Algorithms for Image Thresholding

Thresholding is an important and effective step in almost all areas of image processing. It is a main tool in pattern recognition, image segmentation, edge detection and scene analysis. In this book, we talk about different applications of thresholding such as: acoustic signal processing, muscle activity detection in EMG signal analysis, optical character recognition and character image extraction, image thresholding of historical documents, color applications, non destructive testing applications,forest fire detection, medical imaging, biometric application, satellite imaging, and object detection. In this way, we present Histogram shape, clustering, entropy-based thresholding method and types of entropy. Also we discuss many thresholding algorithms such as: Algorithms based on attribute similarity, spatial thresholding methods, and locally adaptive thresholding methods. In addition, we present a thresholding technique based on 2D Tsallis entropy. The effectiveness of the proposed method is demonstrated by using examples from the real-world and synthetic images. The performance evaluation of the proposed technique in terms of the quality of the thresholded images are presented.