAGARI SCRIPT

FRAGMENTATION OF HANDWRITTEN TOUCHING CHARACTERS IN DEVANAGARI SCRIPT International Journal of Information Technology, Modeling and Computing (IJITMC) Vol. 2, No. 1, February 2014 FRAGMENTATION OF HANDWRITTEN TOUCHING CHARACTERS IN DEVANAGARI SCRIPT Shuchi Kapoor 1 and Vivek

More information

Industrial Marking and Labeling, Inc. with all fonts converted to outlines or

Industrial Marking and Labeling, Inc.   with all fonts converted to outlines or 11490 South 1 53r d Street O maha, N E 681 3 8 create a high quality label from what you can supply us. If you have any questions or concerns feel free to contact us and we will help you with what will

More information

Laboratory of Applied Robotics

Laboratory of Applied Robotics Laboratory of Applied Robotics OpenCV: Shape Detection Paolo Bevilacqua RGB (Red-Green-Blue): Color Spaces RGB and HSV Color defined in relation to primary colors Correlated channels, information on both

More information

The PAGE (Page Analysis and Ground-truth Elements) Format Framework

The PAGE (Page Analysis and Ground-truth Elements) Format Framework 2010,IEEE. Reprinted, with permission, frompletschacher, S and Antonacopoulos, A, The PAGE (Page Analysis and Ground-truth Elements) Format Framework, Proceedings of the 20th International Conference on

More information

Animal detection using DNNs: Mobility Assistant for Visually Impaired (MAVI)

Animal detection using DNNs: Mobility Assistant for Visually Impaired (MAVI) Animal detection using DNNs: Mobility Assistant for Visually Impaired (MAVI) By Mukund Rungta 2014CS10238 Facial Recognition with OpenFace: Mobility Assistant for Visually Impaired (MAVI) By Sarvesh Chandoliya

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

Overlay Text Detection and Recognition for Soccer Game Indexing

Overlay Text Detection and Recognition for Soccer Game Indexing Overlay Text Detection and Recognition for Soccer Game Indexing J. Ngernplubpla and O. Chitsophuk, Member, IACSIT Abstract In this paper, new multiresolution overlaid text detection and recognition is

More information

Feature Extractors. CS 188: Artificial Intelligence Fall Nearest-Neighbor Classification. The Perceptron Update Rule.

Feature Extractors. CS 188: Artificial Intelligence Fall Nearest-Neighbor Classification. The Perceptron Update Rule. CS 188: Artificial Intelligence Fall 2007 Lecture 26: Kernels 11/29/2007 Dan Klein UC Berkeley Feature Extractors A feature extractor maps inputs to feature vectors Dear Sir. First, I must solicit your

More information

IJSER. Real Time Object Visual Inspection Based On Template Matching Using FPGA

IJSER. Real Time Object Visual Inspection Based On Template Matching Using FPGA International Journal of Scientific & Engineering Research, Volume 4, Issue 8, August-2013 823 Real Time Object Visual Inspection Based On Template Matching Using FPGA GURURAJ.BANAKAR Electronics & Communications

More information

(Updated 29 Oct 2016)

(Updated 29 Oct 2016) (Updated 29 Oct 2016) 1 Class Maker 2016 Program Description Creating classes for the new school year is a time consuming task that teachers are asked to complete each year. Many schools offer their students

More information

Statistical Approach to a Color-based Face Detection Algorithm

Statistical Approach to a Color-based Face Detection Algorithm Statistical Approach to a Color-based Face Detection Algorithm EE 368 Digital Image Processing Group 15 Carmen Ng Thomas Pun May 27, 2002 Table of Content Table of Content... 2 Table of Figures... 3 Introduction:...

More information

Improving Latent Fingerprint Matching Performance by Orientation Field Estimation using Localized Dictionaries

Improving Latent Fingerprint Matching Performance by Orientation Field Estimation using Localized Dictionaries 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. 3, Issue. 11, November 2014,

More information

Introduction to Operations Research Prof. G. Srinivasan Department of Management Studies Indian Institute of Technology, Madras

Introduction to Operations Research Prof. G. Srinivasan Department of Management Studies Indian Institute of Technology, Madras Introduction to Operations Research Prof. G. Srinivasan Department of Management Studies Indian Institute of Technology, Madras Module 03 Simplex Algorithm Lecture - 03 Tabular form (Minimization) In this

More information

Skew angle Detection and correction using Radon Transform

Skew angle Detection and correction using Radon Transform Skew Angle Detection and Correction using Radon Transform 1 Jinal Patel 1, Anup Shah 2, Dr. Hetal Patel 3 1 P.G. Student, Electronics & Communication Engineering Dept., ADIT, New Vallabh Vidyanagar-388121,

More information

TEXT DETECTION AND MARKER BASED FINGER TRACKING IN BUILDING A LANGUAGE ASSISTANT FOR WEARABLE GLASSES

TEXT DETECTION AND MARKER BASED FINGER TRACKING IN BUILDING A LANGUAGE ASSISTANT FOR WEARABLE GLASSES International Conference on Internet Studies, April2-4, 2018, Katamatsu, Japan TEXT DETECTION AND MARKER BASED FINGER TRACKING IN BUILDING A LANGUAGE ASSISTANT FOR WEARABLE GLASSES Ting Kwok Chan, Ying

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

CHAPTER 18: CLIENT COMMUNICATION

CHAPTER 18: CLIENT COMMUNICATION CHAPTER 18: CLIENT COMMUNICATION Chapter outline When to communicate with clients What modes of communication to use How much to communicate How to benefit from client communication Understanding your

More information

Toward Part-based Document Image Decoding

Toward Part-based Document Image Decoding 2012 10th IAPR International Workshop on Document Analysis Systems Toward Part-based Document Image Decoding Wang Song, Seiichi Uchida Kyushu University, Fukuoka, Japan wangsong@human.ait.kyushu-u.ac.jp,

More information

ABSTRACT 1. INTRODUCTION 2. RELATED WORK

ABSTRACT 1. INTRODUCTION 2. RELATED WORK Improving text recognition by distinguishing scene and overlay text Bernhard Quehl, Haojin Yang, Harald Sack Hasso Plattner Institute, Potsdam, Germany Email: {bernhard.quehl, haojin.yang, harald.sack}@hpi.de

More information

DATABASE DEVELOPMENT OF HISTORICAL DOCUMENTS: SKEW DETECTION AND CORRECTION

DATABASE DEVELOPMENT OF HISTORICAL DOCUMENTS: SKEW DETECTION AND CORRECTION DATABASE DEVELOPMENT OF HISTORICAL DOCUMENTS: SKEW DETECTION AND CORRECTION S P Sachin 1, Banumathi K L 2, Vanitha R 3 1 UG, Student of Department of ECE, BIET, Davangere, (India) 2,3 Assistant Professor,

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

Machine Vision Tools for Solving Auto ID Applications

Machine Vision Tools for Solving Auto ID Applications Machine Vision Tools for Solving Auto ID Applications Part 3 of a 3-part webinar series: Introduction to Machine Vision Track, Trace & Control Solutions About your Instructors Dr. Jonathan Ludlow Machine

More information

Cloud Storage Submitted in partial fulfillment of the requirement for the award of degree of Bachelor of Technology in Computer Science

Cloud Storage Submitted in partial fulfillment of the requirement for the award of degree of Bachelor of Technology in Computer Science A Seminar report On Cloud Storage Submitted in partial fulfillment of the requirement for the award of degree of Bachelor of Technology in Computer Science SUBMITTED TO: SUBMITTED BY: Acknowledgement I

More information

Note: TAO OCR is a derivitive of the same OCR engine used in Microsoft's "Seeing AI" application!

Note: TAO OCR is a derivitive of the same OCR engine used in Microsoft's Seeing AI application! TopOCR's Accessible User Interface By simply typing Control-Q, TopOCR can be transformed into a PC-based Reading Machine application for use with document cameras. It has a very easy to learn Visually

More information

Automated Video Analysis of Crowd Behavior

Automated Video Analysis of Crowd Behavior Automated Video Analysis of Crowd Behavior Robert Collins CSE Department Mar 30, 2009 Computational Science Seminar Series, Spring 2009. We Are... Lab for Perception, Action and Cognition Research Interest:

More information

Restoring Chinese Documents Images Based on Text Boundary Lines

Restoring Chinese Documents Images Based on Text Boundary Lines Proceedings of the 2009 IEEE International Conference on Systems, Man, and Cybernetics San Antonio, TX, USA - October 2009 Restoring Chinese Documents Images Based on Text Boundary Lines Hong Liu Key Laboratory

More information

PowerPoint 2010 Quick Start to a Presentation

PowerPoint 2010 Quick Start to a Presentation PowerPoint 2010 Quick Start to a Presentation Backstage View Button Similar to old File button 1 On opening a new presentation, from Slides choose a Layout for a particular template, e.g. a title page.

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

Flash offers a way to simplify your work, using symbols. A symbol can be

Flash offers a way to simplify your work, using symbols. A symbol can be Chapter 7 Heavy Symbolism In This Chapter Exploring types of symbols Making symbols Creating instances Flash offers a way to simplify your work, using symbols. A symbol can be any object or combination

More information

Mobile Robot Path Planning in Static Environment

Mobile Robot Path Planning in Static Environment Mobile Robot Path Planning in Static Environment A Thesis Submitted in Partial Fulfilment of the Requirements for the Degree of Bachelor of Technology in Computer Science & Engineering Submitted by: Raman

More information

E-BOOK The Truth About Diallers

E-BOOK The Truth About Diallers E-BOOK The Truth About Diallers How dialler modes dispess myths and misconceptions. Contents Four Misconceptions About Predictive Diallers The Truth Behind the Myths Preview Dialling Progressive Dialling

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

Extraction and Recognition of Alphanumeric Characters from Vehicle Number Plate

Extraction and Recognition of Alphanumeric Characters from Vehicle Number Plate Extraction and Recognition of Alphanumeric Characters from Vehicle Number Plate Surekha.R.Gondkar 1, C.S Mala 2, Alina Susan George 3, Beauty Pandey 4, Megha H.V 5 Associate Professor, Department of Telecommunication

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

A Road Marking Extraction Method Using GPGPU

A Road Marking Extraction Method Using GPGPU , pp.46-54 http://dx.doi.org/10.14257/astl.2014.50.08 A Road Marking Extraction Method Using GPGPU Dajun Ding 1, Jongsu Yoo 1, Jekyo Jung 1, Kwon Soon 1 1 Daegu Gyeongbuk Institute of Science and Technology,

More information

Nitesh Kumar Singh, Avinash verma, Anurag kumar

Nitesh Kumar Singh, Avinash verma, Anurag kumar International Journal of Scientific & Engineering Research, Volume 5, Issue 4, April-2014 331 Text & Non-Text Segmentation in Colored Images Nitesh Kumar Singh, Avinash verma, Anurag kumar Abstract The

More information

Determining Document Skew Using Inter-Line Spaces

Determining Document Skew Using Inter-Line Spaces 2011 International Conference on Document Analysis and Recognition Determining Document Skew Using Inter-Line Spaces Boris Epshtein Google Inc. 1 1600 Amphitheatre Parkway, Mountain View, CA borisep@google.com

More information

Khmer OCR for Limon R1 Size 22 Report

Khmer OCR for Limon R1 Size 22 Report PAN Localization Project Project No: Ref. No: PANL10n/KH/Report/phase2/002 Khmer OCR for Limon R1 Size 22 Report 09 July, 2009 Prepared by: Mr. ING LENG IENG Cambodia Country Component PAN Localization

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

USER MANUAL Table of Contents Slide 00 of 66

USER MANUAL Table of Contents Slide 00 of 66 USER MANUAL 1.5 www.dgflick.com Table of Contents Slide 00 of 66 Table of Contents Table of Contents... 1 1.0. Getting Started... 2 1.1. What is Video Xpress Suite?... 3 1.2. System Requirements to Run

More information

(Refer Slide Time: 00:01:27 min)

(Refer Slide Time: 00:01:27 min) Computer Aided Design Prof. Dr. Anoop Chawla Department of Mechanical engineering Indian Institute of Technology, Delhi Lecture No. # 01 An Introduction to CAD Today we are basically going to introduce

More information

DEVANAGARI SCRIPT SEPARATION AND RECOGNITION USING MORPHOLOGICAL OPERATIONS AND OPTIMIZED FEATURE EXTRACTION METHODS

DEVANAGARI SCRIPT SEPARATION AND RECOGNITION USING MORPHOLOGICAL OPERATIONS AND OPTIMIZED FEATURE EXTRACTION METHODS DEVANAGARI SCRIPT SEPARATION AND RECOGNITION USING MORPHOLOGICAL OPERATIONS AND OPTIMIZED FEATURE EXTRACTION METHODS Sushilkumar N. Holambe Dr. Ulhas B. Shinde Shrikant D. Mali Persuing PhD at Principal

More information

The first thing you ll want to do when you open Premiere is start a new project. Make sure to select a name and location you ll remember.

The first thing you ll want to do when you open Premiere is start a new project. Make sure to select a name and location you ll remember. A Beginner s Guide to Premiere Pro Premiere Pro can seem scary with all of its many panels and buttons, but this document can help relieve some of the mystery surrounding the complexities of Premiere Pro.

More information

Localization, Extraction and Recognition of Text in Telugu Document Images

Localization, Extraction and Recognition of Text in Telugu Document Images Localization, Extraction and Recognition of Text in Telugu Document Images Atul Negi Department of CIS University of Hyderabad Hyderabad 500046, India atulcs@uohyd.ernet.in K. Nikhil Shanker Department

More information

Estimation of Skew Angle in Binary Document Images Using Hough Transform

Estimation of Skew Angle in Binary Document Images Using Hough Transform Estimation of Skew Angle in Binary Document Images Using Hough Transform Nandini N., Srikanta Murthy K., and G. Hemantha Kumar Abstract This paper includes two novel techniques for skew estimation of binary

More information

Estimation of Skew Angle in Binary Document Images Using Hough Transform

Estimation of Skew Angle in Binary Document Images Using Hough Transform Estimation of Skew Angle in Binary Document Images Using Hough Transform Nandini N., Srikanta Murthy K., and G. Hemantha Kumar Abstract This paper includes two novel techniques for skew estimation of binary

More information

TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK

TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK 1 Po-Jen Lai ( 賴柏任 ), 2 Chiou-Shann Fuh ( 傅楸善 ) 1 Dept. of Electrical Engineering, National Taiwan University, Taiwan 2 Dept.

More information

Scene Text Recognition for Augmented Reality. Sagar G V Adviser: Prof. Bharadwaj Amrutur Indian Institute Of Science

Scene Text Recognition for Augmented Reality. Sagar G V Adviser: Prof. Bharadwaj Amrutur Indian Institute Of Science Scene Text Recognition for Augmented Reality Sagar G V Adviser: Prof. Bharadwaj Amrutur Indian Institute Of Science Outline Research area and motivation Finding text in natural scenes Prior art Improving

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

Janitor Bot - Detecting Light Switches Jiaqi Guo, Haizi Yu December 10, 2010

Janitor Bot - Detecting Light Switches Jiaqi Guo, Haizi Yu December 10, 2010 1. Introduction Janitor Bot - Detecting Light Switches Jiaqi Guo, Haizi Yu December 10, 2010 The demand for janitorial robots has gone up with the rising affluence and increasingly busy lifestyles of people

More information

How to work with text

How to work with text How to work with text Adobe Flash Professional lets you add text to a Flash application in two formats: You can add Text Layout Framework (TLF) text. You can add Classic text. Using the Text Layout Framework

More information

CaseComplete Roadmap

CaseComplete Roadmap CaseComplete Roadmap Copyright 2004-2014 Serlio Software Development Corporation Contents Get started... 1 Create a project... 1 Set the vision and scope... 1 Brainstorm for primary actors and their goals...

More information