Abstract-A novel graph theoretic approach for data clustering is presented and its application to the image segmentation problem is demonstrated. The data to be clustered are represented by an undirected adjacency graph G with arc capacities assigned to reflect the similarity between the linked vertices. Clustering is achieved by removing arcs of G to form mutually exclusive subgraphs such that the largest inter-subgraph maximum flow is minimized. For graphs of moderate size (- 2000 vertices), the optimal solution is obtained through partitioning a flow and cut equivalent tree of 6, which can be efficiently constructed using the Gomory-Hu algorithm. However for larger graphs this approach is impractical. New theorems for subgraph condensation are derived and are then used to develop a fast algorithm which hierarchically constructs and partitions a partially equivalent tree of much reduced size. This algorithm results in an optimal solution equivalent to that obtained by partitioning the complete equivalent tree and is able to handle very large graphs with several hundred thousand vertices. The new clustering algorithm is applied to the image segmentation problem. The segmentation is achieved by effectively searching for closed contours of edge elements (equivalent to minimum cuts in G), which consist mostly of strong edges, while rejecting contours containing isolated strong edges. This method is able to accurately locate region boundaries and at the same time guarantees the formation of closed edge contours. Index Terms-Clustering, edge contours, flow and cut equivalent tree, graph theory, image segmentation, subgraph condensation. D I.

A general technique for the recovery of significant image features is presented. The technique is basedon the mean shift algorithm, a simple nonparametric procedure for estimating density gradients. Drawbacks of the current methods (including robust clustering) are avoided. Featurespace of any naturecan beprocessed, and as an example, color image segmentation is discussed. The segmentation is completely autonomous, only its class is chosen by the user. Thus, the same program can produce a high quality edge image, or provide, by extracting all the significant colors, a preprocessor for content-based query systems. A 512 x 512 color image is analyzed in less than 10 seconds on a standard workstation. Gray level images are handled as color images having only the lightness coordinate.

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 nondestructive testing and document image applications. 2004 SPIE and IS&T. [DOI: 10.1117/1.1631316] 1

Image segmentation is very essential and critical to image processing and pattern recognition. This survey provides a summary of color image segmentation techniques available now. Basically, color segmentation approaches are based on monochrome segmentation approaches operating in di erent color spaces. Therefore, we rst discuss the major segmentation approaches for segmenting monochrome images: histogram thresholding, characteristic feature clustering, edge detection, region-based methods, fuzzy techniques, neural networks, etc. � then review some major color representation methods and their advantages/disadvantages� nally summarize the color image segmentation techniques using di erent color representations. The usage of color models for image segmentation is also discussed. Some novel approaches such as fuzzy method and physics based method are investigated as well.

Image differencing is used for many applications involving change detection. Although it is usually followed by a thresholding operation to isolate regions of change there are few methods available in the literature specific to (and appropriate for) change detection. We describe four different methods for selecting thresholds that work on very different principles. Either the noise or the signal is modelled, and the model covers either the spatial or intensity distribution characteristics. The methods are: 1/ a Normal model is used for the noise intensity distribution, 2/ signal intensities are tested by making local intensity distribution comparisons in the two image frames (i.e. the difference map is not used), 3/ the spatial properties of the noise are modelled by a Poisson distribution, and 4/ the spatial properties of the signal are modelled as a stable number of regions (or stable Euler number).

We propose a new automatic image segmentation method. Color edges in an image are first obtained automatically by combining an improved isotropic edge detector and a fast entropic thresholding technique. After the obtained color edges have provided the major geometric structures in an image, the centroids between these adjacent edge regions are taken as the initial seeds for seeded region growing (SRG). These seeds are then replaced by the centroids of the generated homogeneous image regions by incorporating the required additional pixels step by step. Moreover, the results of color-edge extraction and SRG are integrated to provide homogeneous image regions with accurate and closed boundaries. We also discuss the application of our image segmentation method to automatic face detection. Furthermore, semantic human objects are generated by a seeded region aggregation procedure which takes the detected faces as object seeds.

Abstract. Image segmentation has been, and still is, a relevant research area in Computer Vision, and hundreds of segmentation algorithms have been proposed in the last 30 years. However, it is well known that elemental segmentation techniques based on boundary or region information often fail to produce accurate segmentation results. Hence, in the last few years, there has been a tendency towards algorithms which take advantage of the complementary nature of such information. This paper reviews different segmentation proposals which integrate edge and region information and highlights 7 different strategies and methods to fuse suchinformation. In contrast withother surveys which only describe and compare qualitatively different approaches, this survey deals with a real quantitative comparison. In this sense, key methods have been programmed and their accuracy analyzed and compared using synthetic and real images. A discussion justified with experimental results is given and the code is available on Internet.

We present a methodology for the quantitative performance evaluation of detection algorithms in computer vision. A common method is to generate a variety of input images by varying the image parameters and evaluate the performance of the algorithm as algorithm parameters vary. Operating curves that relate the probability of mis-detection and false alarm are generated for each parameter setting. Such an analysis does not integrate the performance of the numerous operating curves. In this paper we outline a methodology for summarizing many operating curves into a few performance curves. This methodology is adapted from the human psychophysics literature and is general to any detection algorithm. The central concept is to measure the effect of variables in terms of the equivalent effect of a critical signal variable; which in turn facilitates the determination of the breakdown point of the algorithm. We demonstrate the methodology by comparing the performance of two line detection algorit...

This paper describes a modified logical thresholding method for binarization of seriously degraded and very poor quality gray-scale document images. This method can deal with complex signal-dependent noise, variable background intensity caused by nonuniform illumination, shadow, smear or smudge and very low contrast. The output image has no obvious loss of useful information. Firstly, we analyse the clustering and connection characteristics of the character stroke from the run-length histogram for selected image regions and various inhomogeneous gray-scale backgrounds. Then, we propose a modified logical thresholding method to extract the binary image adaptively from the degraded gray-scale document image with complex and inhomogeneous background. It can adjust the size of the local area and logical thresholding level adaptively according to the local run-length histogram and the local gray-scale inhomogeneity. Our method can threshold various poor quality gray-scale document images automatically without need of any prior knowledge of the document image and manual fine-tuning of parameters. It keeps useful information more accurately without overconnected and broken strokes of the characters, and thus, has a wider range of applications compared with other methods.

Otsu reference proposed a criterion for maximizing the between-class variance of pixel intensity to perform picture thresholding. However, Otsu’s method for image segmentation is very time-consuming because of the inefficient formulation of the between-class variance. In this paper, a faster version of Otsu’s method is proposed for improving the efficiency of computation for the optimal thresholds of an image. First, a criterion for maximizing a modified between-class variance that is equivalent to the criterion of maximizing the usual between-class variance is proposed for image segmentation. Next, in accordance with the new criterion, a recursive algorithm is designed to efficiently find the optimal threshold. This procedure yields the same set of thresholds as the original method. In addition, the modified between-class variance can be pre-computed and stored in a look-up table. Our analysis of the new criterion clearly shows that it takes less computation to compute both the cumulative probability (zeroth order moment) and the mean (first order moment) of a class, and that determining the modified between-class variance by accessing a look-up table is quicker than that by performing mathematical arithmetic operations. For example, the experimental results of a five-level threshold selection show that our proposed method can reduce down the processing time from more than one hour by the conventional Otsu’s method to less than 107 seconds. Keywords: Otsu’s thresholding, image segmentation, picture thresholding, multilevel thresholding, recursive algorithm 1.