Showing papers on "Segmentation-based object categorization published in 1994"

Multiresolution color image segmentation

Abstract: Image segmentation is the process by which an original image is partitioned into some homogeneous regions. In this paper, a novel multiresolution color image segmentation (MCIS) algorithm which uses Markov random fields (MRF's) is proposed. The proposed approach is a relaxation process that converges to the MAP (maximum a posteriori) estimate of the segmentation. The quadtree structure is used to implement the multiresolution framework, and the simulated annealing technique is employed to control the splitting and merging of nodes so as to minimize an energy function and therefore, maximize the MAP estimate. The multiresolution scheme enables the use of different dissimilarity measures at different resolution levels. Consequently, the proposed algorithm is noise resistant. Since the global clustering information of the image is required in the proposed approach, the scale space filter (SSF) is employed as the first step. The multiresolution approach is used to refine the segmentation. Experimental results of both the synthesized and real images are very encouraging. In order to evaluate experimental results of both synthesized images and real images quantitatively, a new evaluation criterion is proposed and developed. >

Watershed, Hierarchical Segmentation and Waterfall Algorithm

Abstract: A major drawback when using the watershed transformation as a segmentation tool comes from the over-segmentation of the image. Over-segmentation is produced by the great number of minima embedded in the image or in its gradient. A powerful technique has been designed to suppress over-segmentation by a primary selection of markers pointing out the regions or objects to be segmented in the image. However, this approach can be used only if we are able to compute the marker set before applying the watershed transformation. But, in many cases and especially for complex scenes, this is not possible and an alternative technique must be used to reduce the over-segmentation. This technique is based on mosaic images and on the computation of a watershed transform on a valued graph derived from the mosaic images. This approach leads to a hierarchical segmentation of the image and considerably reduces over-segmentation.

A multiscale algorithm for image segmentation by variational method

Abstract: Most segmentation algorithms are composed of several procedures: split and merge, small region elimination, boundary smoothing,..., each depending on several parameters. The introduction of an energy to minimize leads to a drastic reduction of these parameters. The authors prove that the most simple segmentation tool, the “region merging” algorithm, made according to the simplest energy, is enough to compute a local energy minimum belonging to a compact class and to achieve the job of most of the tools mentioned above. The authors explain why “merging” in a variational framework leads to a fast multiscale, multichannel algorithm, with a pyramidal structure. The obtained algorithm is $O(n\ln n)$, where n is the number of pixels of the picture. This fast algorithm is applied to make grey level and texture segmentation and experimental results are shown.

Hierarchical morphological segmentation for image sequence coding

Abstract: This paper deals with a hierarchical morphological segmentation algorithm for image sequence coding. Mathematical morphology is very attractive for this purpose because it efficiently deals with geometrical features such as size, shape, contrast, or connectivity that can be considered as segmentation-oriented features. The algorithm follows a top-down procedure. It first takes into account the global information and produces a coarse segmentation, that is, with a small number of regions. Then, the segmentation quality is improved by introducing regions corresponding to more local information. The algorithm, considering sequences as being functions on a 3-D space, directly segments 3-D regions. A 3-D approach is used to get a segmentation that is stable in time and to directly solve the region correspondence problem. Each segmentation stage relies on four basic steps: simplification, marker extraction, decision, and quality estimation. The simplification removes information from the sequence to make it easier to segment. Morphological filters based on partial reconstruction are proven to be very efficient for this purpose, especially in the case of sequences. The marker extraction identifies the presence of homogeneous 3-D regions. It is based on constrained flat region labeling and morphological contrast extraction. The goal of the decision is to precisely locate the contours of regions detected by the marker extraction. This decision is performed by a modified watershed algorithm. Finally, the quality estimation concentrates on the coding residue, all the information about the 3-D regions that have not been properly segmented and therefore coded. The procedure allows the introduction of the texture and contour coding schemes within the segmentation algorithm. The coding residue is transmitted to the next segmentation stage to improve the segmentation and coding quality. Finally, segmentation and coding examples are presented to show the validity and interest of the coding approach. >

Quad-tree segmentation for texture-based image query

Abstract: In this paper we propose a technique for segmenting images by texture content with application to indexing images in a large image database Using quad-tree decomposition, texture features are extracted from spatial blocks at a hierarchy of scales in each image The quad-tree is grown by iteratively testing conditions for splitting parent blocks based on texture content of children blocks While this approach does not achieve smooth identification of texture region borders, homogeneous blocks of texture are extracted which can be used in a database index Furthermore, this technique performs the segmentation directly using image spatial-frequency data In the segmentation reported here, texture features are extracted from the wavelet representation of the image This method however, can use other subband decompositions including Discrete Cosine Transform (DCT), which has been adopted by the JPEG standard for image coding This makes our segmentation method extremely applicable to databases containing compressed image data We show application of the texture segmentation towards providing a new method for searching for images in large image databases using “Query-by-texture”

Spatio-Temporal Segmentation of Video Data

Abstract: Image segmentation provides a powerful semantic description of video imagery essential in image understanding and efficient manipulation of image data. In particular, segmentation based on image motion defines regions undergoing similar motion allowing image coding system to more efficiently represent video sequences. This paper describes a general iterative framework for segmentation of video data . The objective of our spatiotemporal segmentation is to produce a layered image representation of the video for image coding applications whereby video data is simply described as a set of moving layers.

Texture-based segmentation of road images

Abstract: The extraction of road boundaries is one of the basic requirements for an autonomous navigation system to guide a vehicle on a road. The existent road detection approaches have some difficulties with the roads that have neither marked lanes nor different colors between their surface and the environment. Instead of gray value or color, texture can be an important feature in such images. Taking this as motivation, the authors developed a texture-based road segmentation approach. The textures in road images are usually strongly anisotropic with a dominant orientation. Such oriented textures can be described by their orientation field that consists of orientation and strength of texture anisotropy. The authors describe a new approach for estimating the orientation field of oriented textures based on the covariance matrix of the grey value changes in an image. As an image feature, the strength of texture anisotropy is then used in the unsupervised road segmentation in the initial phase as well as in the supervised road segmentation in subsequent phases. The authors' algorithm has been tested with real road image sequences.

Digital Image Processing Methods

Abstract: Nonlinear filters morphological segmentation for textures and particles multispectral image segmentation in magnetic resonance imaging thinning and skeletonizing syntactic image pattern recognition heuristic parallel approach for 3D articulated line-drawing object pattern representation and recognition handwritten character recognition digital image compression image-processing architectures digital halftoning.

Genetic learning for adaptive image segmentation

Abstract: From the Publisher: Genetic Learning for Adaptive Image Segmentation presents the first closed-loop image segmentation system that incorporates genetic and other algorithms to adapt the segmentation process to changes in image characteristics caused by variable environmental conditions, such as time of day, time of year, weather, etc. Image segmentation performance is evaluated using multiple measures of segmentation quality. These quality measures include global characteristics of the entire image as well as local features of individual object regions in the image. The goals of this adaptive image segmentation system are to provide continuous adaptation to normal environmental variations, to exhibit learning capabilities, and to provide robust performance when interacting with a dynamic environment. This research is directed towards adapting the performance of a well known existing segmentation algorithm (Phoenix) across a wide variety of environmental conditions which cause changes in the image characteristics. Genetic Learning for Adaptive Image Segmentation presents a large number of experimental results and compares performance with standard techniques used in computer vision for both consistency and quality of segmentation results. These results demonstrate, (a) the ability to adapt the segmentation performance in both indoor and outdoor color imagery, and (b) that learning from experience can be used to improve the segmentation performance over time.

Adaptive Bayesian segmentation of color images

Abstract: An adaptive Bayesian segmentation algorithm for color images is presented, which extends the adaptive clustering approach of Pappas to multichannel images. A scalar segmentation label field is generated for the multichannel data, which is modeled as a vector field, where the components of the vector field (each individual channel) are assumed to be conditionally independent given the segmentation labels. The class conditional probability model for the vector image field is taken as a multivariate Gaussian with a space-varying mean function. A Gibbs random field is employed as the a priori probability model for the segmentation label field that imposes a spatial connectivity constraint on the labels. The space-varying class means associated with the image segments can be used to form an estimate of the actual image from noisy observations. Experimental results are provided to demonstrate the benefits of using adaptivity via the space-varying means and the spatial connectivity constraint. We also discuss the effects of the color space within which the clustering is performed on resulting segmentations.

A fast algorithm for MDL-based multi-band image segmentation

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 shown. >

Color image segmentation by a watershed algorithm and region adjacency graph processing

Abstract: A new method for gray-scale, color and multispectral image segmentation is proposed. The method is based on a morphological split-and-merge fast watershed algorithm and region adjacency graph processing. It features partly iterative processing with relatively low computational load. Two system alternatives are presented and their application to color image segmentation is discussed. First computer simulations show correctness of operation and encourage for further research. >

MUM (Merge Using Moments) segmentation for SAR images

Abstract: In Synthetic Aperture Radar (SAR) and other systems employing coherent illumination to form high-resolution images, the resulting image is generally corrupted by a form of multiplicative noise, known as coherent speckle, with a signal-to-noise ration of unity. This severe form of noise presents singular problems for image processing software of all kinds. This paper describes a segmentation scheme, Merge Using Moments (MUM), for image corrupted by coherent speckle. The image is initially massively over-segmented. A scheme based on examination of the statistical properties (moments) of adjoining regions is employed to improve an over-fine segmentation by merging regions to produce a coarser segmentation. This scheme is employed iteratively until no remaining merge appears valid, at which time a good segmentation is obtained. Segmentation using μm on SAR imagery are given and the results compared to other segmentation schemes. The results of using it on typical SAR images illustrate its potential.

Anisotropic diffusion pyramids for image segmentation

Abstract: We introduce the Anisotropic Diffusion Pyramid (ADP), a structure for multiresolution image processing. We also develop the ADP for use in region-based segmentation. The pyramid is constructed using the anisotropic diffusion equations, creating an efficient scale-space representation. Segmentation is accomplished using pyramid node linking. Since anisotropic diffusion preserves edge localization as the scale is increased, the region boundaries in the coarse-to-fine ADP segmentation are accurately delineated. An application to segmentation of remotely sensed data is provided. The results of ADP segmentation are compared to Gaussian-based pyramidal segmentation. The examples show that the ADP has a superior ability to subdivide the image into integral groupings, minimizing the error in boundary localization and in pixel intensity. >

An algorithm for simultaneous motion estimation and scene segmentation

Abstract: We present an algorithm that simultaneously performs motion estimation and scene segmentation in image sequences. This algorithm improves upon the traditional approach of using the motion estimates that are obtained separately as input for scene segmentation. Based on the maximum a posteriori probability (MAP) criterion, the interdependence of constraints for motion estimation and scene segmentation are expressed in a Gibbs distribution. The solution is obtained based on the highest confidence first (HCF) and iterated conditional mode (ICM) optimization methods. Experimental results suggest that this algorithm is of potential use for low-bit rate video coding. >

A combined Markov random field and wave-packet transform-based approach for image segmentation

Abstract: The author formulates a novel segmentation algorithm which combines the use of Markov random field models for image-modeling with the use of the discrete wavepacket transform for image analysis. Image segmentations are derived and refined at a sequence of resolution levels, using as data selected wave-packet transform images or "channels". The segmentation algorithm is compared with nonmultiresolution Markov random field-based image segmentation algorithms in the context of synthetic image example problems, and found to be both significantly more efficient and effective. >

Textured image segmentation by context enhanced clustering

Abstract: An unsupervised textured image segmentation technique based on multidimensional feature vector clustering is described, where the features are the parameters of an autoregressive model, The benefits of incorporating spatial contextual information are demonstrated on both true cluster number estimation and actual image segmentation. A simple within-cluster distance is used for cluster validity analysis, where feature vectors are modified through local spatial dependency. This greatly reduces the dispersion in the raw feature data fed to the clustering process, and improves the true cluster number estimation. At the segmentation stage, three schemes incorporating contextual information at feature vector and label levels are proposed to enhance the segmentation accuracy. One is a development of a technique due to Mardia and Hainsworth (1988). The proposed approaches are tested on a four-class textured image.

Initializing snakes [object delineation]

Abstract: We propose a snake-based approach that lets a user specify only the distant end points of the curve he wishes to delineate without having to supply an almost complete polygonal approximation. We achieve much better convergence properties than those of traditional snakes by using the image information around these end points to provide boundary conditions and by introducing an optimization schedule that allows the snake to take image information into account first only near its extremities and then, progressively, towards its center. These snakes could be used to alleviate the often repetitive task practitioners have to face when segmenting images by abolishing the need to sketch a feature of interest in its entirety, that is, to perform a painstaking, almost complete, manual segmentation. >

Color image segmentation using fuzzy clustering and supervised learning

Abstract: We propose a technique for the segmentation of color map images by means of an algorithm based on fuzzy clustering and prototype optimization. Its purpose is to facilitate the extraction of lines and characters from a wide variety of geographical map images. In this method, segmentation is considered to be a process of pixel classification. The fuzzy c-means clustering algorithm is applied to a number of training areas taken from a selection of different color map images. Prototypes, generated from the clustered pixels, that satisfy a set of validation criteria are then optimized using a neural network with supervised learning. The image is segmented using the optimized prototypes according to the nearest neighbor rule. The method has been verified to work efficiently with real geographical map data.

A region-region and region-edge cooperative approach of image segmentation

Abstract: In the task of segmentation of some complex pictures, it is often difficult to obtain satisfactory results using only one approach of image segmentation. The tendency toward the integration of several techniques seems to be the best solution. The authors introduce a new approach of image segmentation, which tends to combine several sources of knowledge about the image in a way to produce better segmentation results. First, they try to locate germs that are homogenous by means of a region-region cooperative process. A region growing process is then applied to these germs in order to find the region borders. This process is controlled, on the one hand, by the germs' parameters, and on the other hand by a gradient information obtained by a simple edge detector. Finally, a region merging step is applied on the extracted regions in order to reconstruct regions that have been split by the germs' extraction process. This method has given good segmentation results over several complex natural images. >

Image segmentation device

Abstract: Images having a moving pattern against a fixed or quasi-fixed background are segmented by determining a silhouette of the moving pattern, and forming a segmentation image filling the silhouette. On a pixel-by-pixel basis, differences are determined between the current image and previous images of a sequence, and compared with a threshold to form a binary image of background and useful zone. The boundaries of the useful zone are regularized, and irregularities in the useful zone and in the background are suppressed. A segmentation image is then formed within the silhouette.

Page segmentation using decision integration and wavelet packets

Abstract: A new algorithm for layout-independent document page segmentation is suggested. Text, image and graphics regions in a document image are treated as three different "texture" classes. Soft local decisions on small blocks are made using wavelet packet based feature vectors. Segmentation is performed by propagating and integrating soft local decisions over neighboring blocks, within and across scales. The "uncertainties" associated with local decisions are reduced as more contextual evidence is incorporated in the process of decision integration. The majority, taken over weighted combined votes, determines the final decision. The suggested algorithm is based on parallel independent computations which have low complexity. It can also be applied to other signal and image segmentation tasks.

Benchmarking page segmentation algorithms

Abstract: A method for automatically evaluating the quality of document page segmentation algorithms is introduced. Many different zoning techniques are now available but there is no robust method available to benchmark and evaluate them reliably. Our proposed strategy is a region-based approach, in which segmentation results are compared with manually generated "ground truth files", describing all possible correct segmentations. A segmentation ground truthing scheme has been proposed. The evaluation of segmentation quality is achieved by testing the overlap between the two sets of regions. In fact, the regions are defined as the "black" pixels contained in the extracted polygons. An explicit specification of segmentation errors and a numerical evaluation are derived. The algorithm is simple and fast, and provides a multi-level output for each segmentation. >

A fuzzy logic approach to image segmentation

Abstract: A novel image segmentation algorithm derived in a fuzzy entropy framework is presented. First, the fuzzy entropy function is computed based on fuzzy region width and the Shannon's function of the image. Then all of the local entropy maxima are located in order to find the optimal partition for image segmentation scene local entropy maxima corresponding to the uncertainties among various regions in the image. This algorithm is very effective for the images whose histograms have no clear peaks and valleys, or the number of the segmentation classes is unknown, or the probabilistic model of the image and the different segmentation classes are unknown. A large number of experiments have been carried out on different kinds of images. Good performances of the proposed algorithm have been achieved.

Segmentation of medical images using an active contour model incorporating region-based image features

Abstract: An improved segmentation algorithm based on the active contour model is developed. A distinguishing element of our algorithm is the incorporation of region-based image features which improves signifcantly the reliability of the algorithm, and allows multi- region segmentation of an image. We use simulated annealing in the energy minimization in order to locate the globally optimal solution and enhance flexibility in the construction of energy functional.© (1994) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.