Traffic Sign Segmentation and Recognition in Scene Images

Size: px
Start display at page:

Download "Traffic Sign Segmentation and Recognition in Scene Images"

Transcription

1 Traffic Segmentation and Recognition in Scene Images Fei Qin 1, Bin Fang 1, Hengjun Zhao 1 1. Department of Computer Science, Chongqing University, Chongqing , China jiemy@cqu.edu.cn, fb@cqu.edu.cn, zhhj@cqu.edu.cn Abstract: Traffic s provide drivers with very valuable information about the road, in order to make driving safer and easier. They are designed to be easily recognized by human drivers mainly because their color and shape are very different from natural environments. Automatic traffic sign detection and recognition is important in the development of unmanned vehicles, and is expected to provide information on road signs and guide vehicles during driving. This paper deals with traffic sign detection and recognition from image sequences. In order to reduce the computational complexity in the scene image processing, an effective method for traffic sign segmentation based on color distance is proposed in this work. The scene image is mapped to a matrix by computing the color distance. Through the selection of appropriate distance threshold on the basis of large number of scene image samples, it quickly obtains the binary image. To obtain better classification performance, we use linear support vector machine with the Distance to Border features of the segmented blobs to get the shape information, and then realize the rough classification based on Color-Geometric Model. Traffic sign classification is implemented using RBF kernel based support vector machine with edge related pixels of interest as the feature. The experimental result shows that our method can work well and achieve the traffic sign segmentation and recognition with sufficiently high processing speed and satisfactory accuracy. Key Words: Traffic ; Image Segmentation; Color Distance; Pattern Recognition; Distance to Border; SVM Algorithm 1. INTRODUCTION Computer vision plays an important role nowadays along with advancement in science and technology. Automatic Traffic Recognition (TSR), as an important subtask of Intelligent Transportation System (ITS), has been of great interest for many years. How to realize traffic sign recognition under complex conditions in real-time has been drawing technical attention but remaining to be a challenge [1]. Generally speaking, a pattern recognition system consists of two major components, detection and classification. Traffic sign detection is the premise of traffic sign recognition, and how to locate fast and detect accurately the traffic sign is very crucial in real-time system. How to identify the traffic sign rapidly and precisely is equally fundamental. Like many other countries, in China, traffic signs are designed to be easily detected and recognized by human beings according to the colors and shapes. Color is considered as one of the most distinct and useful features in traffic sign segmentation as well. However, it is not easy to identify whether a pixel is red or blue or not, as pictures captured by cameras are affected by various factors, such as weather, illumination, and so on. Selecting a proper color space plays a crucial role in color segmentation. Usually a color image is converted from the RGB (Red, Green and Blue) color space to HSV (Hue, Saturation and Value) color space because the hue value is invariant to the illumination as well [2]. Yet the present transformation algorithm spends much time on floating-point operations which results in low efficiency. Hence in our work, we focus our attention on color segmentation based on the RGB color space. A wide variety of different color segmentation schemes for traffic sign images have been proposed in recent years, and some good results have been achieved. Aryuanto Soetedjo et al. [3] started with selecting an appropriate threshold based on a great of experiments. A pixel is red if R/(R+G+B)>TR, where R, G, B, TR represent respectively the value of R, G, B of the pixel and the selected threshold. Another color segmentation strategy proposed by Mudan Hu, et al. [4] is based on Chromatic Aberration (CA) in RGB color space. They selected λr-g-b as the characteristic operator for the red prohibition sign and λb-r-g for the blue directional sign. Taking the red sign as an example, CA is 0 if λr-g-b<0; CA is 255 if λr-g-b>255; CA equals to λr-g-b otherwise. CA represents the gray value of chromatic aberration. The Otsu s thresholding algorithm is subsequently induced and applied to output segmented image. Several research works about traffic sign classification have been done and certain results have been achieved. Merve Can Kuş et al. [5] developed a colored traffic sign recognition system using Scale Invariant Feature Transform (SIFT). Min Shi et al. [6] discussed two kinds of features for representing each sign and analyzed four different kernels and two SVM types. King Hann Lim et al. [7] proposed a hybrid traffic sign recognition scheme combining of knowledge-based analysis and radial basis function neural classifier. In this work, we present a general framework for detection and recognition of traffic signs from image sequences. This paper is organized as follows: Section 2 details our proposed method for traffic sign segmentation. Section 3 focuses on the technique for traffic sign recognition. Section 4 shows the experimental results, followed with the conclusion and discussion in section /10/$ IEEE

2 2. TRAFFIC SIGN SEGMENTATION Traffic s are designed to be easily detected and recognized by human beings according to the distinct colors and shapes. Similar to many other countries, in China, traffic signs of road safeties are mainly classified into three categories, the prohibition signs, directional signs and warning signs. Red is the basic color for prohibition signs, with background mainly in white. In the directional signs, blue is the background color, mainly with white-core designs. As for warning signs, yellow is chosen as the fundamental color, with black border, and the core-based designs are also mainly in black. Taking the traffic signs in our country as the example, as shown later, we will details out method in this section, covering three steps: the color distance, the selection of threshold and the thresholding segmentation. 2.1 Color Distance As we know, Euclidean distance is defined as the straight line distance between two points. In N dimensions, the Euclidean distance between two points is: d( p, q) = ( p q ) where p i (or q i ) is the coordinate of p (or q) in dimension i. Euclidean distance is one of the most common uses of distances in Bayes Decision Theory and Statistical Pattern Recognition. Assume that the feature space is isotropic and the problem of feature scaling does not exist; it can be used to measure the similarity between two vectors. Logically, the RGB values of each pixel can be considered as a point in the RGB color space. Therefore, the Color Distance (CD) [8], which denotes the difference between two colors, is defined as: N i= 1 i i 2 (1) Similarly, for the blue directional signs, a pixel is identified as blue if CD blue <TH blue and the yellow warning signs, a pixel is yellow if CD yellow <TH yellow, where TH blue and TH yellow indicate the blue threshold and the yellow threshold respectively. Unfortunately, we have to pay attention to the selection of Standard Color (SC). It is assumed that the SC of traffic sign is close to the ideal one. So far, we can do the segmentation as long as the right threshold is selected. How to choose an appropriate threshold remains to be a challenge. We take the red prohibition sign as an example in the subsequent subsections. 2.2 Threshold Selection The selection of threshold is crucial. Inappropriate value means introducing excessive amount of noise or taking away the target object, and possibly resulting in failing to extract the target image. Our method of threshold selection is mostly similar to the idea proposed by Ling Luo and Xiying Li [9]. The threshold is not an experience threshold but a statistic threshold. The method to search for color segmentation threshold uses consecutive images which includes traffic signs. Using experience threshold roughly segments these consecutive images. After that, positive and negative samples are classified manually. The next task is to do a statistical work both in positive-sample-set and negative-sample-set. Obviously, our threshold parameter is color distance. We prepare 240 positive samples and 240 negative samples for the statistical work, and the results are shown in Fig. 1. The histogram s abscissa represents value of Color Distance, whose range is from 0 to The ordinate represents the number of pixels. CD( i, j) = ( R R ) + ( G G ) + ( B B ) i j i j i j (2) where R i, G i, B i and R j, G j, B j, respectively, indicate the RGB values of pixel i and j in RGB color space. Obviously, CD(i,j), the distance between color i and j, can be used to measure the similarity between the two colors. According to the color distance model given above, the color distance between a pixel and the standard red (255,0,0) can be written as: CD = ( R 255) + ( G 0) + ( B 0) red (3) where R, G, B are the values of red, green, and blue of the pixel. Here, we mention the property that CD red represents the prospect of a pixel to be taken as red (as well as non-red) pixel. The lower the value, the higher (lower for non-red ones) is the possibility. Thus, the red prohibition signs, a pixel in traffic sign image is classified into red if CD red <TH red, where TH red represents a red threshold which will be discussed in the next subsection. Fig. 1: Positive-sample-set and negative sample-set s color distance histogram statistics We are focused on the two black broken lines. The positive samples are mostly on the left side of the second broken line, while the negative samples are mostly on the right side of the second broken line. This means that the positive samples and negative samples are mostly able to separate from each other though the color distance. Meanwhile, we also mention that there are hardly any

3 negative samples on the left side of the first broken line. Between the two broken lines, the closer to the first broken line, the less noise is introduced and the more target is missed; Otherwise, the opposite. Hence, an appropriate threshold can be selected naturally. However, the brightness varies a lot between the images. It is noticed that the average pixel value is less than 100 in too dark images and greater than 180 in too light images [10]. According to our statistical work, the TH value may be selected as 184, 158, 150 for too dark images, normal brightness images, and too light images, respectively. 2.3 Traffic Segmentation Traffic sign segmentation is very vital in the area of traffic sign detection, by which the noise may be attenuated further in order to reduce the computational complexity, and thus improve the detection efficiency and accuracy. Now that the TH value is selected, a binary image is quickly obtained with the following formula: 255, CD < TH Bi = (4) 0, otherwise where Bi represents the value of a pixel in the binary (gray) image. According to the TH values selected for different cases and the rules as stated above, we achieve the binarization under different brightness as shown in Fig. 2. Respectively, Fig. 2(d) shows the binary image of Fig. 2(a), Fig. 2(e) is the binarization result of Fig. 2(b), and Fig. 2(f) comes up with the result of binarization of Fig. 2(c). of each pixel in the image, as it is known that the function f(x)= is monotonous on [0, ). (a) (c) Fig. 3: Warning and directional sign segmentation results (a), (c) Original scene images (b), (d) Segmentation results of our method The next stage is to locate traffic sign candidates. Detected objects can be screened based on some common features, such as area, height to width ratio, position, etc. Traffic sign segmentation becomes very easy based on the binary image. Meanwhile, the shape and color can be utilized to assist with traffic sign recognition. 3. TRAFFIC SIGN RECOGNITION (b) (d) 3.1 Color-Geometric Model (CGM) (a) (b) (c) According to analysis of the color and shape attribute of 116 Chinese traffic signs, it is noted that there is a unique and fixed relation between the geometric shape and the color of traffic signs, which is called Color-Geometric Model (CGM) [11]. Fig.4 shows the unique and fixed relation. Red Blue Yellow (d) (e) (f) Fig. 2: Segmentation results under different brightness (a) Too dark image (b) Normal brightness (c) Too light image (d) Result of (a) (e) Result of (b) (f) Result of (c) In order to further verify the feasibility and applicability of our method, we also select a yellow warning sign image and a blue directional sign image for experimenting purposes. Fig. 3 presents the segmentation effect. We have to point out that, in order to avoid floating-point operations so as to improve the efficiency, it is not necessary to do the square root operation while computing the CD value Prohibition Directional Fig. 4: Framework of CGM Warning We can directly divide the 116 Chinese traffic signs of three major classes into several subclasses by color and shape. It establishes a good foundation for the further recognition.

4 3.2 Distance to Border (DtB) In order to recognize the shape of traffic sign, many methods have been proposed for obtaining the feature vectors. In this work, we use Distance to Border (DtB) [12] vector as the feature vector for training SVM. DtB is the distance from external edge of the blob to its bounding box. Thus for a segmented blob we have four DtB vectors for left, right, top and bottom. The main advantage of this method is its robustness to translation, rotation and scale. The algorithm is invariant to translation because it does not depend on the position of appearance of the blob in the scene. It is invariant to rotation because all blobs have been previously orientated in a reference position using the DtB vectors. In order to make the DtBs invariant to changes of scale, the blobs are zoomed to Therefore, there are four DtB vectors of 36 components for a single instance. Fig. 5 shows the four DtB vectors for a segmented circular blob. (a) (b) (c) Fig. 5: (a) Segmented circular blob (b) Binary image of (a) (c) DtB for circular blob 3.3 Support Vector Machine (SVM) SVM is a set of related supervised learning methods used for classification and regression. It is based on mathematical foundations of statistical learning theory, which was proposed first by Vapnik in 1992 [13]. The main idea is to construct a hyper-plane as the decision surface in such a way that the margin of separation between positive and negative samples is maximized. SVM algorithm is described as follows: Suppose the set of training samples T=(x 1, y 1 ),,(x l, y l ), where x i R n, i=1,,l, y i {1,,k} is the class of x i and k is the number of classes. The two-class classification problem is the optimum equation as follow: 1 ij T ij ij ij T min ( w ) w + C ( ) ij ij ij ξt w (5) w, b, ξ 2 t where w is a normal vector, which is perpendicular to the hyper-plane. The constant C is only as an additional constraint on the Lagrange multipliers. ξ i is a non-zero penalizing function. We get the decision function, that is, the classifier that can decide the class of x. 1, gx ( ) > 0 f( x) = 1, others (6) l g( x) = yak( x, x ) + b i= 1 where x is the input vector to be classified, x i (i=1,,l) is a support vector, and K(x, x i ) is known as kernel function. A kernel constructs an implicit mapping from the input space into a feature space, and then a linear machine is trained in the feature space to classify input vectors. Four different kernels are commonly used: linear kernel: K(x i, x j )=x i T x j polynomial: K(x i, x j )=(γx i T x j +r) d, γ>0 radial basis function (RBF): K(x i, x j )=exp(-γ x i -x j 2 ), γ>0 sigmoid: K(x i, x j )=tanh(γx i T x j +r) where γ, r, and d are kernel parameters. The traditional SVM is a binary classifier. Two common methods to build the multiclass SVM are where each classifier distinguishes (i) between one of the labels to the rest (one-versus-all) or (ii) between every pair of classes (one-against-one). Classification of new instances for one-versus-all case is done by a winner-takes-all strategy, in which the classifier with the highest output function assigns the class (it is important that the output functions be calibrated to produce comparable scores). For the one-against-one approach, classification is done by a max-wins voting strategy, in which every classifier assigns the instance to one of the two classes, then the vote for the assigned class is increased by one vote, and finally the class with most votes determines the instance classification. 3.4 Traffic Classification i i i (7) In the shape classification stage, we need to build a multiclass SVM to classify 5 types of shapes including circle, rectangle, positive triangle, inverse triangle, and octagon. One-against-one classifier is applied here. k(k-1)/2 SVM classifiers perform k-category classification. In case of tie, positives outputs of SVMs are computed to decide the shape and if the total number of votes is lower than 2, the object is discarded like noise. In fact, there are only one octagonal sign and only one inverse triangular sign in China. Once the shape information is obtained, we can realize rough classification based on CGM. Moreover, it also can be utilized to extract Pixels of Interest (POI) by using a mask image corresponding to the shape of the blob. The shape classified blob is first normalized to a size of The masking operation is applied, with only those pixels that are crucial part of the sign reserved. Then the edge of the masked POI is extracted and used as the feature vector for traffic sign classification. The detailed process can be found in [14][15]. Different one-versus-all SVMs classifiers with a RBF kernel are employed. The parameters of cost (C) and gamma (g) are also important for the training and testing, we can get the optimal parameters by grid search and cross-validation. We have to point out that both training and testing are done based on the CGM so as to reduce the complexity.

5 To build the multiclass SVMs, we use a package called LIBSVM that developed by Lin Chih-Jen [16]. 4. EXPERIMENTAL RESULTS In our experiment, train and test sequences have been recorded with a video camera (JAI BB-141 GE) fixed onto the top of a vehicle while driving at usual speed. The video sequences were saved in JPG file format with a resolution of We use a dataset of 1000 images which contains 2059 signs in all for the simulation experiment. Table 1 summarizes the experimental results of traffic sign recognition. True Positive (TP) denotes the number of traffic signs correctly classified. False Positive (FP) indicates the number of signs wrongly classified. False Negative (FN) is the number of noise objects wrongly classified as traffic signs. Table 1: Traffic sign recognition results Traffic s No. TP FP FN Red Circle Red Inv-Triangle Red Octagon Blue Circle Blue Rectangle Yellow Pos-Triangle CONCLUSION AND DISCUSSION In this work, we present a system for segmentation and recognition of traffic signs in scene images. A color based segmentation method using color distance is introduced. In recognition stage, we develop a linear SVM for shape classification and another SVM with RBF kernel for recognition of POI, where CGM is applied as prior knowledge. Experiment results show that our algorithm is succinct and conducive to real-time processing. However, the selected TH values in this paper depend on the large number of samples captured in special environment. How to dynamically select the right TH value requires further study, and will be explored in the next research phase. ACKNOWLEDGMENTS This work is supported by Natural Science Foundation of China ( ). REFERENCES [1] D.M. Gavrila. U. Franke, C. Wohler, and S. Gorzig. Real-time vision for intelligent vehicles, IEEE Instrumentation & Measurement Magazme, 4(2), pp , [2] C.Y. Fang, C.S. Fuh, and P.S. Yen. An automatic road sign recognition system based on a computational model of human recognition processing. Computer Vision and Image Understanding, vol. 63, no. 3, pp , [3] Aryuanto Soetedjo and Koichi Yamada. An Efficient Algorithm for Traffic Detection. Journal of Advanced Computational Intelligence and Intelligent Informatics, vol. 10, no. 3, pp , [4] Mudan Hu, Shuangdong Zhu, and Ken Chen. An Effective Method for Traffic Segmentation, International Conference on Intelligent Human-Machine Systems and Cybernetics, pp , [5] Merve Can Kuş, Muhittin Gökmen, and Şima Etaner-Uyar. Traffic Recognition using Scale Invariant Feature Transform and Color Classification. International Symposium on Computer and Information Sciences, pp. 1-6, [6] Min Shi, Haifeng Wu, and Hasan Fleyeh. Support Vector Machine for Traffic s Recognition, IEEE International Joint Conference on Neural Networks, pp , [7] King Hann Lim, Li-Minn Ang and Kah Phooi Seng. New Hybrid Technique for Traffic Recognition. IEEE International Symposium on Intelligent al Processing and Communication Systems, pp. 1-4, [8] M. Abdullah-Al-Wadud and Oksam Chae. Region-of-Interest Selection for Skin Dectection Based Applications. Proc. the IEEE International Conference on Convergence Information Technology, pp , [9] Ling Luo and Xiying Li. A method to search for color segmentation threshold in traffic sign detection. International Conference on Image and Graphics, pp , [10] J.Torresen, J.W.Armingol, and M.A.Salchs, et al. Road Traffic Detection and Classification. IEEE Conference on Intelligent Transportation Systems, pp , [11] Zhu Shuangdong and Liu Lanlan. Color-Geometric Model for Traffic Recognition. International Workshop on Intelligent Systems and Intelligent Computing, pp , 2006 [12] S. Lafuente Arroyo, P. Gil Jimenez et al. Traffic Shape Classification Evaluation I: SVM using Distance to Borders. Proceedings of IEEE Intelligent Vehicles Symposium, pp , [13] V. Vapnik, Statistical Learning Theory, New York: John Wiley & Sons, [14] S. Maldonado Bascon, S. Lafuente Arroyo et al. Road- Dectection and Recognition Based on Support Vector Machines. IEEE Transactions on Intelligent Transportation Systems, vol. 8, no. 2, June [15] Kiran C.G., Lekhesh V.Prabhu, Abdu Rahiman V. and Rajeev K. Traffic Detection and Pattern Recognition using Support Vector Machine. International Conference on Advances in Pattern Recognition, pp , [16] Chih-Chung Chang and Chih-Jen Lin, LIBSVM: A Library for Support Vector Machines, [Online]. Available:

Road-Sign Detection and Recognition Based on Support Vector Machines. Maldonado-Bascon et al. et al. Presented by Dara Nyknahad ECG 789

Road-Sign Detection and Recognition Based on Support Vector Machines. Maldonado-Bascon et al. et al. Presented by Dara Nyknahad ECG 789 Road-Sign Detection and Recognition Based on Support Vector Machines Maldonado-Bascon et al. et al. Presented by Dara Nyknahad ECG 789 Outline Introduction Support Vector Machine (SVM) Algorithm Results

More information

THE SPEED-LIMIT SIGN DETECTION AND RECOGNITION SYSTEM

THE SPEED-LIMIT SIGN DETECTION AND RECOGNITION SYSTEM THE SPEED-LIMIT SIGN DETECTION AND RECOGNITION SYSTEM Kuo-Hsin Tu ( 塗國星 ), Chiou-Shann Fuh ( 傅楸善 ) Dept. of Computer Science and Information Engineering, National Taiwan University, Taiwan E-mail: p04922004@csie.ntu.edu.tw,

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

Extracting Road Signs using the Color Information

Extracting Road Signs using the Color Information Extracting Road Signs using the Color Information Wen-Yen Wu, Tsung-Cheng Hsieh, and Ching-Sung Lai Abstract In this paper, we propose a method to extract the road signs. Firstly, the grabbed image is

More information

A Fast and Robust Traffic Sign Recognition

A Fast and Robust Traffic Sign Recognition International Journal of Innovation and Applied Studies ISSN 2028-9324 Vol. 5 No. 2 Feb. 2014, pp. 139-149 2014 Innovative Space of Scientific Research Journals http://www.issr-journals.org/ijias/ A Fast

More information

Traffic sign shape classification evaluation II: FFT applied to the signature of Blobs

Traffic sign shape classification evaluation II: FFT applied to the signature of Blobs Traffic sign shape classification evaluation II: FFT applied to the signature of Blobs P. Gil-Jiménez, S. Lafuente-Arroyo, H. Gómez-Moreno, F. López-Ferreras and S. Maldonado-Bascón Dpto. de Teoría de

More information

C. Premsai 1, Prof. A. Kavya 2 School of Computer Science, School of Computer Science Engineering, Engineering VIT Chennai, VIT Chennai

C. Premsai 1, Prof. A. Kavya 2 School of Computer Science, School of Computer Science Engineering, Engineering VIT Chennai, VIT Chennai Traffic Sign Detection Via Graph-Based Ranking and Segmentation Algorithm C. Premsai 1, Prof. A. Kavya 2 School of Computer Science, School of Computer Science Engineering, Engineering VIT Chennai, VIT

More information

Traffic Signs Recognition Experiments with Transform based Traffic Sign Recognition System

Traffic Signs Recognition Experiments with Transform based Traffic Sign Recognition System Sept. 8-10, 010, Kosice, Slovakia Traffic Signs Recognition Experiments with Transform based Traffic Sign Recognition System Martin FIFIK 1, Ján TURÁN 1, Ľuboš OVSENÍK 1 1 Department of Electronics and

More information

Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation

Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation M. Blauth, E. Kraft, F. Hirschenberger, M. Böhm Fraunhofer Institute for Industrial Mathematics, Fraunhofer-Platz 1,

More information

TRAFFIC SIGN RECOGNITION USING MSER AND RANDOM FORESTS. Jack Greenhalgh and Majid Mirmehdi

TRAFFIC SIGN RECOGNITION USING MSER AND RANDOM FORESTS. Jack Greenhalgh and Majid Mirmehdi 20th European Signal Processing Conference (EUSIPCO 2012) Bucharest, Romania, August 27-31, 2012 TRAFFIC SIGN RECOGNITION USING MSER AND RANDOM FORESTS Jack Greenhalgh and Majid Mirmehdi Visual Information

More information

Two Algorithms for Detection of Mutually Occluding Traffic Signs

Two Algorithms for Detection of Mutually Occluding Traffic Signs Two Algorithms for Detection of Mutually Occluding Traffic Signs Thanh Bui-Minh, Ovidiu Ghita, Paul F. Whelan, Senior Member, IEEE, Trang Hoang, Vinh Quang Truong Abstract The robust identification of

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

Automatic Shadow Removal by Illuminance in HSV Color Space

Automatic Shadow Removal by Illuminance in HSV Color Space Computer Science and Information Technology 3(3): 70-75, 2015 DOI: 10.13189/csit.2015.030303 http://www.hrpub.org Automatic Shadow Removal by Illuminance in HSV Color Space Wenbo Huang 1, KyoungYeon Kim

More information

Face Recognition Using Vector Quantization Histogram and Support Vector Machine Classifier Rong-sheng LI, Fei-fei LEE *, Yan YAN and Qiu CHEN

Face Recognition Using Vector Quantization Histogram and Support Vector Machine Classifier Rong-sheng LI, Fei-fei LEE *, Yan YAN and Qiu CHEN 2016 International Conference on Artificial Intelligence: Techniques and Applications (AITA 2016) ISBN: 978-1-60595-389-2 Face Recognition Using Vector Quantization Histogram and Support Vector Machine

More information

Developing an intelligent sign inventory using image processing

Developing an intelligent sign inventory using image processing icccbe 2010 Nottingham University Press Proceedings of the International Conference on Computing in Civil and Building Engineering W Tizani (Editor) Developing an intelligent sign inventory using image

More information

Face Recognition using SURF Features and SVM Classifier

Face Recognition using SURF Features and SVM Classifier International Journal of Electronics Engineering Research. ISSN 0975-6450 Volume 8, Number 1 (016) pp. 1-8 Research India Publications http://www.ripublication.com Face Recognition using SURF Features

More information

Study on road sign recognition in LabVIEW

Study on road sign recognition in LabVIEW IOP Conference Series: Materials Science and Engineering PAPER OPEN ACCESS Study on road sign recognition in LabVIEW To cite this article: M Panoiu et al 2016 IOP Conf. Ser.: Mater. Sci. Eng. 106 012009

More information

Pedestrian Detection with Improved LBP and Hog Algorithm

Pedestrian Detection with Improved LBP and Hog Algorithm Open Access Library Journal 2018, Volume 5, e4573 ISSN Online: 2333-9721 ISSN Print: 2333-9705 Pedestrian Detection with Improved LBP and Hog Algorithm Wei Zhou, Suyun Luo Automotive Engineering College,

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

A Robust Algorithm for Detection and Classification of Traffic Signs in Video Data

A Robust Algorithm for Detection and Classification of Traffic Signs in Video Data A Robust Algorithm for Detection and Classification of Traffic Signs in Video Data Thanh Bui-Minh, Ovidiu Ghita, Paul F. Whelan, Senior Member, IEEE, and Trang Hoang Abstract The accurate identification

More information

Preliminary Local Feature Selection by Support Vector Machine for Bag of Features

Preliminary Local Feature Selection by Support Vector Machine for Bag of Features Preliminary Local Feature Selection by Support Vector Machine for Bag of Features Tetsu Matsukawa Koji Suzuki Takio Kurita :University of Tsukuba :National Institute of Advanced Industrial Science and

More information

KBSVM: KMeans-based SVM for Business Intelligence

KBSVM: KMeans-based SVM for Business Intelligence Association for Information Systems AIS Electronic Library (AISeL) AMCIS 2004 Proceedings Americas Conference on Information Systems (AMCIS) December 2004 KBSVM: KMeans-based SVM for Business Intelligence

More information

Performance analysis of robust road sign identification

Performance analysis of robust road sign identification IOP Conference Series: Materials Science and Engineering OPEN ACCESS Performance analysis of robust road sign identification To cite this article: Nursabillilah M Ali et al 2013 IOP Conf. Ser.: Mater.

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

Road signs shapes detection based on Sobel phase analysis

Road signs shapes detection based on Sobel phase analysis Road signs shapes detection based on Sobel phase analysis Elena Cardarelli, Paolo Medici, Pier Paolo Porta, and VisLab Dipartimento di Ingegneria dell Informazione Università degli Studi di Parma, ITALY

More information

REAL-TIME ROAD SIGNS RECOGNITION USING MOBILE GPU

REAL-TIME ROAD SIGNS RECOGNITION USING MOBILE GPU High-Performance Сomputing REAL-TIME ROAD SIGNS RECOGNITION USING MOBILE GPU P.Y. Yakimov Samara National Research University, Samara, Russia Abstract. This article shows an effective implementation of

More information

Short Survey on Static Hand Gesture Recognition

Short Survey on Static Hand Gesture Recognition Short Survey on Static Hand Gesture Recognition Huu-Hung Huynh University of Science and Technology The University of Danang, Vietnam Duc-Hoang Vo University of Science and Technology The University of

More information

Published by: PIONEER RESEARCH & DEVELOPMENT GROUP(

Published by: PIONEER RESEARCH & DEVELOPMENT GROUP( Image Based Detection and Recognition of Road Signs Mrs.S.Sathiya 1, Dr.M.Balasubramanian 2, R.Sivaranjini 3 1 Department of Computer Science, Annamalai university Chidambaram, Tamilnadu, India Abstract

More information

INTELLIGENT MACHINE VISION SYSTEM FOR ROAD TRAFFIC SIGN RECOGNITION

INTELLIGENT MACHINE VISION SYSTEM FOR ROAD TRAFFIC SIGN RECOGNITION INTELLIGENT MACHINE VISION SYSTEM FOR ROAD TRAFFIC SIGN RECOGNITION Aryuanto 1), Koichi Yamada 2), F. Yudi Limpraptono 3) Jurusan Teknik Elektro, Fakultas Teknologi Industri, Institut Teknologi Nasional

More information

OBJECT SORTING IN MANUFACTURING INDUSTRIES USING IMAGE PROCESSING

OBJECT SORTING IN MANUFACTURING INDUSTRIES USING IMAGE PROCESSING OBJECT SORTING IN MANUFACTURING INDUSTRIES USING IMAGE PROCESSING Manoj Sabnis 1, Vinita Thakur 2, Rujuta Thorat 2, Gayatri Yeole 2, Chirag Tank 2 1 Assistant Professor, 2 Student, Department of Information

More information

Enhanced Image. Improved Dam point Labelling

Enhanced Image. Improved Dam point Labelling 3rd International Conference on Multimedia Technology(ICMT 2013) Video Text Extraction Based on Stroke Width and Color Xiaodong Huang, 1 Qin Wang, Kehua Liu, Lishang Zhu Abstract. Video text can be used

More information

A Novel Approach to Image Segmentation for Traffic Sign Recognition Jon Jay Hack and Sidd Jagadish

A Novel Approach to Image Segmentation for Traffic Sign Recognition Jon Jay Hack and Sidd Jagadish A Novel Approach to Image Segmentation for Traffic Sign Recognition Jon Jay Hack and Sidd Jagadish Introduction/Motivation: As autonomous vehicles, such as Google s self-driving car, have recently become

More information

Robust color segmentation algorithms in illumination variation conditions

Robust color segmentation algorithms in illumination variation conditions 286 CHINESE OPTICS LETTERS / Vol. 8, No. / March 10, 2010 Robust color segmentation algorithms in illumination variation conditions Jinhui Lan ( ) and Kai Shen ( Department of Measurement and Control Technologies,

More information

Research of Traffic Flow Based on SVM Method. Deng-hong YIN, Jian WANG and Bo LI *

Research of Traffic Flow Based on SVM Method. Deng-hong YIN, Jian WANG and Bo LI * 2017 2nd International onference on Artificial Intelligence: Techniques and Applications (AITA 2017) ISBN: 978-1-60595-491-2 Research of Traffic Flow Based on SVM Method Deng-hong YIN, Jian WANG and Bo

More information

Fast Road Sign Detection Using Hough Transform for Assisted Driving of Road Vehicles

Fast Road Sign Detection Using Hough Transform for Assisted Driving of Road Vehicles Fast Road Sign Detection Using Hough Transform for Assisted Driving of Road Vehicles Miguel Ángel García-Garrido, Miguel Ángel Sotelo, and Ernesto Martín-Gorostiza Department of Electronics, University

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

Driving Supportive System for Warning Traffic Sign Classification

Driving Supportive System for Warning Traffic Sign Classification IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 16, Issue 4, Ver. VII (Jul Aug. 2014), PP 35-44 Driving Supportive System for Warning Traffic Sign Classification

More information

A New Algorithm for Shape Detection

A New Algorithm for Shape Detection IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 19, Issue 3, Ver. I (May.-June. 2017), PP 71-76 www.iosrjournals.org A New Algorithm for Shape Detection Hewa

More information

Vision-based Frontal Vehicle Detection and Tracking

Vision-based Frontal Vehicle Detection and Tracking Vision-based Frontal and Tracking King Hann LIM, Kah Phooi SENG, Li-Minn ANG and Siew Wen CHIN School of Electrical and Electronic Engineering The University of Nottingham Malaysia campus, Jalan Broga,

More information

Edge Detection and Template Matching Approaches for Human Ear Detection

Edge Detection and Template Matching Approaches for Human Ear Detection Edge and Template Matching Approaches for Human Ear K. V. Joshi G H Patel College Engineering and Technology vallabh vidyanagar, Gujarat, India N. C. Chauhan A D Patel Institute Technology New vallabh

More information

Reduced Image Noise on Shape Recognition Using Singular Value Decomposition for Pick and Place Robotic Systems

Reduced Image Noise on Shape Recognition Using Singular Value Decomposition for Pick and Place Robotic Systems Reduced Image Noise on Shape Recognition Using Singular Value Decomposition for Pick and Place Robotic Systems Angelo A. Beltran Jr. 1, Christian Deus T. Cayao 2, Jay-K V. Delicana 3, Benjamin B. Agraan

More information

A Practical Guide to Support Vector Classification

A Practical Guide to Support Vector Classification A Practical Guide to Support Vector Classification Chih-Wei Hsu, Chih-Chung Chang, and Chih-Jen Lin Department of Computer Science and Information Engineering National Taiwan University Taipei 106, Taiwan

More information

Table of Contents. Recognition of Facial Gestures... 1 Attila Fazekas

Table of Contents. Recognition of Facial Gestures... 1 Attila Fazekas Table of Contents Recognition of Facial Gestures...................................... 1 Attila Fazekas II Recognition of Facial Gestures Attila Fazekas University of Debrecen, Institute of Informatics

More information

Binarization of Color Character Strings in Scene Images Using K-means Clustering and Support Vector Machines

Binarization of Color Character Strings in Scene Images Using K-means Clustering and Support Vector Machines 2011 International Conference on Document Analysis and Recognition Binarization of Color Character Strings in Scene Images Using K-means Clustering and Support Vector Machines Toru Wakahara Kohei Kita

More information

AUGMENTING GPS SPEED LIMIT MONITORING WITH ROAD SIDE VISUAL INFORMATION. M.L. Eichner*, T.P. Breckon

AUGMENTING GPS SPEED LIMIT MONITORING WITH ROAD SIDE VISUAL INFORMATION. M.L. Eichner*, T.P. Breckon AUGMENTING GPS SPEED LIMIT MONITORING WITH ROAD SIDE VISUAL INFORMATION M.L. Eichner*, T.P. Breckon * Cranfield University, UK, marcin.eichner@cranfield.ac.uk Cranfield University, UK, toby.breckon@cranfield.ac.uk

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

A Novel Smoke Detection Method Using Support Vector Machine

A Novel Smoke Detection Method Using Support Vector Machine A Novel Smoke Detection Method Using Support Vector Machine Hidenori Maruta Information Media Center Nagasaki University, Japan 1-14 Bunkyo-machi, Nagasaki-shi Nagasaki, Japan Email: hmaruta@nagasaki-u.ac.jp

More information

Object Tracking using HOG and SVM

Object Tracking using HOG and SVM Object Tracking using HOG and SVM Siji Joseph #1, Arun Pradeep #2 Electronics and Communication Engineering Axis College of Engineering and Technology, Ambanoly, Thrissur, India Abstract Object detection

More information

Color Content Based Image Classification

Color Content Based Image Classification Color Content Based Image Classification Szabolcs Sergyán Budapest Tech sergyan.szabolcs@nik.bmf.hu Abstract: In content based image retrieval systems the most efficient and simple searches are the color

More information

AN APPROACH OF SEMIAUTOMATED ROAD EXTRACTION FROM AERIAL IMAGE BASED ON TEMPLATE MATCHING AND NEURAL NETWORK

AN APPROACH OF SEMIAUTOMATED ROAD EXTRACTION FROM AERIAL IMAGE BASED ON TEMPLATE MATCHING AND NEURAL NETWORK AN APPROACH OF SEMIAUTOMATED ROAD EXTRACTION FROM AERIAL IMAGE BASED ON TEMPLATE MATCHING AND NEURAL NETWORK Xiangyun HU, Zuxun ZHANG, Jianqing ZHANG Wuhan Technique University of Surveying and Mapping,

More information

Pupil Localization Algorithm based on Hough Transform and Harris Corner Detection

Pupil Localization Algorithm based on Hough Transform and Harris Corner Detection Pupil Localization Algorithm based on Hough Transform and Harris Corner Detection 1 Chongqing University of Technology Electronic Information and Automation College Chongqing, 400054, China E-mail: zh_lian@cqut.edu.cn

More information

Adaptive Zoom Distance Measuring System of Camera Based on the Ranging of Binocular Vision

Adaptive Zoom Distance Measuring System of Camera Based on the Ranging of Binocular Vision Adaptive Zoom Distance Measuring System of Camera Based on the Ranging of Binocular Vision Zhiyan Zhang 1, Wei Qian 1, Lei Pan 1 & Yanjun Li 1 1 University of Shanghai for Science and Technology, China

More information

An Angle Estimation to Landmarks for Autonomous Satellite Navigation

An Angle Estimation to Landmarks for Autonomous Satellite Navigation 5th International Conference on Environment, Materials, Chemistry and Power Electronics (EMCPE 2016) An Angle Estimation to Landmarks for Autonomous Satellite Navigation Qing XUE a, Hongwen YANG, Jian

More information

A Novel Algorithm for Color Image matching using Wavelet-SIFT

A Novel Algorithm for Color Image matching using Wavelet-SIFT International Journal of Scientific and Research Publications, Volume 5, Issue 1, January 2015 1 A Novel Algorithm for Color Image matching using Wavelet-SIFT Mupuri Prasanth Babu *, P. Ravi Shankar **

More information

Project Report for EE7700

Project Report for EE7700 Project Report for EE7700 Name: Jing Chen, Shaoming Chen Student ID: 89-507-3494, 89-295-9668 Face Tracking 1. Objective of the study Given a video, this semester project aims at implementing algorithms

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

Detection and Recognition of Traffic Signs Based on HSV Vision Model and Shape features

Detection and Recognition of Traffic Signs Based on HSV Vision Model and Shape features 1366 JOURNAL OF COMPUTERS, VOL. 8, NO. 5, MAY 2013 Detection and Recognition of Traffic Signs Based on HSV Vision Model and Shape features Yixin Chen International School of Software, Wuhan University,

More information

Computers and Mathematics with Applications. An embedded system for real-time facial expression recognition based on the extension theory

Computers and Mathematics with Applications. An embedded system for real-time facial expression recognition based on the extension theory Computers and Mathematics with Applications 61 (2011) 2101 2106 Contents lists available at ScienceDirect Computers and Mathematics with Applications journal homepage: www.elsevier.com/locate/camwa An

More information

People Recognition and Pose Estimation in Image Sequences

People Recognition and Pose Estimation in Image Sequences People Recognition and Pose Estimation in Image Sequences Chikahito Nakajima Central Research Institute of Electric Power Industry, 2-11-1, Iwado Kita, Komae, Tokyo Japan. nakajima@criepi.denken.or.jp

More information

An embedded system of Face Recognition based on ARM and HMM

An embedded system of Face Recognition based on ARM and HMM An embedded system of Face Recognition based on ARM and HMM Yanbin Sun 1,2, Lun Xie 1, Zhiliang Wang 1,Yi An 2 1 Department of Electronic Information Engineering, School of Information Engineering, University

More information

A Fast Caption Detection Method for Low Quality Video Images

A Fast Caption Detection Method for Low Quality Video Images 2012 10th IAPR International Workshop on Document Analysis Systems A Fast Caption Detection Method for Low Quality Video Images Tianyi Gui, Jun Sun, Satoshi Naoi Fujitsu Research & Development Center CO.,

More information

Postprint.

Postprint. http://www.diva-portal.org Postprint This is the accepted version of a paper presented at 13th International Conference on Image Analysis and Recognition, ICIAR 2016, Póvoa de Varzim, Portugal, July 13-15.

More information

Medical images, segmentation and analysis

Medical images, segmentation and analysis Medical images, segmentation and analysis ImageLab group http://imagelab.ing.unimo.it Università degli Studi di Modena e Reggio Emilia Medical Images Macroscopic Dermoscopic ELM enhance the features 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

Computer Aided Drafting, Design and Manufacturing Volume 26, Number 2, June 2016, Page 18

Computer Aided Drafting, Design and Manufacturing Volume 26, Number 2, June 2016, Page 18 Computer Aided Drafting, Design and Manufacturing Volume 26, Number 2, June 2016, Page 18 CADDM The recognition algorithm for lane line of urban road based on feature analysis Xiao Xiao, Che Xiangjiu College

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

Scene Text Detection Using Machine Learning Classifiers

Scene Text Detection Using Machine Learning Classifiers 601 Scene Text Detection Using Machine Learning Classifiers Nafla C.N. 1, Sneha K. 2, Divya K.P. 3 1 (Department of CSE, RCET, Akkikkvu, Thrissur) 2 (Department of CSE, RCET, Akkikkvu, Thrissur) 3 (Department

More information

Cs : Computer Vision Final Project Report

Cs : Computer Vision Final Project Report Cs 600.461: Computer Vision Final Project Report Giancarlo Troni gtroni@jhu.edu Raphael Sznitman sznitman@jhu.edu Abstract Given a Youtube video of a busy street intersection, our task is to detect, track,

More information

Segmentation Framework for Multi-Oriented Text Detection and Recognition

Segmentation Framework for Multi-Oriented Text Detection and Recognition Segmentation Framework for Multi-Oriented Text Detection and Recognition Shashi Kant, Sini Shibu Department of Computer Science and Engineering, NRI-IIST, Bhopal Abstract - Here in this paper a new and

More information

Application of Geometry Rectification to Deformed Characters Recognition Liqun Wang1, a * and Honghui Fan2

Application of Geometry Rectification to Deformed Characters Recognition Liqun Wang1, a * and Honghui Fan2 6th International Conference on Electronic, Mechanical, Information and Management (EMIM 2016) Application of Geometry Rectification to Deformed Characters Liqun Wang1, a * and Honghui Fan2 1 School of

More information

Adaptive Learning of an Accurate Skin-Color Model

Adaptive Learning of an Accurate Skin-Color Model Adaptive Learning of an Accurate Skin-Color Model Q. Zhu K.T. Cheng C. T. Wu Y. L. Wu Electrical & Computer Engineering University of California, Santa Barbara Presented by: H.T Wang Outline Generic Skin

More information

Face Recognition Technology Based On Image Processing Chen Xin, Yajuan Li, Zhimin Tian

Face Recognition Technology Based On Image Processing Chen Xin, Yajuan Li, Zhimin Tian 4th International Conference on Machinery, Materials and Computing Technology (ICMMCT 2016) Face Recognition Technology Based On Image Processing Chen Xin, Yajuan Li, Zhimin Tian Hebei Engineering and

More information

Car tracking in tunnels

Car tracking in tunnels Czech Pattern Recognition Workshop 2000, Tomáš Svoboda (Ed.) Peršlák, Czech Republic, February 2 4, 2000 Czech Pattern Recognition Society Car tracking in tunnels Roman Pflugfelder and Horst Bischof Pattern

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

A Novel Criterion Function in Feature Evaluation. Application to the Classification of Corks.

A Novel Criterion Function in Feature Evaluation. Application to the Classification of Corks. A Novel Criterion Function in Feature Evaluation. Application to the Classification of Corks. X. Lladó, J. Martí, J. Freixenet, Ll. Pacheco Computer Vision and Robotics Group Institute of Informatics and

More information

Real-Time Detection of Road Markings for Driving Assistance Applications

Real-Time Detection of Road Markings for Driving Assistance Applications Real-Time Detection of Road Markings for Driving Assistance Applications Ioana Maria Chira, Ancuta Chibulcutean Students, Faculty of Automation and Computer Science Technical University of Cluj-Napoca

More information

Pixel-Pair Features Selection for Vehicle Tracking

Pixel-Pair Features Selection for Vehicle Tracking 2013 Second IAPR Asian Conference on Pattern Recognition Pixel-Pair Features Selection for Vehicle Tracking Zhibin Zhang, Xuezhen Li, Takio Kurita Graduate School of Engineering Hiroshima University Higashihiroshima,

More information

The Effects of Outliers on Support Vector Machines

The Effects of Outliers on Support Vector Machines The Effects of Outliers on Support Vector Machines Josh Hoak jrhoak@gmail.com Portland State University Abstract. Many techniques have been developed for mitigating the effects of outliers on the results

More information

Data mining with Support Vector Machine

Data mining with Support Vector Machine Data mining with Support Vector Machine Ms. Arti Patle IES, IPS Academy Indore (M.P.) artipatle@gmail.com Mr. Deepak Singh Chouhan IES, IPS Academy Indore (M.P.) deepak.schouhan@yahoo.com Abstract: Machine

More information

Online Mathematical Symbol Recognition using SVMs with Features from Functional Approximation

Online Mathematical Symbol Recognition using SVMs with Features from Functional Approximation Online Mathematical Symbol Recognition using SVMs with Features from Functional Approximation Birendra Keshari and Stephen M. Watt Ontario Research Centre for Computer Algebra Department of Computer Science

More information

Mobile Camera Based Text Detection and Translation

Mobile Camera Based Text Detection and Translation Mobile Camera Based Text Detection and Translation Derek Ma Qiuhau Lin Tong Zhang Department of Electrical EngineeringDepartment of Electrical EngineeringDepartment of Mechanical Engineering Email: derekxm@stanford.edu

More information

12 Classification using Support Vector Machines

12 Classification using Support Vector Machines 160 Bioinformatics I, WS 14/15, D. Huson, January 28, 2015 12 Classification using Support Vector Machines This lecture is based on the following sources, which are all recommended reading: F. Markowetz.

More information

An adaptive container code character segmentation algorithm Yajie Zhu1, a, Chenglong Liang2, b

An adaptive container code character segmentation algorithm Yajie Zhu1, a, Chenglong Liang2, b 6th International Conference on Machinery, Materials, Environment, Biotechnology and Computer (MMEBC 2016) An adaptive container code character segmentation algorithm Yajie Zhu1, a, Chenglong Liang2, b

More information

Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong)

Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong) Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong) References: [1] http://homepages.inf.ed.ac.uk/rbf/hipr2/index.htm [2] http://www.cs.wisc.edu/~dyer/cs540/notes/vision.html

More information

Classification with Class Overlapping: A Systematic Study

Classification with Class Overlapping: A Systematic Study Classification with Class Overlapping: A Systematic Study Haitao Xiong 1 Junjie Wu 1 Lu Liu 1 1 School of Economics and Management, Beihang University, Beijing 100191, China Abstract Class overlapping has

More information

Digital image processing

Digital image processing Digital image processing Image enhancement algorithms: grey scale transformations Any digital image can be represented mathematically in matrix form. The number of lines in the matrix is the number of

More information

An Efficient Approach for Color Pattern Matching Using Image Mining

An Efficient Approach for Color Pattern Matching Using Image Mining An Efficient Approach for Color Pattern Matching Using Image Mining * Manjot Kaur Navjot Kaur Master of Technology in Computer Science & Engineering, Sri Guru Granth Sahib World University, Fatehgarh Sahib,

More information

CS231A Course Project Final Report Sign Language Recognition with Unsupervised Feature Learning

CS231A Course Project Final Report Sign Language Recognition with Unsupervised Feature Learning CS231A Course Project Final Report Sign Language Recognition with Unsupervised Feature Learning Justin Chen Stanford University justinkchen@stanford.edu Abstract This paper focuses on experimenting with

More information

Dimension Reduction in Network Attacks Detection Systems

Dimension Reduction in Network Attacks Detection Systems Nonlinear Phenomena in Complex Systems, vol. 17, no. 3 (2014), pp. 284-289 Dimension Reduction in Network Attacks Detection Systems V. V. Platonov and P. O. Semenov Saint-Petersburg State Polytechnic University,

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

Road Sign Detection and Tracking from Complex Background

Road Sign Detection and Tracking from Complex Background Road Sign Detection and Tracking from Complex Background By Chiung-Yao Fang( 方瓊瑤 ), Sei-Wang Chen( 陳世旺 ), and Chiou-Shann Fuh( 傅楸善 ) Department of Information and Computer Education National Taiwan Normal

More information

Visibility Estimation of Road Signs Considering Detect-ability Factors for Driver Assistance Systems

Visibility Estimation of Road Signs Considering Detect-ability Factors for Driver Assistance Systems WSEAS TRANSACTIONS on SIGNA PROCESSING Visibility Estimation of Road Signs Considering Detect-ability Factors for Driver Assistance Systems JAFAR J. AUKHAIT Communications, Electronics and Computer Engineering

More information

Using Layered Color Precision for a Self-Calibrating Vision System

Using Layered Color Precision for a Self-Calibrating Vision System ROBOCUP2004 SYMPOSIUM, Instituto Superior Técnico, Lisboa, Portugal, July 4-5, 2004. Using Layered Color Precision for a Self-Calibrating Vision System Matthias Jüngel Institut für Informatik, LFG Künstliche

More information

Bus Detection and recognition for visually impaired people

Bus Detection and recognition for visually impaired people Bus Detection and recognition for visually impaired people Hangrong Pan, Chucai Yi, and Yingli Tian The City College of New York The Graduate Center The City University of New York MAP4VIP Outline Motivation

More information

Data Mining: Concepts and Techniques. Chapter 9 Classification: Support Vector Machines. Support Vector Machines (SVMs)

Data Mining: Concepts and Techniques. Chapter 9 Classification: Support Vector Machines. Support Vector Machines (SVMs) Data Mining: Concepts and Techniques Chapter 9 Classification: Support Vector Machines 1 Support Vector Machines (SVMs) SVMs are a set of related supervised learning methods used for classification Based

More information

Image enhancement for face recognition using color segmentation and Edge detection algorithm

Image enhancement for face recognition using color segmentation and Edge detection algorithm Image enhancement for face recognition using color segmentation and Edge detection algorithm 1 Dr. K Perumal and 2 N Saravana Perumal 1 Computer Centre, Madurai Kamaraj University, Madurai-625021, Tamilnadu,

More information

Facial expression recognition using shape and texture information

Facial expression recognition using shape and texture information 1 Facial expression recognition using shape and texture information I. Kotsia 1 and I. Pitas 1 Aristotle University of Thessaloniki pitas@aiia.csd.auth.gr Department of Informatics Box 451 54124 Thessaloniki,

More information

EE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm

EE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm EE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm Group 1: Mina A. Makar Stanford University mamakar@stanford.edu Abstract In this report, we investigate the application of the Scale-Invariant

More information

TRAFFIC SIGN RECOGNITION USING A MULTI-TASK CONVOLUTIONAL NEURAL NETWORK

TRAFFIC SIGN RECOGNITION USING A MULTI-TASK CONVOLUTIONAL NEURAL NETWORK TRAFFIC SIGN RECOGNITION USING A MULTI-TASK CONVOLUTIONAL NEURAL NETWORK Dr. S.V. Shinde Arshiya Sayyad Uzma Shaikh Department of IT Department of IT Department of IT Pimpri Chinchwad college of Engineering

More information

THE VIEWING TRANSFORMATION

THE VIEWING TRANSFORMATION ECS 178 Course Notes THE VIEWING TRANSFORMATION Kenneth I. Joy Institute for Data Analysis and Visualization Department of Computer Science University of California, Davis Overview One of the most important

More information