Showing papers on "Range segmentation published in 2000"

Object localization and border detection criteria design in edge-based image segmentation: automated learning from examples

Abstract: This paper provides methodology for fully automated model-based image segmentation. All information necessary to perform image segmentation is automatically derived from a training set that is presented in a form of segmentation examples. The training set is used to construct two models representing the objects-shape model and border appearance model. A two-step approach to image segmentation is reported. In the first step, an approximate location of the object of interest is determined. In the second step, accurate border segmentation is performed. The shape-variant Hough transform method was developed that provides robust object localization automatically. It finds objects of arbitrary shape, rotation, or scaling and can handle object variability. The border appearance model was developed to automatically design cost functions that can be used in the segmentation criteria of edge-based segmentation methods. The authors' method was tested in five different segmentation tasks that included 489 objects to be segmented. The final segmentation was compared to manually defined borders with good results [rms errors in pixels: 1.2 (cerebellum), 1.1 (corpus callosum), 1.5 (vertebrae), 1.4 (epicardial), and 1.6 (endocardial) borders]. Two major problems of the state-of-the-art edge-based image segmentation algorithms were addressed: strong dependency on a close-to-target initialization, and necessity for manual redesign of segmentation criteria whenever new segmentation problem is encountered.

A multiresolution image segmentation technique based on pyramidal segmentation and fuzzy clustering

Abstract: In this paper, an unsupervised image segmentation technique is presented, which combines pyramidal image segmentation with the fuzzy c-means clustering algorithm. Each layer of the pyramid is split into a number of regions by a root labeling technique, and then fuzzy c-means is used to merge the regions of the layer with the highest image resolution. A cluster validity functional is used to find the optimal number of objects automatically. Segmentation of a number of synthetic as well as clinical images is illustrated and two fully automatic segmentation approaches are evaluated, which determine the left ventricular volume (LV) in 140 cardiovascular magnetic resonance (MR) images. First fuzzy c-means is applied without pyramids. In the second approach the regions generated by pyramidal segmentation are merged by fuzzy c-means. The correlation coefficients of manually and automatically defined LV lumen of all 140 and 20 end-diastolic images were equal to 0.86 and 0.79, respectively, when images were segmented with fuzzy c-means alone. These coefficients increased to 0.90 and 0.93 when the pyramidal segmentation was combined with fuzzy c-means. This method can be applied to any dimensional representation and at any resolution level of an image series. The evaluation study shows good performance in detecting LV lumen in MR images.

Method of and apparatus for segmenting a pixellated image

Abstract: This invention relates to a method for segmenting a pixellated image, comprising: (a) selecting at least one first region from a first reference image; (b) deriving from values of pixels of the at least one first region a first threshold such that a first predetermined proportion of the pixels have values on a first side of the first threshold; (c) forming a difference image as a difference between each pixel of the image and a corresponding pixel of an image of a non-occluded background; and (d) allocating each difference image pixel to at least one first type of region if the value of the difference image pixel is on the first side of the first threshold and the values of more than a first predetermined number of neighboring difference image pixels are on the first side of the first threshold. An apparatus for performing the foregoing method is disclosed.

Hierarchical color image region segmentation for content-based image retrieval system

Abstract: In this work, we propose a model of a content-based image retrieval system by using the new idea of combining a color segmentation with relationship trees and a corresponding tree-matching method. We retain the hierarchical relationship of the regions in an image during segmentation. Using the information of the relationships and features of the regions, we can represent the desired objects in images more accurately. In retrieval, we compare not only region features but also region relationships.

Method and apparatus for segmenting an image using a combination of image segmentation techniques

Abstract: This invention relates to a method and apparatus for segmenting an image using a combination of image segmentation techniques. More particularly, the invention is directed to an improved image segmentation technique for use in an image processing system that performs at least two distinct image segmentation processes on an image and combines the results to obtain a combined multi-layer representation of the image that can be suitably processed. In a specific example, a block based segmentation technique is performed on an image to generate a MRC (mixed raster content) representation—having foreground, background and selector layers. A pixel based segmentation technique is also performed on the image to generate rendering hints. The MRC representation and the rendering hints are then combined to obtain a four (4) layer representation of the image. The four layer representation is subsequently processed as required by the image processing system, e.g. compressed and stored.

Morphological segmentation of histology cell images

Abstract: Two algorithms for segmentation of cell images are proposed. They have a unique part that contains computation of morphological gradient to extract object borders and thinning the obtained borders to get a line of one-pixel thickness. For this task, we propose the fast gray-scale thinning algorithm that is based on the idea of the analysis of binary image layers. Then, the obtained one-pixel lines are used to extract cells and compute their characteristics. The algorithms based on morphological and split/merge segmentation are developed and used for this task.

Color Image Segmentation for Multimedia Applications

Abstract: Image segmentation is crucial for multimedia applications. Multimedia databases utilize segmentation for the storage and indexing of images and video. Image segmentation is used for object tracking in the new MPEG-7 video compression standard. It is also used in video conferencing for compression and coding purposes. These are only some of the multimedia applications in image segmentation. It is usually the first task of any image analysis process, and thus, subsequent tasks rely heavily on the quality of segmentation. The proposed method of color image segmentation is very effective in segmenting a multimedia-type image into regions. Pixels are first classified as either chromatic or achromatic depending on their HSI color values. Next, a seed determination algorithm finds seed pixels that are in the center of regions. These seed pixels are used in the region growing step to grow regions by comparing these seed pixels to neighboring pixels using the cylindrical distance metric. Merging regions that are similar in color is a final means used for segmenting the image into even smaller regions.

An adaptive contour closure algorithm and its experimental evaluation

Abstract: The potential of edge-based complete image segmentation into regions has not gained the due attention in the literature thus far. The present paper attempts to explore this potential by proposing an adaptive grouping algorithm to solve the contour closure problem that is the key to a successful edge-based complete image segmentation. The effectiveness of the proposed algorithm is extensively tested in the range image domain and compared to several region-based segmentation methods within a rigorous comparison framework. On three range image databases of varying quality acquired by different range scanners, it is shown that the proposed approach is able to achieve very appealing performance with respect to both segmentation quality and computation time.

ROI segmentation image processing system

Abstract: An improved ROI segmentation image processing system substantially masks non-ROI image data from a digital image to produce a ROI segmented image for subsequent digital processing. The ROI segmentation image processing system is a computer-based system having a collimation subsystem configured to detect and mask out collimated regions within the image. Furthermore, a direct exposure (DE) subsystem is configured to detect and remove DE regions from the image. Holes generated in the image are filled-in to provide a resulting image with only ROI.

Morphological segmentation of sport scenes using color information

Abstract: We propose a new method for segmenting image sequences in sports scenes containing brisk movement. An important feature of this method is the computation of color histograms in the areas for the turf, which is done interactively during rehearsal. Another important feature is automatic morphological segmentation during broadcast. The morphological segmentation consists of two operations: coarse segmentation by binary reconstruction based on the areas detected by thresholding the color histogram, and fine segmentation by watershed transformation with markers. It is shown that this new method achieves accurate segmentation in sport scenes.

Efficient image segmentation for region-based motion estimation and compensation

Abstract: An intra-frame segmentation strategy to assist region-based motion estimation and compensation is presented. It is based on the multiresolution application of a histogram clustering and a probabilistic relaxation-labeling algorithm, followed by a local gradient-based bottom-up merging procedure. Specially suited for region-based video coding, it strongly differs from other proposals in that it generates arbitrary shaped image regions with pixel accuracy at a low computational cost, while allowing full reconstruction of the segmentation at the decoder without the transmission of any region description information.

AM-FM image segmentation

Abstract: We introduce a new modulation domain texture segmentation algorithm. The approach begins by constructing a dominant component AM-FM image model, where the dominant amplitude and frequency modulations are used as segmentation features. Statistical clustering is applied in this feature space to compute an initial segmentation which is then refined by morphological filtering and connected components labeling. The algorithm, which consistently delivers correct pixel classification rates exceeding 94%, is only partially unsupervised at present since the desired number of regions must be known a priori. Our future work is focused on developing strategies to make the approach fully unsupervised.

Region-based image retrieval system using efficient feature description

Abstract: In this paper we introduce a region-based image retrieval system, FRIP. This system includes a robust image segmentation scheme using scaled and shifted color and shape description scheme using modified radius-based signature. For image segmentation, by using our proposed circular filter, we can keep the boundary of object naturally and merge small senseless regions of object into a whole body. For efficient shape description, we extract 5 features from each region: color, texture, scale, location, and shape. From these features, we calculate the similarity distance between the query and database regions and it returns the top K-nearest neighbor regions.

Color image segmentation by supervised pixel classification in a color texture feature space. Application to soccer image segmentation

Abstract: We describe an approach to color image segmentation which is considered as a supervised pixel classification problem. The pixel classification algorithm analyses the color texture features, that is to say the texture features which are computed by tacking into account the color components of the neighbor pixels. We determine the most discriminating color texture features among a multidimensional set of color texture features by means of an iterative feature selection procedure associated to an information criterion. We successfully apply our approach to soccer image segmentation.

A novel approach to depth ordering in monocular image sequences

Abstract: Object oriented representation of image sequences requires accurate motion segmentation and depth ordering techniques. Unfortunately, the lack of precise motion estimates at the object boundaries makes these two tasks very difficult. We present a detailed analysis of the behaviour of dense motion estimation techniques at object boundaries which reveals the systematic nature of the motion estimation error; the motion of the occluding surface is observed in a small neighbourhood on the occluded side. We then show how the joint use of still image segmentation and robust regression can eliminate this error. Furthermore we present a novel technique which uses the position of the error as a depth cue. The validity of this technique, which requires only sub-pixel motion and which is capable of distinguishing between different types of intensity discontinuities, such as object boundaries, surface marks and illumination discontinuities, is then demonstrated on several synthetic and real image sequences.

Image segmentation via multiple active contour models and fuzzy clustering with biomedical applications

Abstract: We address the problem of automatically segmenting cell nuclei or cluster of cell nuclei in image medical microscopy. We present a system of automatic segmentation combining fuzzy clustering and multiple active contour models. An automatic initialization algorithm based on fuzzy clustering is used to robustly identify and classify all possible seed regions in the image. These seeds are propagated outward simultaneously to localize the final contours of all objects. We present examples of quantitative segmentation on biomedical images: segmentation of lobules in color images of histology and segmentation of nuclei in cytological images.

Estimation of homogeneous regions for segmentation of textured images

Abstract: In this paper a novel method for the unsupervised segmentation of textured images is presented. Textures are modeled as spatial interactions between pixels. Thus, a certain window size is required to extract texture features and to estimate texture boundaries by using the features. As long as the size of the window is fixed over the whole of an image, we cannot accurately estimates texture regions that have similar properties. In this paper the problem of selection of an appropriate size for window used to estimate homogeneous texture regions is investigated via hypothesis and testing. Experiments on segmentation of textures in synthetic and natural images show the effectiveness of the method.

Color image segmentation method

Abstract: A color image segmentation method is provided The color image segmentation method includes the steps of: (a) calculating a first value representing the degree of difference between a pixel and the color of peripheral pixels based a plurality of pixel values of an input image; (b) obtaining a converted image by converting the first calculated value into a value of a predetermined scale; and (c) segmenting the converted image According to the color image segmentation method, an effective and an automatic segmentation is possible, and a segmentation speed is high even when segmenting an image containing much noise

Object segmentation for Z-keying using stereo images

Abstract: We propose a robust object segmentation framework exploiting multiple cues such as shape, intensity (color) and depth. Though over last few decades, various segmentation, schemes have been developed, those schemes based on intensity and motion information have well-known disadvantages. To alleviate those problems we take into account depth information using MRF/GRF framework. The experimental results show the effectiveness of the proposed framework by clearly separating "objects of interest" from real, rather than blue-screen, scenes. The proposed scheme will be a key part for wide scope of applications requiring object-based functionalities as well as Z-keying for photo-realistic mixed reality.

Image segmenting apparatus and method

Abstract: An image segmenting apparatus and method is provided. The image segmenting apparatus includes an initial image segmenting unit, a region structurizing unit and a redundant region combiner. The initial image segmenting unit converts color signals of an input image into a color space which is based on predetermined signals, and segments the input image into a plurality of regions according to positions of color pixels of the input image in the color space. The region structurizing unit classifies the plurality of regions into layers according to horizontal, adjacent relation and hierarchical, inclusive relation between the regions, and groups adjacent regions into region groups in each layer, so as to derive a hierarchical, inclusive relation between the region groups. The redundant region combiner determines the order in which adjacent regions are combined according to the horizontal, adjacent relation between regions and the hierarchical, inclusive relation between region groups. The redundant region combiner also determines whether to combine adjacent regions according to the determined combination order, and combines adjacent regions if the adjacent regions are determined to be substantially the same. Even if regions appears to be adjacent each other in a region adjacent graph (RAG), a structural inclusive relation between regions can be derived by excluding the combination of the regions or rearranging their combination order according to a hierarchical structure. Subsequently, the mutual relation between two regions can be inferred from the inclusive relation even if the color signals of the two regions, for example, a region in a highlighted area and a region in its surrounding area, are not similar to each other.

Rough and accurate segmentation of natural color images using fuzzy region-growing algorithm

Abstract: We present a rough and an accurate segmentation of natural color images using a fuzzy region-growing algorithm. In the proposed method, the color difference and the color gradient are used as the pixel features to produce an accurate segmentation, while the local fractal dimension is used as the region feature to yield a rough segmentation in a natural color image. The effectiveness of the proposed method is confirmed through computer simulations that demonstrate a rough segmentation at the fine-texture regions and an accurate segmentation at the strong-edge regions simultaneously.

Document image segmentation using loose gray scale template matching

Abstract: A Document Image Segmentation method is disclosed for matching a plurality of templates with a received image wherein the received image being bitmap data including at least a plurality of gray-scale pixel tiles that define the received image, the matching method having the steps of first receiving said image data so as to extract pixel tile information of said received image wherein said pixel tile information being of a predetermined matrix size; then matching loosely said pixel tile information with at least one of a plurality of templates so as to generate pixel-wise looseness interval values there between; and finally outputting an identifier associated with the matching template such that said identifier indicates a classification. The classification is preferably based on at least one of continuous tone pictorials, text, half tones, high/low frequency range; and line art graphic. Also, preferably the classification contains information about the image source.

Optimal range segmentation parameters through genetic algorithms

Abstract: A wide number of algorithms for surface segmentation in range images have been recently proposed characterized by different approaches (edge filling, region growing,...), different surface types (either for planar or curved surfaces) and different parameters involved. Optimization of the parameter set is a particularly critical task since the range of parameter variability is often quite large: parameter selection depends on surface type, sensors and the required speed which strongly of affect performance. A framework for parameter optimization is proposed based on genetic algorithms. Such algorithms allow a general approach that has been successfully applied on different state-of-the-art segmenters and different range image databases.

Improving image segmentation using edge information

Abstract: We report methods for image segmentation that combine region growing and edge detection. Existing schemes that use region-based processing provide unambiguous segmentation, but they often divide regions that are not clearly separated, while merging regions across a break in an otherwise strong edge. Edge-based schemes are subject to noise and global variation in the picture (e.g. illumination), but do reliably identify strong boundaries. Our combined algorithm begins by using region growing to produce an over-segmented image. This phase is fast (order N, where N is the number of pels in the image). We then modify the over-segmented output of the region growing using edge criteria such as edge strength, edge smoothness, edge straightness and edge continuity. Two techniques-line-segment subtraction and line-segment addition-have been investigated. In the subtraction technique, the weakest edge (based on a weighted combination of the criteria) is removed at each step. In addition technique, the strongest edge is used to seed a multi-segment line that grows out from it at both ends. At every junction, the adjoining edge that has the highest edge strength is appended. We have also investigated a form of look-ahead, where the growing of lines depends on the strength of the adjoining edge and those to which it is linked. The overall procedure for both techniques, current results and the areas for improvement and expansion have been discussed.

Efficient unsupervised content-based segmentation in stereoscopic video sequences

Abstract: This paper presents an efficient technique for unsupervised content-based segmentation in stereoscopic video sequences by appropriately combined different content descriptors in a hierarchical framework. Three main modules are involved in the proposed scheme; extraction of reliable depth information, image partition into color and depth regions and a constrained fusion algorithm of color segments using information derived from the depth map. In the first module, each stereo pair is analyzed and the disparity field and depth map are estimated. Occlusion detection and compensation are also applied for improving the depth map estimation. In the following phase, color and depth regions are created using a novel complexity-reducing multiresolution implementation of the Recursive Shortest Spanning Tree algorithm (M-RSST). While depth segments provide a coarse representation of the image content, color regions describe very accurately object boundaries. For this reason, in the final phase, a new segmentation fusion algorithm is employed which projects color segments onto depth segments. Experimental results are presented which exhibit the efficiency of the proposed scheme as content-based descriptor, even in case of images with complicated visual content.

Image segmentation combining region depth and object features

Abstract: Object recognition systems need image segmentation processes that relate image regions to world objects. These methods present often three problems: the generation of a large number of small regions, undersegmentation (different objects are associated to the same image region) and oversegmentation (a scene object is segmented in various regions). In order to overcome these problems, we propose an image segmentation method that combines depth information and object surface properties obtained from a pair of stereo images. The system work under the standard assumption that 3D objects have planar faces and regular shapes. First a region growing segmentation process is applied to both images generating two labeled images. Then, depth information of the region frontiers is obtained by matching the labeled segments from left and right image rows. The stereo matching problem is solved by finding a path through a 2D search plane whose axes are the left and right segmented lines. Original image regions are then merged based on their size, surface information and frontiers depth information. In this way, image regions are associated to surfaces that are contiguous in the 3D space and they present a common property (such as gray level, color or texture).

Document classification using segmentation tag statistics

Abstract: A first aspect of the of the present invention is a system and method for classifying an input document based a segmentation tag statistics. The method includes receiving first pass segmentation tags for a plurality of pixels within a block of image data; determining an image type for the block of image data using statistics compiled from the first pass segmentation tags; and generating rendering tags for pixels within the block of image data as function of second pass segmentation tags and the image type. Beneficially, the image type identified for the block of image data is used to optimize the rendering process.