Showing papers on "Range segmentation published in 2001"

Unsupervised segmentation of color-texture regions in images and video

Abstract: A method for unsupervised segmentation of color-texture regions in images and video is presented. This method, which we refer to as JSEG, consists of two independent steps: color quantization and spatial segmentation. In the first step, colors in the image are quantized to several representative classes that can be used to differentiate regions in the image. The image pixels are then replaced by their corresponding color class labels, thus forming a class-map of the image. The focus of this work is on spatial segmentation, where a criterion for "good" segmentation using the class-map is proposed. Applying the criterion to local windows in the class-map results in the "J-image," in which high and low values correspond to possible boundaries and interiors of color-texture regions. A region growing method is then used to segment the image based on the multiscale J-images. A similar approach is applied to video sequences. An additional region tracking scheme is embedded into the region growing process to achieve consistent segmentation and tracking results, even for scenes with nonrigid object motion. Experiments show the robustness of the JSEG algorithm on real images and video.

Automatic image segmentation by integrating color-edge extraction and seeded region growing

Abstract: 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.

Probabilistic framework for segmenting people under occlusion

Abstract: In this paper we address the problem of segmenting foreground regions corresponding to a group of people given models of their appearance that were initialized before occlusion. We present a general framework that uses maximum likelihood estimation to estimate the best arrangement for people in terms of 2D translation that yields a segmentation for the foreground region. Given the segmentation result we conduct occlusion reasoning to recover relative depth information and we show how to utilize this depth information in the same segmentation framework. We also present a more practical solution for the segmentation problem that is online to avoid searching an exponential space of hypothesis. The person model is based on segmenting the body into regions in order to spatially localize the color-features corresponding to the way people are dressed. Modeling these regions involves modeling their appearance (color distributions) as well us their spatial distribution with respect to the body. We use a non-parametric approach bused on kernel density estimation to represent the color distribution of each region and therefore we do not restrict the clothing to be of uniform color instead it can be any mixture of colors and/or patterns. We also present a method to automatically initialize these models and learn them before the occlusion.

Object based segmentation of video using color, motion and spatial information

Abstract: Video segmentation is different from segmentation of a single image. While several correct solutions may exist for segmenting a single image, there needs to be a consistency among segmentations of each frame for video segmentation. Previous approaches of video segmentation concentrate on motion, or combine motion and color information in a batch fashion. We propose a maximum a posteriori probability (MAP) framework that uses multiple cues, like spatial location, color and motion, for segmentation. We assign weights to color and motion terms, which are adjusted at every pixel, based on a confidence measure of each feature. We also discuss the appropriate modeling of PDFs of each feature of a region. The correct modeling of the spatial PDF imposes temporal consistency among segments in consecutive frames. This approach unifies the strengths of both color segmentation and motion segmentation in one framework, and shows good results on videos that are not suited for either of these approaches.

Segmentation and boundary detection using multiscale intensity measurements

Abstract: Image segmentation is difficult because objects may differ from their background by any of a variety of properties that can be observed in some, but often not all scales. A further complication is that coarse measurements, applied to the image for detecting these properties, often average over properties of neighboring segments, making it difficult to separate the segments and to reliably detect their boundaries. Below we present a method for segmentation that generates and combines multiscale measurements of intensity contrast, texture differences, and boundary integrity. The method is based on our former algorithm SWA, which efficiently detects segments that optimize a normalized-cut like measure by recursively coarsening a graph reflecting similarities between intensities of neighboring pixels. In this process aggregates of pixels of increasing size are gradually collected to form segments. We intervene in this process by computing properties of the aggregates and modifying the graph to reflect these coarse scale measurements. This allows us to detect regions that differ by fine as well as coarse properties, and to accurately locate their boundaries. Furthermore, by combining intensity differences with measures of boundary integrity across neighboring aggregates we can detect regions separated by weak, yet consistent edges.

for Optimal Boundary & Region Segmentation of Objects in N-D Images

Abstract: In this paper we describe a new technique for general purpose interactive segmentation of N-dimensional images. The user marks certain pixels as “object” or “background” to provide hard constraints for segmentation. Additional soji constraints incorporate both boundary and region information. Graph cuts are used to find the globally optimal segmentation of the N-dimensional image. The obtained solution gives the best balance of boundary and region properties among all segmentations satishing the constraints. The topology o$our segmentation is unrestricted and both “object” and “background” segments may consist of several isolatedparts. Some experimental results are presented in the context ofphotohideo editing and medical image segmentation. We also demonstrate an interesting Gestalt example. A fast implementation of our segmentation method is possible via a new mar-$ow algorithm in [2].

Dynamic depth recovery from multiple synchronized video streams

Abstract: This paper addresses the problem of extracting depth information of non-rigid dynamic 3D scenes from multiple synchronized video streams. Three main issues are discussed in this context. (i) temporally consistent depth estimation, (ii) sharp depth discontinuity estimation around object boundaries, and (iii) enforcement of the global visibility constraint. We present a framework in which the scene is modeled as a collection of 3D piecewise planar surface patches induced by color based image segmentation. This representation is continuously estimated using an incremental formulation in which the 3D geometric, motion, and global visibility constraints are enforced over space and time. The proposed algorithm optimizes a cost function that incorporates the spatial color consistency constraint and a smooth scene motion model.

Image background replacement method

Abstract: An image's pixels are initially segmented into pixels of the image foreground and background by comparing the pixels of the image to updated models of background reference pixels. Pixel structures are identified in the image. The probability that a pixel is in the background or foreground is refined by considering the initial segmentation of the pixel's neighbors and the pixel's membership in a pixel structure. If a pixel is identified as a background pixel it is replaced by a pixel of a new background.

An unsupervised color image segmentation algorithm for face detection applications

Abstract: This paper presents an unsupervised color segmentation technique to divide skin detected pixels into a set of homogeneous regions which can be used in face detection applications or any other application which may require color segmentation. The algorithm is carried out in a two stage processing, where the chrominance and luminance information are used consecutively. For each stage a novel algorithm which combines pixel and region based color segmentation techniques is used. The algorithm has proven to be effective under a large number of test images.

Image processing method and apparatus, recording medium, and imaging apparatus

Abstract: For the purpose of providing an image processing method for determining the variance of noise in an image, a residual sum of squares of pixel values is determined for each of a plurality of local regions defined over the entire image (502 - 508); a histogram thereof is obtained (510); and the variance of noise is determined based on the value of the residual sum of squares that gives a peak of the histogram (512, 514)

Image processing apparatus and method, program, and recording medium

Abstract: Image refreshers enhance edge portions of field data stored in field memories, and then store the result in field memories. An intra-field interpolating unit interpolates a moving image pixel using a single piece of field data stored in the field memory, and then stores the moving image pixel in an interpolation memory. An inter-field interpolating unit interpolates a still image pixel using two pieces of field data stored in the field memories, and then stores the still image pixel in an interpolation memory. A still/moving image area determining unit determines whether each pixel of a progressive picture is a still image pixel or a moving image pixel. On the basis of a result of the determination by the still/moving image area determining unit, a selector reads a pixel value in the interpolation memory for a moving image pixel, and reads a pixel value from the interpolation memory for a still image pixel.

Structure-adaptive B-snake for segmenting complex objects

Abstract: In this paper, we presented a structure-adaptive B-snake model for segmenting the complex structures in medical images. A strategy of automatic control-point insertion, adaptive to the structure of the studied object, has been proposed. Furthermore, a method of minimum mean square energy (MMSE) is developed to iteratively estimate the position of those control points in the B-snake model. By applying the proposed structure-adaptive B-snake model to medical images, we show that our method is robust and accurate in object contour extraction.

Hand and face segmentation using motion and color cues in digital image sequences

Abstract: In this paper, we present a hand and face segmentation algorithm using motion and color cues. The algorithm is proposed for the content based representation of sign language image sequences, where the hands and face constitute a video object. Our hand and face segmentation algorithm consists of three stages, namely color segmentation, temporal segmentation, and video object plane generation. In color segmentation, we model the skin color as a normal distribution and classify each pixel as skin or non-skin based on its Mahalanobis distance. The aim of temporal segmentation is to localize moving objects in image sequences. A statistical variance test is employed to detect object motion between two consecutive images. Finally, the results from color and temporal segmentation are analyzed to yield a change detection mask. The performance of the algorithm is illustrated by simulation carried out on the silent test sequence.

Segmentation of soil section images using connected operators

Abstract: Segmentation of soil section images is an important task for automating the measurement of the grains' properties as well as for detecting and recognizing objects in the soil, important for its bioecological quality. We apply several types of morphological systems to watershed-based segmentation of soil section images. We use efficient connected operators such as reconstruction open-closing and area open-closing as well as some relatively new operators, the levelings, for image denoising, simplification and feature/marker extraction. Further, we introduce an improvement of the reconstruction operators used in segmentation, based on a generalized multiscale connectivity analysis.

Document processing apparatus and method

Abstract: A document processing apparatus for segmenting a color document image into regions obtains a binary image by binarizing a color image, and extracts regions having different background colors from the color image to generate region information indicating the position and size of each extracted region. By making region segmentation on the basis of the binary image and region information, a region segmentation result that reflects the background colors can be obtained. In this way, region segmentation which can maintain region differences expressed by colors in a color document can be implemented.

Set-valued maps for image segmentation

Abstract: The goal of this paper is an analytical basis of a region growing method using set-valued maps. They are to provide an approach to image segmentation that does not use a priori conditions on the final segment. Seizing a suggestion of Demongeot and Leitner ([8]), we start with a compact subset of the grey-valued image, and the region growing method is based on the continuous deformation of sets for decreasing some error functional. Avoiding any further restrictions on these sets leads to describing the process as a set-valued map. The ansatz of the deforming sets utilizes reachable sets of differential inclusions that admit more than one velocity of propagation at each point. So set-valued maps underlie a mathematical segmentation problem posed and solved in the first part. Then we present a suggestion how to apply the analytical results to a very simple computer implementation.

Image segmentation using local spectral histograms

Abstract: We propose a new algorithm for image segmentation. We use the spectral histogram, which is a vector consisting of marginal distributions of responses from chosen filters as a generic feature for texture as well as intensity images. Motivated by a new segmentation energy functional, we derive an iterative and deterministic approximation algorithm for segmentation. Based on the relationships between different scales and neighboring windows, we also develop an algorithm which can automatically detect homogeneous regions in an input image, which may consist of texture regions. To reduce the boundary uncertainty due to the large spatial window used for spectral histograms, we propose a novel local feature by building precise probability models based on current segmentation results. We have applied our algorithm to intensity, texture, and natural images and obtained good results with accurate texture boundaries.

Segmentation of Colour Images with Highlights and Shadows sing Fuzzy-like Reasoning

Abstract: In this paper, a fuzzy-like technique is presented that resolves several difficult issues related to image segmentation, such as highlights and shadows. Large, relatively continuous, areas within an image are usually easy to segment, and the pixels included within different segments are often determined by using derived edge information. However, in many cases, pixels which lie between segments or in high frequency areas of an image cannot be easily categorised as belonging to any particular segments. Typically, according to the dichromatic reflection model, these pixels may belong to the matte, highlight or shadow area of the closest segment; or, in association with neighbouring pixels, they make up a separate smaller segment. The dichromatic reflection model is applied here to merge highlight and shadow areas with matte areas in an image. By segmenting those pixels into proper regions, the proposed fuzzy-like reasoning approach provides a more human-like segmentation of images.

Method and apparatus for rotation registration of extended field of view ultrasound images

Abstract: 1 method is provided for obtaining an extended field of view diagnostic ultrasound image. image frame and a second image frame of an object of interest are acquired. The image are rotated relative to one another. Pixel points, representing spatial points in the object rest, are identified in the first image frame. Pixel points corresponding to the pixel points first image frame are then computed in the second image frame. A rotation angle en the first and the second image frames is calculated based on a least-squares relation en the pixel points. The first and second image frames are combined to form a part of an ded field of view image.

Active appearance motion model segmentation

Abstract: An adaptive method for temporal sequence segmentation was developed and its performance assessed in the segmentation of cardiac motion image sequences. The primary contribution of this paper is the development of a novel, 2D+time active appearance motion model (AAMM) that represents the dynamics of the cardiac cycle in combination with the shape and image appearance of the heart. Cootes' 2D active appearance model (AAM) framework was extended by considering a complete image sequence as a single shape/intensity sample. This way, the proven strength of AAMs, like robustness and ability to capture observer preference, are augmented with temporal consistency over an image sequence.

Segmentation of text lines in digitized images

Abstract: A method for locating symbols arranged in one or more rows in an image includes smearing the image, and fitting line segments through edge points of features in the smeared image. A group is found of the line segments that are in mutual proximity and are mutually substantially parallel. A region of the image that contains the group of the line segments is identified as a possible location of the symbols.

Image segmentation by edge pixel classification with maximum entropy

Abstract: Image segmentation is a process to classify image pixels into different classes according to some pre-defined criterion. An entropy based image segmentation method is proposed to segment a gray-scale image. The method starts with an arbitrary template. An index called Gray-scale Image Entropy (GIE) is employed to measure the degree of resemblance between the template and the true scene that gives rise to the gray-scale image. The classification status of the edge pixels in the template is modified in such a way as to maximize the GIE. By repeatedly processing all the edge pixels until a termination condition is met, the template would be changed to a configuration that closely resembles the true scene. This optimum template (in an entropy sense) is taken to be the desired segmented image. Investigation results from simulation study and the segmentation of practical images demonstrate the feasibility of the proposed method.

Method for automatic segmentation of image data from multiple data sources

Abstract: A method ( 300 ) and apparatus ( 400 ) is described for segmenting an image ( 102 ). Starting with each pixel of the image ( 102 ) being a separate region, segments are formed by merging the regions. As merging proceeds, a merging cost of the regions being merged generally increases. This increase however is not purely monotonic as the overall rise in the merging cost is punctuated by departures from monotonicity. A complete pass is made through the segmentation, in which all regions are merged until only one remains. By analysing the points immediately after significant departures from monotonicity, a final segmentation stopping value (λ stop ) is chosen as being the last return to monotonicity from such a significant departure. Segmentation is repeated until the merging cost reaches the final segmentation stopping value (λ stop ).

Improving a genetic algorithm segmentation by means of a fast edge detection technique

Abstract: This paper presents a new hybrid range image segmentation approach Two separate techniques are applied consecutively First, an edge based segmentation technique extracts the edge points-creases and jumps-contained in the given range image Then, by using only the edge point position information, the boundaries are computed Secondly, the points clustered into each region are approximated by single surfaces through a genetic algorithm (GA) The GA takes advantage of previous edge representation finding the surface parameters that best fit each region It works in a local way, according to the boundary information, reducing considerably the required CPU time Experimental results with different range images are presented; moreover a comparison using either the edge detection stage or not is given

Content based representation of colour image sequences

Abstract: A procedure is described for the spatiotemporal segmentation and tracking of objects in colour image sequences. For this purpose, we propose the novel procedure of the k-means with a connectivity constraint algorithm as a general segmentation algorithm combining several types of information including colour, motion and compactness. A new colour distance is also defined for this algorithm. The regularisation parameters are evaluated automatically using the min-max criterion. In this algorithm, the use of spatiotemporal regions is introduced since a number of frames is analyzed simultaneously and as a result the same region is present in consequent frames. Experimental results on real and synthetic colour data demonstrate the performance of the data.

Edge-based image segmentation using curvature sign maps from reflectance and range images

Abstract: A new approach to image segmentation by edge detection is proposed for preserving objects topology and shape while retrieving precisely located, one-pixel-wide edges. The method is based on mean (H) and Gaussian (K) surface curvatures sign maps (HK-sign maps) computed from both registered reflectance and range images, provided by a single sensor. HK-sign maps have been used to identify objects regions on range and intensity images, but not edges, as presented in this work. The combination of the computed range and reflectance edge maps has led to more accurate segmentation results than just by using either of them alone. The proposed algorithm has been tested on real images and compared to four traditional range image segmentation algorithms. Experimental results demonstrate the viability and usefulness of our approach.

An adaptive technique for the extraction of object region and boundary from images with complex environment

Abstract: A faster and accurate method for the extraction of object region and boundary from images with complex background environment is presented in this paper. The segmentation procedure begins with the computation of an optimum threshold to distinguish the darker regions in the image. It is an automatic thresholding algorithm that would work under all lighting conditions, where prefixing of threshold value is considered ineffective. The centre of mass of this thresholded region acts as a seed for further processing. Then the object region is obtained by using a region growing technique called integrated neighbourhood search. A quad-structure based technique is used to enhance the speed of region search significantly. A back projection algorithm is used to optimise the search for the pixels belonging to the object region.. A boundary thinning and connecting algorithm based on the application of a novel search window on the preliminary boundary is used to obtain a connected single pixel width boundary. The new method does not need a priori knowledge about the image characteristics. The main advantage of the proposed technique is its high-speed response, which brought an average of 36% decrease in the processing time involved that facilitates real-time analysis of the images.

Region based segmentation technique and algorithms for 3D image

Abstract: Region growing is a general technique for image segmentation, where image characteristics are used to group adjacent pixels together to form regions. This paper presents a parallel algorithm for solving the region growing problem based on the split and merge approach, and uses it to test and compare various parallel architecture models. Image segmentation is the process by which the original image is partitioned into some meaningful regions. It is the foundation of higher level processing; eg, object recognition. Both algorithms are supposed to segment 2D as well as 3D data sets. An objective comparison performs the evaluation using specified region growing, splitting and merging, and region segmentation.