Scene Text Extraction Using Focus of Mobile Camera Egyul Kim, SeongHun Lee, JinHyung Kim Artificial Intelligence & Pattern Recognition Lab, KAIST, Korea.

Slides:



Advertisements
Similar presentations
A Graph based Geometric Approach to Contour Extraction from Noisy Binary Images Amal Dev Parakkat, Jiju Peethambaran, Philumon Joseph and Ramanathan Muthuganapathy.
Advertisements

QR Code Recognition Based On Image Processing
Road-Sign Detection and Recognition Based on Support Vector Machines Saturnino, Sergio et al. Yunjia Man ECG 782 Dr. Brendan.
Evaluating Color Descriptors for Object and Scene Recognition Koen E.A. van de Sande, Student Member, IEEE, Theo Gevers, Member, IEEE, and Cees G.M. Snoek,
Robust statistical method for background extraction in image segmentation Doug Keen March 29, 2001.
SUPPORTING LANDMARK IMAGE RETRIEVAL WITH SKYLINE EXTRACTION TECHNIQUES Date : 2012 / 04 / 12 資訊碩一 LAB603.
Rear Lights Vehicle Detection for Collision Avoidance Evangelos Skodras George Siogkas Evangelos Dermatas Nikolaos Fakotakis Electrical & Computer Engineering.
Wen-Hung Liao Department of Computer Science National Chengchi University November 27, 2008 Estimation of Skin Color Range Using Achromatic Features.
LING 111 Teaching Demo By Tenghui Zhu Introduction to Edge Detection Image Segmentation.
Facial feature localization Presented by: Harvest Jang Spring 2002.
High-level Component Filtering for Robust Scene Text Detection
IEEE TCSVT 2011 Wonjun Kim Chanho Jung Changick Kim
Modeling Pixel Process with Scale Invariant Local Patterns for Background Subtraction in Complex Scenes (CVPR’10) Shengcai Liao, Guoying Zhao, Vili Kellokumpu,
Real-time Embedded Face Recognition for Smart Home Fei Zuo, Student Member, IEEE, Peter H. N. de With, Senior Member, IEEE.
Natural and Seamless Image Composition Wenxian Yang, Jianmin Zheng, Jianfei Cai, Senior Member, IEEE, Susanto Rahardja, Senior Member, IEEE, and Chang.
Text Detection in Video Min Cai Background  Video OCR: Text detection, extraction and recognition  Detection Target: Artificial text  Text.
Robust Object Segmentation Using Adaptive Thresholding Xiaxi Huang and Nikolaos V. Boulgouris International Conference on Image Processing 2007.
Face Detection: a Survey Speaker: Mine-Quan Jing National Chiao Tung University.
Region-Level Motion- Based Background Modeling and Subtraction Using MRFs Shih-Shinh Huang Li-Chen Fu Pei-Yung Hsiao 2007 IEEE.
An Approach to Korean License Plate Recognition Based on Vertical Edge Matching Mei Yu and Yong Deak Kim Ajou University Suwon, , Korea 指導教授 張元翔.
A Wrapper-Based Approach to Image Segmentation and Classification Michael E. Farmer, Member, IEEE, and Anil K. Jain, Fellow, IEEE.
A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE.
Shadow Removal Seminar
Smart Traveller with Visual Translator. What is Smart Traveller? Mobile Device which is convenience for a traveller to carry Mobile Device which is convenience.
A Real-Time for Classification of Moving Objects
Handwritten Thai Character Recognition Using Fourier Descriptors and Robust C-Prototype Olarik Surinta Supot Nitsuwat.
Shadow Detection In Video Submitted by: Hisham Abu saleh.
Tricolor Attenuation Model for Shadow Detection. INTRODUCTION Shadows may cause some undesirable problems in many computer vision and image analysis tasks,
New Segmentation Methods Advisor : 丁建均 Jian-Jiun Ding Presenter : 蔡佳豪 Chia-Hao Tsai Date: Digital Image and Signal Processing Lab Graduate Institute.
Mutual Information-based Stereo Matching Combined with SIFT Descriptor in Log-chromaticity Color Space Yong Seok Heo, Kyoung Mu Lee, and Sang Uk Lee.
EADS DS / SDC LTIS Page 1 7 th CNES/DLR Workshop on Information Extraction and Scene Understanding for Meter Resolution Image – 29/03/07 - Oberpfaffenhofen.
CPSC 601 Lecture Week 5 Hand Geometry. Outline: 1.Hand Geometry as Biometrics 2.Methods Used for Recognition 3.Illustrations and Examples 4.Some Useful.
A General Framework for Tracking Multiple People from a Moving Camera
An efficient method of license plate location Pattern Recognition Letters 26 (2005) Journal of Electronic Imaging 11(4), (October 2002)
S EGMENTATION FOR H ANDWRITTEN D OCUMENTS Omar Alaql Fab. 20, 2014.
1 Iterative Multimodel Subimage Binarization for Handwritten Character Segmentation Author: Amer Dawoud and Mohamed S. Kamel Source: IEEE TRANSACTIONS.
Joon Hyung Shim, Jinkyu Yang, and Inseong Kim
1 Webcam Mouse Using Face and Eye Tracking in Various Illumination Environments Yuan-Pin Lin et al. Proceedings of the 2005 IEEE Y.S. Lee.
Scene Completion Using Millions of Photographs James Hays, Alexei A. Efros Carnegie Mellon University ACM SIGGRAPH 2007.
NTIT IMD 1 Speaker: Ching-Hao Lai( 賴璟皓 ) Author: Hongliang Bai, Junmin Zhu and Changping Liu Source: Proceedings of IEEE on Intelligent Transportation.
Interactive Sand Art Drawing Using RGB-D Sensor
Imaged Document Text Retrieval without OCR IEEE Trans. on PAMI vol.24, no.6 June, 2002 報告人:周遵儒.
Handwritten Signature Verification
Image-Based Segmentation of Indoor Corridor Floors for a Mobile Robot Yinxiao Li and Stanley T. Birchfield The Holcombe Department of Electrical and Computer.
Zhongyan Liang, Sanyuan Zhang Under review for Journal of Zhejiang University Science C (Computers & Electronics) Publisher: Springer A Credible Tilt License.
By Pushpita Biswas Under the guidance of Prof. S.Mukhopadhyay and Prof. P.K.Biswas.
Wonjun Kim and Changick Kim, Member, IEEE
Face Detection Final Presentation Mark Lee Nic Phillips Paul Sowden Andy Tait 9 th May 2006.
Preliminary Transformations Presented By: -Mona Saudagar Under Guidance of: - Prof. S. V. Jain Multi Oriented Text Recognition In Digital Images.
Arabic Handwriting Recognition Thomas Taylor. Roadmap  Introduction to Handwriting Recognition  Introduction to Arabic Language  Challenges of Recognition.
Date of download: 5/29/2016 Copyright © 2016 SPIE. All rights reserved. From left to right are camera views 1,2,3,5 of surveillance videos in TRECVid benchmarking.
NLP&CC 2012 报告人:许灿辉 单 位:北京大学计算机科学技术研究所 Integration of Text Information and Graphic Composite for PDF Document Analysis 基于复合图文整合的 PDF 文档分析 Integration of.
Learning and Removing Cast Shadows through a Multidistribution Approach Nicolas Martel-Brisson, Andre Zaccarin IEEE TRANSACTIONS ON PATTERN ANALYSIS AND.
Portable Camera-Based Assistive Text and Product Label Reading From Hand-Held Objects for Blind Persons.
Shadow Detection in Remotely Sensed Images Based on Self-Adaptive Feature Selection Jiahang Liu, Tao Fang, and Deren Li IEEE TRANSACTIONS ON GEOSCIENCE.
A School of Mechanical Engineering, Hebei University of Technology, Tianjin , China Research on Removing Shadow in Workpiece Image Based on Homomorphic.
Student Gesture Recognition System in Classroom 2.0 Chiung-Yao Fang, Min-Han Kuo, Greg-C Lee, and Sei-Wang Chen Department of Computer Science and Information.
Related Research and Progress in Historical Document Recognition 马龙龙 多语言处理研究室
Video object segmentation and its salient motion detection using adaptive background generation Kim, T.K.; Im, J.H.; Paik, J.K.;  Electronics Letters 
Author : Sang Hwa Lee, Junyeong Choi, and Jong-Il Park
Presenter: Ibrahim A. Zedan
A new data transfer method via signal-rich-art code images captured by mobile devices Source: IEEE Transactions on Circuits and Systems for Video Technology,
Text Detection in Images and Video
RGB-D Image for Scene Recognition by Jiaqi Guo
Estimation of Skin Color Range Using Achromatic Features
Color Image Retrieval based on Primitives of Color Moments
Speaker: YI-JIA HUANG Date: 2011/12/08 Authors: C. N
Christian Wolf Jean-Michel Jolion Françoise Chassaing
Source: Pattern Recognition Letters 29 (2008)
Color Image Retrieval based on Primitives of Color Moments
Presentation transcript:

Scene Text Extraction Using Focus of Mobile Camera Egyul Kim, SeongHun Lee, JinHyung Kim Artificial Intelligence & Pattern Recognition Lab, KAIST, Korea Ming Chuang University Date: Location: th International Conference on Document Analysis and Recognition 文件分析與辨識 國際研討會 S403-1

Outline 1.Introduction 2.Scene text extraction method 2.1 Selection of text color candidates 2.2 Extraction of connected components 2.3 Text verification 3.Experimental result 4.Conclusion /09 $25.00 © 2009 IEEE DOI /ICDAR

1.Introduction : The Context 3

The challenging 4  Non-uniform illumination  Lighting condition, shadows  Complex background  Outdoor images  Complex color  Complex layout  Non-text pixels surround text pixels  Window bars → ‘I’ (text-like)

Related work 5  Past …  Sobel edge detection  Otsu binarization  Connected component extraction  Rule-based connected component filtering  Binarization to gray and gray inverse  Color component  Uniform background  Complex background → missing, false  Sol : interactive graph user interface

2. Scene text extraction method 6

2.1 Selection of text color candidates 1 7  HCL (Hue, chroma, luminance)  Hue is Robust on illumination  compare to luminance or RGB color  Color difference between text : background D HCL = A L (l − l s ) 2 + A CH {c 2 + c 2 s − 2cc s cos(h − h s )} (1) √ ___________________________________________________ Seed color RGBHCL

 Mean-Shift algorithm  Non-parametric clustering  2~5 seed color  Text boundary:  Affect true text color Text & background combine Text segment into small pieces  Sobel edge 2.1 Selection of text color candidates 2 8 seed’ j Figure 3. Color distributions of pixel samples

2.2 Extraction of connected components 1 9  Binarization method  Base on HCL color space Figure 4. Components expansion 0:1

Connected component ? 10

2.2 Extraction of connected components 2 11  Adaptive binarization  Local vs. Global threshold  Text candidate  Fully connected component in binarization  Initial component Figure 5. Binarization result: (a)original image (b)HCL distance on seed color (c)Global binarization result (d)adaptive binarization result

2.3 Text verification 12  Character features  Horizontal  Geometric restrictions(height, width, compactness)  Final text reject reasons (1) Number of components ≥ 3 (2) Variation of distance between components (3) Variation of heights of components (4) Variation of compactness of components Figure 6. Text verification

4. Conclusion 1.Text color candidate  Pixel sampling  Mean-shift alg. 2.Connected components  HCL distance  Adaptive Binarization 3.Text Verification  True text components 13 PrecisionRecall Proposed method (0.89) Figure 7. Example of text detection results

Senior citizen reading assisting 14

Q & A 報告完畢 感謝聆聽 15