IMAGE SEGMENTATION Edited by Pei-Gee Peter Ho Image Segmentation Edited by Pei-Gee Peter Ho Published by InTech Janeza Trdine 9, 51000 Rijeka, Croatia Copyright © 2011 InTech All chapters are Open Access articles distributed under the Creative Commons Non Commercial Share Alike Attribution 3.0 license, which permits to copy, distribute, transmit, and adapt the work in any medium, so long as the original work is properly cited. After this work has been published by InTech, authors have the right to republish it, in whole or part, in any publication of which they are the author, and to make other personal use of the work. Any republication, referencing or personal use of the work must explicitly identify the original source. Statements and opinions expressed in the chapters are these of the individual contributors and not necessarily those of the editors or publisher. No responsibility is accepted for the accuracy of information contained in the published articles. The publisher assumes no responsibility for any damage or injury to persons or property arising out of the use of any materials, instructions, methods or ideas contained in the book. Publishing Process Manager Ivana Lorkovic Technical Editor Teodora Smiljanic Cover Designer Martina Sirotic Image Copyright Robert Gubbins, 2010. Used under license from Shutterstock.com First published March, 2011 Printed in India A free online edition of this book is available at www.intechopen.com Additional hard copies can be obtained from orders@intechweb.org Image Segmentation, Edited by Pei-Gee Peter Ho p. cm. ISBN 978-953-307-228-9 free online editions of InTech Books and Journals can be found at www.intechopen.com Part 1 Chapter 1 Chapter 2 Part 2 Chapter 3 Chapter 4 Chapter 5 Chapter 6 Chapter 7 Preface IX Survey of Image Segmentation Algorithms 1 A Survey of Image Segmentation by the Classical Method and Resonance Algorithm 3 Fengzhi Dai, Masanori Sugisaka and Baolong Zhang A Review of Algorithms for Segmentation of Retinal Image Data Using Optical Coherence Tomography 15 Delia Cabrera DeBuc Image Segmentation Methods 55 Image Segmentation through Clustering Based on Natural Computing Techniques 57 Jose Alfredo F. Costa and Jackson G. de Souza Segmentation with Learning Automata 83 Erik Cuevas, Daniel Zaldivar and Marco Pérez-Cisneros Surround Suppression and Recurrent Interactions V1-V2 for Natural Scene Boundary Detection 99 Francisco J. Díaz-Pernas, Míriam Antón-Rodríguez, Isabel de la Torre-Díez, Mario Martínez-Zarzuela, David González-Ortega, Daniel Boto-Giralda and J. Fernando Díez-Higuera Using Emergence Phenomenon in Meaningful Image Segmentation for Content-based Image Retrieval 119 Sagarmay Deb Dual Active Contour Models for Medical Image Segmentation 129 Gilson Giraldi, Paulo Rodrigues, Jasjit Suri and Sameer Singh Contents Contents VI Image Segmentation Using Maximum Spanning Tree on Affinity Matrix 153 Qiang He and Chee-Hung Henry Chu Image Segmentation by Autoregressive Time Series Model 161 Pei-Gee Peter Ho Evolutionary-based Image Segmentation Methods 179 Licheng Jiao Segmentation of Handwritten Document Images into Text Lines 225 Vassilis Katsouros and Vassilis Papavassiliou IR Image Segmentation by Combining Genetic Algorithm and Multi-scale Edge Detection 241 Li Zhaohui and Chen Ming Segmentation of Remotely Sensed Imagery: Moving from Sharp Objects to Fuzzy Regions 249 Ivan Lizarazo and Paul Elsner Color-based Texture Image Segmentation for Vehicle Detection 273 Ricardo Mejía-Iñigo, María E. Barilla-Pérez and Héctor A. Montes-Venegas Image Segmentation Applications 291 An Enhanced Level Set Algorithm for Wrist Bone Segmentation 293 Donatello Conte, Pasquale Foggia, Francesco Tufano and Mario Vento Mineral Grain Boundary Detection With Image Processing Method: From Edge Detection Operation To Level Set Technique 309 Bibo Lu and Weixing Wang Multiscale Segmentation Techniques for Textile Images 327 Xiqun Lu JSEG Algorithm and Statistical ANN Image Segmentation Techniques for Natural Scenes 343 Luciano Cássio Lulio, Mário Luiz Tronco and Arthur José Vieira Porto Chapter 8 Chapter 9 Chapter 10 Chapter 11 Chapter 12 Chapter 13 Chapter 14 Part 3 Chapter 15 Chapter 16 Chapter 17 Chapter 18 Contents VII Image Segmentation of Ziehl-Neelsen Sputum Slide Images for Tubercle Bacilli Detection 365 R. A. A. Raof, M. Y. Mashor, R. B. Ahmad and S. S. M. Noor Image Segmentation Based on a Two-Dimensional Histogram 379 Masmoudi Lhoussaine, Zennouhi Rachid and Mohamed EL Ansari Segmentation Methods for Biomedical Images 389 Roberto Rodríguez Morales Algorithm Selection Based on a Region Similarity Metric for Intracellular Image Segmentation 419 Satoko Takemoto and Hideo Yokota Extraction of Estuarine/Coastal Environmental Bodies from Satellite Data through Image Segmentation Techniques 435 Ana Teodoro and Hernâni Gonçalves Rock Fracture Image Segmentation Algorithms 459 Weixing Wang Image Segmentation Integrating Generative and Discriminative Methods 489 Yuee Wu and Houqin Bian Pixon-Based Image Segmentation 495 Hamid Hassanpour, Hadi Yousefian and Amin Zehtabian Hardware Implementation 517 Hardware Implementation of a Real-Time Image Segmentation Circuit based on Fuzzy Logic for Edge Detection Application 519 Angel Barriga Chapter 19 Chapter 20 Chapter 21 Chapter 22 Chapter 23 Chapter 24 Chapter 25 Chapter 26 Part 4 Chapter 27 Pref ac e It was estimated that 80% of the information received by human being is visual. Image processing is evolving fast and continually. During the past 10 years, there has been a signifi cant increase in knowledge-based image analysis, image recognition as well as image segmentation. To study a specifi c object in an image, its boundary can be high- lighted by an image segmentation procedure. The objective of the image segmentation is to simplify the representation of pictures into meaningful information by partitioning into image regions. Image segmenta- tion is a technique to locate certain objects or boundaries within an image. There are many algorithms and techniques have been developed to solve image segmentation problems, though, none of the method is a general solution. Among the best, these are neural networks segmentation, one-dimensional signal segmentation, multi-scale segmentation, model based segmentation, graphic partitioning, region growing and K-mean clustering segmentation methods. This book brings together many diff erent aspects of the current research on several fi elds associated to digital image segmentation. Four main parts have been defi ned and allowed gathering the 27 chapters around the following topics: Survey of Image Segmentation Algorithms, Image Segmentation methods, Image Segmentation Appli- cations and Hardware Implementation of Image Segmentation. The book starts with a fi rst set of chapters which addresses most recent general ap- proaches in the image segmentation fi elds. One can fi nd discussion about various new trends on image segmentation techniques. The evolutionary image segmentation algo- rithms and methods are presented next. Recently the most used approach in segmenta- tion of medical images is the level set which is based on optimization mathematics. A segmentation of the image plane is computed by locally minimizing an appropriate en- ergy functional E(C) by evolving the contour C of the region to be segmented starting from an initial contour. In general, this method may use either an explicit (parametric) or implicit representation of the contours. The active contour (also called snakes) image segmentation scheme is very popular in medical surgery these days. The basic idea of the dual snakes is to reject local minima by using two contours: one which contracts from outside the target and one which expands from inside. Such proposal makes pos- sible to reduce the sensitivity to initialization through the comparison between the two X Preface contours energy and positions. The newly developed combined Autoregressive time series imaging modeling with either region growing or Support Vector Machine as classifi ers are detailed in one of the book chapter. In order to solve the image segmen- tation thresholding problem , a new way of using an optimization algorithm based on learning automata for multilevel thresholding is proposed in one chapter of this book. The pixon concept based on a set of disjoint regions with constant shapes and variable sizes was introduced in 1993 to decreases the computational time on image segmentation. A few innovative methods to improve the effi ciency are also included. Nevertheless, the image segmentation applications that demand constrained response times, the specifi c hardware implementation is required. In this book, the chapter ti- tle “Hardware Implementation of a Real-Time Image Segmentation Circuit based on Fuzzy Logic for Edge Detection Application” provides the hardware approach for im- age segmentation. Last, but not the least, we would like to thank all contributors to this book for their re- search, Intech publisher CEO Dr. Aleksandar Lazinica and Ms. Ivana Lorkovic for their publishing eff ort. I am sure that you will enjoy reading this book and get many helpful ideas and overviews on your own study. Pei-Gee Peter Ho, Ph.D. DSP Algorithm development group Naval Undersea Warfare Center at Newport RI, USA [...]... experiment (including the image sampling, processing, segmentation and recognition), which is to segment the image and then recognize each character one by one Part 1 Part 3 Part 2 Fig 3 An example of the classical image segmentation In Fig 3, part 1 is the image sampling and segmentation The top-left window in part 1 gives the image sampled directly from the camera After image processing, the segmented... can be chosen by any features of the image, and the different selection of features results to different threshold δ In this chapter, the eight-connectivity is used to connect the pixels of the object 12 Image Segmentation 3.4 Image segmentation When there are multi-objects in an image, image segmentation is necessary: locating and isolating the objects from the image and then identifying them Once... corner of the image The image is divided into three parts The sky is separated into part-1 and 3 by a trunk of tree in the image Part-2 is the region of trees The influence of clouds is greatly eliminated because the resonance algorithm can handle gradual changes of intensity A Survey of Image Segmentation by the Classical Method and Resonance Algorithm 13 Fig 10 Image segmentation: (a) color image, (b)... break of the characters In Fig 1, there are four rows and four columns of digits 2.2 Image segmentation If there are several targets in an image, image segmentation is necessary: locating and isolating the targets in an image and then identifying them Once isolated, the targets can be measured and classified The general image segmentation algorithm (Agui, Nakajima & Kimi, 1990) is shown in Fig 2a And... threshold for pixel-based image processing methods to deal with this gradation Resonance algorithm is an unsupervised method to generate the region (or feature space) from similar pixels (or feature vectors) in an image It tolerates gradual changes of texture to some extent for image segmentation The purpose of section 3 is to propose the resonancetheory-based method for image segmentation, which means... But different images, or different regions in one image, may have different thresholds We propose an automatic selection method for δ Since δ is used to partition the different regions in an image, it is rather a range of values (determine the maximum and minimum values) than a fixed value to ensure the points have the same or similar features in one region If δ for different regions in an image are selected... segmentation, which is useful when the reader wants to understand image segmentation clearly Fig 1 The principle of segmentation Fig 1 gives the example of the digit segmentation In the image there are some digits but as the image style, not the character If the computer or intelligent system wants to recognize these digits autonomously, first image segmentation is needed to search and locate each digit,... into one region 3.5 The experiment In this section, compared to the conventional method, the natural image in real environment will be applied to analyze the resonance algorithm for image segmentation Fig 10 shows the source image and the segmentation result (Dai, Fujihara & Sugisaka, 2008) In the original image of Fig 10a, sky and trees are two main regions, while the color of the sky is varied gradually... one of the most important sensors for computer vision That is to say, the intelligent system endeavours to find out what is in an image taken by the camera: traffic signs, obstacles or guidelines For image analysis, image segmentation is needed, which means to partition an image into several regions that have homogeneous texture feature This process is usually realized by the region-based, boundary-... interpretation of the OCT image along with the current and future technology development of OCT systems is also presented in this section Section 4 provides the necessary background about medical image segmentation approaches A review of algorithms for segmentation of retinal image data using OCT is presented in Section 5 All A Review of Algorithms for Segmentation of Retinal Image Data Using Optical . col -1: L (line[0].starty, line[0].endy, line[0] [1] .startx, line[0] [1] .endx) row -1, col-0: 7 (line [1] .starty, line [1] .endy, line [1] [0].startx, line [1] [0].endx) row -1, col -1: 6 (line [1] .starty,. 10 Chapter 11 Chapter 12 Chapter 13 Chapter 14 Part 3 Chapter 15 Chapter 16 Chapter 17 Chapter 18 Contents VII Image Segmentation of Ziehl-Neelsen Sputum Slide Images for Tubercle Bacilli Detection. USA Part 1 Survey of Image Segmentation Algorithms 1 A Survey of Image Segmentation by the Classical Method and Resonance Algorithm Fengzhi Dai 1 , Masanori Sugisaka 2 and Baolong Zhang 3 1 Tianjin