Showing papers on "Range segmentation published in 2004"

Efficient Graph-Based Image Segmentation

Abstract: This paper addresses the problem of segmenting an image into regions. We define a predicate for measuring the evidence for a boundary between two regions using a graph-based representation of the image. We then develop an efficient segmentation algorithm based on this predicate, and show that although this algorithm makes greedy decisions it produces segmentations that satisfy global properties. We apply the algorithm to image segmentation using two different kinds of local neighborhoods in constructing the graph, and illustrate the results with both real and synthetic images. The algorithm runs in time nearly linear in the number of graph edges and is also fast in practice. An important characteristic of the method is its ability to preserve detail in low-variability image regions while ignoring detail in high-variability regions.

Combining intensity, edge and shape information for 2D and 3D segmentation of cell nuclei in tissue sections.

Abstract: We present a region-based segmentation method in which seeds representing both object and background pixels are created by combining morphological filtering of both the original image and the gradient magnitude of the image. The seeds are then used as starting points for watershed segmentation of the gradient magnitude image. The fully automatic seeding is done in a generous fashion, so that at least one seed will be set in each foreground object. If more than one seed is placed in a single object, the watershed segmentation will lead to an initial over-segmentation, i.e. a boundary is created where there is no strong edge. Thus, the result of the initial segmentation is further refined by merging based on the gradient magnitude along the boundary separating neighbouring objects. This step also makes it easy to remove objects with poor contrast. As a final step, clusters of nuclei are separated, based on the shape of the cluster. The number of input parameters to the full segmentation procedure is only five. These parameters can be set manually using a test image and thereafter be used on a large number of images created under similar imaging conditions. This automated system was verified by comparison with manual counts from the same image fields. About 90% correct segmentation was achieved for two- as well as three-dimensional images.

Image processing apparatus for generating a wide dynamic range image

Abstract: An image processing apparatus for generating a wide dynamic range image to enable contrast to be maintained in low luminance image areas and high luminance image areas when the image is displayed by a narrow density range display system having: an image data buffer in which short-time exposure image data is stored; an image area segmenting circuit for fractionating long-time exposure image data into areas of proper and improper exposure; a segmented area image information extracting circuit for segmenting the properly exposed area of the long-time exposure image data on the basis of the segmented information and segmenting the improperly exposed area as a properly exposed area by applying the short-time exposure image data; a gradation correcting circuit for gradation-correcting image data in the properly exposed areas of the long-time exposure and the short-time exposure images which have been segmented by the segmented area image information extracting means, respectively; and an image synthesizer for synthesizing the properly exposed areas after gradation correction to form a composite wide dynamic range image.

Method and apparatus for probabilistic image analysis

Abstract: Embodiments of the present invention are directed to a method and apparatus for probabilistic image analysis. In one embodiment, an image is normalized and filtered. A determination is made regarding the likelihood of the image randomly matching characteristics of the reference image. If the likelihood is smaller than a threshold, the system determines that the image and the reference image match. In one embodiment, the likelihood is determined by using patches of skin in the images. In one embodiment, the likelihood is derived from the coherence of the optical flow computed between the two images. In one embodiment, the image is partitioned into a plurality of pixel regions. A pixel region in one image is mapped to a best-fit region in the other image. A neighbor region of the pixel region is mapped to a best-fit pixel region in the other image . The positional relationship between the pixel region and its neighbor is compared with the positional relationship between the two best-fit pixel regions.

Range image segmentation by an effective jump-diffusion method

Abstract: This paper presents an effective jump-diffusion method for segmenting a range image and its associated reflectance image in the Bayesian framework. The algorithm works on complex real-world scenes (indoor and outdoor), which consist of an unknown number of objects (or surfaces) of various sizes and types, such as planes, conics, smooth surfaces, and cluttered objects (like trees and bushes). Formulated in the Bayesian framework, the posterior probability is distributed over a solution space with a countable number of subspaces of varying dimensions. The algorithm simulates Markov chains with both reversible jumps and stochastic diffusions to traverse the solution space. The reversible jumps realize the moves between subspaces of different dimensions, such as switching surface models and changing the number of objects. The stochastic Langevin equation realizes diffusions within each subspace. To achieve effective computation, the algorithm precomputes some importance proposal probabilities over multiple scales through Hough transforms, edge detection, and data clustering. The latter are used by the Markov chains for fast mixing. The algorithm is tested on 100 1D simulated data sets for performance analysis on both accuracy and speed. Then, the algorithm is applied to three data sets of range images under the same parameter setting. The results are satisfactory in comparison with manual segmentations.

Still Image Segmentation Tools for Object-based Multimedia Applications

Abstract: In this paper, a color image segmentation al- gorithm and an approach to large-format image segmen- tation are presented, both focused on breaking down im- ages to semantic objects for object-based multimedia ap- plications. The proposed color image segmentation algo- rithm performs the segmentation in the combined intensity- texture-position feature space in order to produce con- nected regions that correspond to the real-life objects shown in the image. A preprocessing stage of conditional image fil- tering and a modified K-Means-with-connectivity-constraint pixel classification algorithm are used to allow for seamless integration of the different pixel features. Unsupervised op- eration of the segmentation algorithm is enabled by means of an initial clustering procedure. The large-format image seg- mentation scheme employs the aforementioned segmenta- tion algorithm, providing an elegant framework for the fast segmentation of relatively large images. In this framework, the segmentation algorithm is applied to reduced versions of the original images, in order to speed-up the completion of the segmentation, resulting in a coarse-grained segmen- tation mask. The final fine-grained segmentation mask is produced with partial reclassification of the pixels of the original image to the already formed regions, using a Bayes classifier. As shown by experimental evaluation, this novel scheme provides fast segmentation with high perceptual seg- mentation quality.

Apparatus and method for converting two-dimensional image to three-dimensional stereoscopic image in real time using motion parallax

Abstract: Disclosed is a current sample image acquisition unit for acquiring a current sample image, obtained by sampling a current input image provided by an image source; a previous sample image acquisition unit for acquiring a previous sample image, obtained by sampling a previous input image provided by the image source; a motion detector for detecting a moving pixel and a still pixel through comparison between corresponding pixels within the current and previous sample images; a region splitting unit for splitting the current sample image into a plurality of search regions and generating a representative value of the moving pixel in each search region using information about the moving pixel detected by the motion detector; a depth map generator for determining a moving pixel group constructing an object moving in each search region using the representative value of each search region and setting a small weight value for the moving pixel group, to generate a depth map image having the resolution of the original input image; and a positive parallax processor for generating a left-eye image and a right-eye image such that the depth map image is displayed on the display in such a manner that the moving pixel group is located before the screen of the display and remaining pixel groups are arranged behind the screen.

Watershed segmentation for binary images with different distance transforms

Abstract: This work evaluates and compares the performances of watershed segmentation for binary images with different distance transforms including Euclidean, City block and Chessboard.

Shape Particle Filtering for Image Segmentation

Abstract: Deformable template models are valuable tools in medical image segmentation. Current methods elegantly incorporate global shape and appearance, but can not cope with localized appearance variations and rely on an assumption of Gaussian gray value distribution. Furthermore, initialization near the optimal solution is required.

Multi-view image generation

Abstract: A multi-view image generation unit (100) for generating a multi-view image on basis of an input image is disclosed. The generation unit (100) comprises: edge detection means (102) for detecting an edge in the input image; depth map generation means (104) for generating a depth map for the input image on basis of the edge, a first group of elements of the depth map corresponding to the edge having a first depth value, related to a viewer of the multi-view image, and a second group of elements of the depth map corresponding to a region of the input image, being located adjacent to the edge, having a second depth value, related to the viewer of the multi-view image, the first value being less than the second value; and rendering means (106) for rendering the multi-view image on basis of the input image and the depth map.

Adaptive eigen-backgrounds for object detection

Abstract: Most tracking algorithms detect moving objects by comparing incoming images against a reference frame. Crucially, this reference image must adapt continuously to the current lighting conditions if objects are to be accurately differentiated. In this work, a novel appearance model method is presented based on the eigen-background approach. The image can be efficiently represented by a set of appearance models with few significant dimensions. Rather than accumulating the necessarily enormous training set to generate the eigen model, the described technique builds and adapts the eigen-model online evolving both the parameters and number of significant dimension. For each incoming image, a reference frame may be efficiently hypothesized from a subsample of the incoming pixels. A comparative evaluation that measures segmentation accuracy using large amounts of manually derived ground truth is presented.

Segmentation using multiscale cues

Abstract: Edges at multiple scales provide complementary grouping cues for image segmentation. These cues are reliable within different ranges. The larger the scale of an edge, the longer range the grouping cues it designates, and the greater impact it has on the final segmentation. A good segmentation respects grouping cues at each scale. These intuitions are formulated in a graph-theoretic framework where multiscale edges define pairwise pixel affinity at multiple grids, each captured in one graph. A novel criterion called average cuts of normalized affinity is proposed to evaluate a simultaneous segmentation through all these graphs. Its near-global optima can be solved efficiently. With a sparse yet complete characterization of pairwise pixel affinity, this graph-cuts approach leads to a hierarchy of coarse to fine segmentations that naturally take care of textured regions and weak contours.

Energy Partitions and Image Segmentation

Abstract: We address the issue of low-level segmentation for real-valued images. The proposed approach relies on the formulation of the problem in terms of an energy partition of the image domain. In this framework, an energy is defined by measuring a pseudo-metric distance to a source point. Thus, the choice of an energy and a set of sources determines a tessellation of the domain. Each energy acts on the image at a different level of analysiss through the study of two types of energies, two stages of the segmentation process are addressed. The first energy considered, the path variation, belongs to the class of energies determined by minimal paths. Its application as a pre-segmentation method is proposed. In the second part, where the energy is induced by a ultrametric, the construction of hierarchical representations of the image is discussed.

Shape gradient for image segmentation using information theory

Abstract: The paper deals with video and image segmentation using region based active contours. We consider the problem of segmentation through the minimization of a new criterion based on information theory. We first propose to derive a general criterion based on the probability density function using the notion of shape gradient. This general derivation is then applied to criteria based on information theory, such as the entropy or the conditional entropy for the segmentation of sequences of images. We present experimental results on grayscale images and color videos showing the accuracy of the proposed method.

Object recognition using segmentation for feature detection

Abstract: A new method is presented to learn object categories from unlabeled and unsegmented images for generic object recognition. We assume that each object can be characterized by a set of typical regions, and use a new segmentation method - "similarity-measure segmentation" - to split the images into regions of interest. This approach may also deliver segments, which are split into several disconnected parts, which turn out to be a powerful description of local similarities. Several textural features are calculated for each region, which are used to learn object categories with boosting. We demonstrate the flexibility and power of our method by excellent results on various datasets. In comparison, our recognition results are significantly higher than the results published in related work.

Interpolation of edge portions of a digital image

Abstract: A method and apparatus for interpolating color image information are provided One or more image data values for a portion of a digital image in a vicinity of a target pixel are received and stored in a local array A processor determines whether there is an edge in the vicinity of the target pixel based on the data values in the local array If there is not an edge in the vicinity of the target pixel, then long scale interpolation is performed on the image data values in the local array, in order to result in interpolating color information that is missing from the image If there is an edge in the vicinity of the target pixel, then short scale interpolation is performed using image data values in a subset of the local array in a closer vicinity of the target pixel As a result, accurate color rendering of a digital image is achieved, even in the presence of an edge portion that exhibits great contrast between regions of the image

Frame interpolation method and apparatus, and image display system

Abstract: An image interpolation method comprises searching a motion vector from different pairs of blocks on a first and a second reference image symmetrically, extracting a first and a second image block from the first and the second reference image, respectively, the first and the second image block being located by the motion vector, determining a region determination threshold using an absolute difference between paired opposite pixels of the first and the second image block, extracting from each of the first and the second image block a first pixel region that the absolute difference is smaller than the region determination threshold, and obtaining a pixel value of a second pixel region of the to-be-interpolated block from a pixel value of the first pixel region of each of the first and the second image block, the second pixel region corresponding to the first pixel region.

Image generating system and program

Abstract: It is an object to provide an image generating system and program which can generate such an image as in the real world with reduced processing load The alpha-value for each pixel in the original image is set to a value corresponding to its Z-value The set alpha-value is used to perform alpha-blending between the original image and a defocused image As the difference between the Z-value of the focus and the depth value increases, the synthesis ratio of the defocused image is increased The range of depth of field and defocusing effect are controlled by varying the corresponding relationship between the Z-value and the alpha-value The alpha-value is set such that the alpha-value for an pixel located in an area AR 1 between Z 1 and Z 2 will be set to α 1 , the alpha-value for an pixel located in an area AR 2 between Z 2 and Z 3 will be set to α 2 and so forth The alpha-value is set by updating the alpha-value of a pixel located farther from an object when the object is drawn in a frame buffer When the original image is set as a texture which is in turn mapped through the bi-linear filtering method, the defocused image is generated by shifting the texture coordinates by a value smaller than one texel

Image processing apparatus and method, and computer program

Abstract: A representative point for pixel value adjustment at which the same pixel value is to be set is selected from each of a correction image to be corrected and a reference image of a mosaic image. A tone curve that defines an output pixel value with respect to an input pixel value is generated by a line that passes through a pixel-value-conversion coordinate point defined by pixel values indicating the representative points selected from the correction image and the reference image, which are set as input and output values. This line is generated by a spline curve. The pixel value of the correction image is converted based on the generated tone curve.

An information theoretic framework for image segmentation

Abstract: In this paper, an information theoretic framework for image segmentation is presented. This approach is based on the information channel that goes from the image intensity histogram to the regions of the partitioned image. It allows us to define a new family of segmentation methods which maximize the mutual information of the channel. Firstly, a greedy top-down algorithm which partitions an image into homogeneous regions is introduced. Secondly, a histogram quantization algorithm which clusters color bins in a greedy bottom-up way is defined. Finally, the resulting regions in the partitioning algorithm can optionally be merged using the quantized histogram.

Clustering on image boundary regions for deformable model segmentation

Abstract: We present a novel approach, clustering on local image profiles, for statistically characterizing image intensity in object boundary regions. In deformable model segmentation, a driving consideration is the geometry to image match, the degree to which the target image conforms to some template within the object boundary regions. The template should account for variation over a training set and yet be specific enough to drive an optimization to a desirable result. Using clustering, a template can be built that is optimal over the training data in the metric used, such as normalized correlation. We present a method that first determines local cross-boundary image profile types in the space of training data and then builds a template of optimal types. Also presented are the results of a study using this approach on the human kidney in the context of medial representation deformable model segmentation. The results show an improvement in the automatic segmentations using the cluster template, over a previously built template.

Object segmentation using stereo images

Abstract: Object segmentation is one of the vital tasks in various three-dimensional applications. The paper presents a hybrid object segmentation algorithm to combine intensity segmentation and disparity segmentation in a stereoscopic vision system. First, the disparity maps of the stereo images are estimated using a foreground-based disparity estimation method. Then, the intensity stereo images and their corresponding disparity maps are separately segmented using a region-growing technique. The real segmentation mask can be obtained and the semantic object be extracted by a fusion processing on the intensity and disparity segments. Computer simulations indicate the reliable performance of the proposed algorithm for stereoscopic segmentation.

Edge based region growing: a new image segmentation method

Abstract: Quite often, in grey level image segmentation, the objects to be delineated are found in regions of non-uniform illumination. In these cases, using thresholds derived from intensity-based algorithms cannot yield good segmentation performance. Region growing techniques have been shown to perform well under these situations. In this paper, a novel edge based region growing method is presented. Two kinds of seeds (pixels) - hot and cold, are defined near edges (of objects) and both kinds of regions are grown from these seeds simultaneously. In this paper, the approach is not sensitive to the parameters, for example the sizes of different operators and the thresholds in edge detection and edge region detection. This technique produces good segmentation results, even for cases of images with non-uniform illumination.

An Algorithm for Swarm-based Color Image Segmentation

Abstract: Segmentation of nontrivial color images is one of the most difficult tasks in digital image processing. This paper presents a novel color image segmentation algorithm, which uses a biologically inspired paradigm known as swarm intelligence, to segment images based on color similarity. The swarm algorithm employed uses image pixel data and a corresponding segment map to form a context in which stigmergy can occur. The emergent property of the algorithm is that connected segments of similar pixels are found and may later be referenced. We demonstrate the algorithm by applying it to the task of segmenting digital images of butterflies for the purpose of automatic classification.

A semantic approach to segmentation of overlapping objects.

Abstract: Objectives: This paper aims at introducing a novel approach for segmentation of overlapping objects and at demonstrating its applicability to medical images. Methods: This work details a novel approach enhancing the known theory of full-segmentation of an image into regions by lifting it to a semantic segmentation into objects. Our theory allows the formal description of partitioning an image into regions on the first level and allowing the occurrence of overlaps and occlusions of objects on a second, semantic level. Possible applications for the use of this ‘semantical segmentation‘ are the analysis of radiographs and micrographs. We demonstrate our approach by the example of segmentation and separation of overlapping cervical cells and cell clusters on a set of 787 image pairs of registered PAP- and DAPIstained micrographs. The semantical cell segmentation yielding areas of cell plasmas and nuclei are compared to a manual segmentation of the same images, where 2212 cells have been labeled. A direct comparison of over and under-segmentation between the two segmentation sets yields a mean difference value of 10.15% for the nuclei and 10.80% for the plasma. Results: Using the proposed theory of semantical segmentation of images in combination with adequate models of the image contents, our approach allows identifying, separating and distinguishing several overlapping, occluding objects in medical images. Applying the proposed theory to the application of cervical cell segmentation from overlapping cell clusters and aggregates, it can be seen that it is possible to formally describe the complex image contents. Conclusions: The proposed method of semantical segmentation is a mighty tool and under the assumption of the subtractive transparency model can be used in different medical image processing applications such as radiology and microscopy. By using alternative models to solve the ambiguities attached to overlaps and occlusions, further fields of application can be addressed.

Automatic color space selection for biological image segmentation

Abstract: In this paper, we have tested criteria designed by Liu and Borsotti to automatically evaluate the quality of a color segmentation. As they do not correctly answer our microscopy image problems, we propose two modified criteria adapted to two different biological applications. Penalizing inhomogeneity, numerous small regions and misclassified regions, our modified criteria help to select the best color space, for a given segmentation method.

Shape gradient for multimodal image segmentation using mutual information

Abstract: This paper deals with video and image segmentation using region based active contours. We propose to search for an optimal domain with regards to a criterion based on information measures such as entropy of mutual information. We use a general derivation framework based on the notion of shape gradient. This general derivation is applied to criteria based on information theory, such as mutual information for the segmentation of sequences of images. Finally, we present experimental results on color video sequences showing the efficiency of the proposed method for face segmentation.

Method and system for image segmentation

Abstract: A method for segmenting an image is disclosed wherein a fractal map of the image is generated by estimating the fractal dimension of each pixel in the image. The image is segmented by thresholding the fractal map of the image.