Improving the non-extensive medical image segmentation based on Tsallis entropy.
ABSTRACT Thresholding techniques for image segmentation is one of the most popular approaches in Computational Vision systems. Recently,
M. Albuquerque has proposed a thresholding method (Albuquerque et al. in Pattern Recognit Lett 25:1059–1065, 2004) based on the Tsallis entropy, which is a generalization of the traditional Shannon entropy through the introduction of an
entropic parameter q. However, the solution may be very dependent on the q value and the development of an automatic approach to compute a suitable value for q remains also an open problem. In this paper, we propose a generalization of the Tsallis theory in order to improve the non-extensive
segmentation method. Specifically, we work out over a suitable property of Tsallis theory, named the pseudo-additive property,
which states the formalism to compute the whole entropy from two probability distributions given an unique q value. Our idea is to use the original M. Albuquerque’s algorithm to compute an initial threshold and then update the q value using the ratio of the areas observed in the image histogram for the background and foreground. The proposed technique
is less sensitive to the q value and overcomes the M. Albuquerque and k-means algorithms, as we will demonstrate for both ultrasound breast cancer images and synthetic data.
- SourceAvailable from: psu.edu
Conference Proceeding: A fast algorithm for MDL-based multi-band image segmentation[show abstract] [hide abstract]
ABSTRACT: We consider the problem of image segmentation and describe an algorithm that is based on the Minimum Description Length (MDL) principle, is fast, is applicable to multi-band images, and guarantees closed regions. We construct an objective function that, when minimized, yields a partitioning of the image into regions where the pixel values in each band of each region are described by a polynomial surface plus noise. The polynomial orders and their coefficients are determined by the algorithm. The minimization is difficult because (1) it involves a search over a very large space and (2) there is extensive computation required at each stage of the search. To address the first of these problems we use a region-merging minimization algorithm. To address the second we use an incremental polynomial regression that uses computations from the previous stage to compute results in the current stage, resulting in a significant speed up over the non-incremental technique. The segmentation result obtained is suboptimal in general but of high quality. Results on real images are shownComputer Vision and Pattern Recognition, 1994. Proceedings CVPR '94., 1994 IEEE Computer Society Conference on; 07/1994
- [show abstract] [hide abstract]
ABSTRACT: We conduct an exhaustive survey of image thresholding methods, categorize them, express their formulas under a uniform notation, and finally carry their performance comparison. The thresholding methods are categorized according to the information they are exploiting, such as histogram shape, measurement space clustering, entropy, object attributes, spatial correlation, and local gray-level surface. 40 selected thresholding methods from various categories are compared in the context of nondestructive testing applications as well as for document images. The comparison is based on the combined performance measures. We identify the thresholding algorithms that perform uniformly better over nonde- structive testing and document image applications. © 2004 SPIE and IS&T. (DOI: 10.1117/1.1631316)J. Electronic Imaging. 01/2004; 13:146-168.
- [show abstract] [hide abstract]
ABSTRACT: Two methods of entropic thresholding proposed by Pun (Signal Process.,2, 1980, 223–237;Comput. Graphics Image Process.16, 1981, 210–239) have been carefully and critically examined. A new method with a sound theoretical foundation is proposed. Examples are given on a number of real and artifically generated histograms.Computer Vision, Graphics, and Image Processing. 01/1980;