Showing papers on "Range segmentation published in 1989"

Range image segmentation based on differential geometry: a hybrid approach

Abstract: The authors describe a hybrid approach to the problem of image segmentation in range data analysis, where hybrid refers to a combination of both region- and edge-based considerations. The range image of 3-D objects is divided into surface primitives which are homogeneous in their intrinsic differential geometric properties and do not contain discontinuities in either depth of surface orientation. The method is based on the computation of partial derivatives, obtained by a selective local biquadratic surface fit. Then, by computing the Gaussian and mean curvatures, an initial region-gased segmentation is obtained in the form of a curvature sign map. Two additional initial edge-based segmentations are also computed from the partial derivatives and depth values, namely, jump and roof-edge maps. The three image maps are then combined to produce the final segmentation. Experimental results obtained for both synthetic and real range data of polyhedral and curved objects are given. >

Fast segmentation of range imagery into planar regions

Abstract: A technique is presented for rapidly dividing surfaces in range imagery into regions satisfying a common homogeneity criterion. The result is a segmentation of the range information into approximately planar surface regions. Key features that enhance that algorithm's speed include the development of appropriate region descriptors and the use of fast region comparison techniques for segmentation decisions. The algorithm is a split-and-merge segmentation approach, where the homogeneity criteria is based on a 3-parameter planar surface description technique. The three parameters are two angles describing the orientation of the normal to the local best fit plane and the original range value. Speed is achieved because both the region splitting and the rejection of merge possibilities can often be based on simple comparisons of only the two orientation parameters. A fast, but more complex region-to-region range continuity test is also developed, for use when the orientation homogeneity tests are inconclusive. The importance of merge ordering is considered, and in particular, an effective ordering technique based on dynamic criteria relaxation is demonstrated. Example segmentations of simple and complex range data images are shown, and the effects of noise and preprocessing are examined.

Method and device for image generation

Abstract: PURPOSE: To generate a moving picture fast by generating image data on respective bodies by using individual spatial filters which are determined by the statistical characteristics of the respective bodies, generating pixel assemblies, and composing image data on an area cut with the movement information signals of the bodies. CONSTITUTION: An individual spatial filter 15 1-n for each body generates image data showing the body according to its statistical characteristics and image data are supplied to a pixel constituting means 17 1-n to generate a pixel assembly. Then an actual image is composed of image data cut by an area dividing means 21 1-n with from the pixel assembly regarding the body with the movement information signal of the body. Therefore, when the body moves, its movement information signal varies, so the image data cut from the pixel assembly varies, and consequently a moving image is easily generated to speed up the moving image generation by the omission of arithmetic required for the image data generation. COPYRIGHT: (C)1991,JPO&Japio

Method of segmenting characters in lines which may be skewed, for allowing improved optical character recognition

Abstract: A method of segmenting characters of a document image comprises the steps of dividing the document image into a plurality of divided regions and setting a check width with respect to each of the divided regions, where each check width is greater than or equal to a width of a corresponding one of the divided regions so that the check widths of two mutually adjacent divided regions partially overlap each other, reading image data amounting to one line of the document image, obtaining from the image data horizontal projections of each line data within each of the check widths, where each horizontal projection is a number of black picture elements in a corresponding data line within a check width and each data line is made up of a plurality of picture elements arranged horizontally, segmenting a line based on the horizontal projections, obtaining from the image data vertical projections, where each vertical projection is a number of black picture elements in a vertical direction, determining a character segmentation range based on the vertical projections, and segmenting each character of the line within the character segmentation range.

Method of processing sampled signal valves produced by a color imaging device

Abstract: Blurring along edges between regions of different color characteristics in interpolated color images is avoided by a signal processing technique that segments the fully sampled channel into a plurality of contiguous image regions of respectively different image characteristics. The segmentation mechanism is such that, within a respective region, the fully sampled signal values are associated with a common image characteristic. A boundary between adjacent regions occurs where the segmentation mechanism has inferred the presence of an edge between sub-sampled locations and has assigned signal values for successive sampling locations of the fully sampled channel on opposite sides of the edge in accordance with different image characteristics. After the image has been segmented, within each region, signal values for non-sampled locations of a sub-sampled channel are interpolated in accordance with a predetermined relationship between fully sampled and sub-sampled signal values at a sampling location in that region whereat each of fully sampled and sub-sampled signal values have been produced. In addition, more than one segmentation mechanism may be employed. In this case, the image processing performance of each segmentation scheme is weighted. Interpolation values based upon each segmentation scheme are then combined as a weighted average.

Top-down image segmentation using object detection and contour relaxation

Abstract: A novel segmentation technique that starts with the whole image being a single region is presented. First, an object detection scheme, which marks those locations where local statistics deviate significantly from the overall statistics, provides location and approximate shapes of the major objects (regions) in the scene. Exact boundaries are subsequently obtained by a contour relaxation algorithm, which includes a general model for typical region shapes. Object detection and contour relaxation are repeated recursively until a stable segmentation result is achieved. Segmentation results are presented. >

Segmentation Using Intensity And Range Data

Abstract: Perception is the integration of various sensor outputs into a unified vision of the world. A major part of research in machine vision has been limited to the use of individual sensors for building machine vision systems. The use of multisensor data is advocated for object recognition systems, and an algorithm for fusion of intensity and range data for segmentation is proposed. The algorithm consists of two steps. First, the initial seed segmentation is achieved by using the most dominating sensor at a given time. For this purpose the distributions of the intensity and range data are considered, and the image is segmented recursively by using the most significant peak in both histograms. Second, the initial segmentation is refined by using region merging; the regions are merged if the combined strengths of range and intensity boundaries are low. The experimental results for synthetic and real scenes are presented.

Method and apparatus for processing and reproducing images

Abstract: Image information relating to an image is printed in a laser printer by forming image elements according to a raster pattern of image points and printing dots in a fixed number N of the image points within each image element, N being smaller than the number of image points in an image element. The image points wherein a dot is to be printed are arranged into a cluster with a minimal perimeter. The dots printed within an image element are all printed with the same intensity and thus have the same diameter, and may overlap contiguous image points in order to fill up the total area of the image element. In an embodiment the position of the cluster within each image element is selected according to the image information.

Hierarchical segmentation of 3-D range images

Abstract: The authors present a novel approach for segmentation of dense three-dimensional range images. In this approach, four local properties, namely the 3-D coordinate, the surface normal, the Gaussian curvature, and the mean curvature of each data point, are combined in a hierarchical data structure to segment a given 3-D dense range map into surface patches. This algorithm is applicable to planar as well as curved surfaces; several examples of segmentation of such surfaces are presented. >

Geometry Guided Segmentation

Abstract: Our overall goal is to develop an image understanding system for automatically interpreting dental radiographs. This paper describes the module that integrates the intrinsic image data to form the region adjacency graph that represents the image. The specific problem is to develop a robust method for segmenting the image into small regions that do not overlap anatomical boundaries. Classical algorithms for finding homogeneous regions (i.e., 2 class segmentation or connected components) will not always yield correct results since blurred edges can cause adjacent anatomical regions to be labeled as one region. This defect is a problem in this and other applications where an object count is necessary. Our solution to the problem is to guide the segmentation by intrinsic properties of the constituent objects. The module takes a set of intrinsic images as arguments. A connected components-like algorithm is performed, but the connectivity relation is not 4- or 8-neighbor connectivity in binary images; the connectivity is defined in terms of the intrinsic image data. We shall describe both the classical method and the modified segmentation procedures, and present experiments using both algorithms. Our experiments show that for the dental radiographs a segmentation using gray level data in conjunction with edges of the surfaces of teeth give a robust and reliable segmentation.

A curve analysis approach to surface feature extraction from range image

Abstract: A curve analysis approach to extracting surface curvature features from a range image is presented. The aim is to cope with the problem of the sensitivity of the derivative estimation to the noise and the conflict between the smoothness of the image required by the feature extraction procedures and the preservation of the local structure of the original image. It is based on the analysis of a one-dimensional image profile, because the surface curvature such as mean curvature and Gaussian curvature can be computed from the partial derivatives in the two axis directions. These derivatives should be estimated using only coherent data. This is achieved by curve fitting after curve segmentation. A measure is presented for postprocessing of segmentation that takes into account the pixel value in relation to a threshold and its neighboring context. The use of this measure significantly improves the quality of image segmentation. >

A parallel color algorithm for segmenting images of 3-D scenes

Abstract: Summary form only given, as follows. A parallel color algorithm for image segmentation is presented. From an input color image, the algorithm labels each pixel in the image according to the corresponding material in the scene. This segmentation is useful for many visual tasks, including inspection and object recognition. It is shown that color information is necessary to generate this kind of segmentation for a 3-D scene. The segmentation algorithm is based on a detailed analysis of the physics underlying color image formation and can be applied to images of a wide range of materials. Image texture is dealt with in a natural way. An initial edge detection on the intensity image is used to guide the color segmentation process. The algorithm is inherently parallel and can be effectively mapped onto high-performance parallel hardware. Results generated by the algorithm on several images are presented. >

Simultaneous image segmentation and edge detection

Abstract: It is shown that the two tasks of region and edge segmentation can be achieved using a single, unified approach based upon the cooccurrence matrix. It is also shown that, when an image is composed of non-textured regions, then the cooccurrence matrix possesses a characteristic structure of peaks corresponding to regions and boundaries in the image. The cooccurrence matrix will be treated as a feature space and, by utilising the structure of the matrix, it will be split into several distinct parts corresponding to contributions from regions or boundaries in the image. A natural mapping between the labelled matrix and the image will be defined. Using the labelled cooccurrence matrix, this natural mapping will enable each pixel in the image to be classified as either a boundary pixel of a specific direction or as a pixel of a particular type of region. This natural mapping simultaneously defines a thresholded edge strength image and an image segmentation. >

Segmentation Of Range Images

Abstract: An algorithm for segmenting range images of industrial parts is presented in this paper Range images, are unique in that they directly approximate the physical surfaces of a real world 3-D scene The segmentation of images ( range or intensity ) is based on edge detection or region growing techniques The algorithm presented in this paper segments the range images by detecting discontinuities There are three types of discontinuities in range images: jump, crease and smooth edges The detection of a jump edge is relatively easy and can be obtained using edge detection techniques used for intensity images The crease and smooth edges are difficult to detect especially in the presence of noise Our approach is based on the analysis of the difference between the input and the filtered images We show that, at an edge, the difference after Gaussian smoothing has a maxima in a direction perpendicular to the edge The close connected regions are then obtained by eroding the image once and an iterative region growing least square fit is used to obtain the final segmented image The performance of the proposed algorithm on a number of range images is presented

Range Image Analysis Via Quadtree And Pyramid Structure Based On Surface Curvature

Abstract: This paper presents a method which can expedite, while maintaining the accuracy, range image analysis such as range image segmentation, classification, and location of the region of interest in the range image, thereby making 3-D vision techniques based on range images more useful in manipulating robots accurately in real time. The proposed method incorporates quadtree and pyramid structure in order to quickly analyze range images. In order to make range image analysis independent of the viewing directions, surface curvatures, which are visible-invariant surface characteristics, are exploited. Specifically, we will discuss the following topics: (1) problems of using the surface curvatures for the range image analysis in the presence of noise; (2) generation of the range image pyramid; (3) reliable range image segmentation and classification via split-and-merge using the planarity test and the surface curvatures; (4) incorporation of the quadtree and the pyramid structure to speed up the projection process.

Image Segmentation Using Background Estimation

Abstract: Segmentation algorithms that do not require preselected thresholds and are rapid and automatic for various applications are introduced. The approach is to track how the background graytone distribution varies throughout the image without a priori knowledge. Rectangular image regions are sampled to track background variations. Criteria based on statistical theory are used to determine the homogeneity of regions and to distinguish between background-homogeneous and object-homogeneous regions. The criteria include upper and lower bounds to account for practical situations which arise when the underlying assumptions become invalid. Segmentation is focused on non-homogeneous regions. The background graytone distribution throughout the image is estimated from regions where it is measurable. Knowledge of the local background distribution throughout the entire image is then used to preserve the local brightness relationship of object pixels to the background. Rather than simply mapping the graytone image into an object-background binary image, more information is retained by determining additional thresholds and mapping pixels into object brightness relative to background and into uncertainty. Image regions made up of uncertainty labelled pixels assist in identifying image regions that require further processing.

Merging regions across feature maps in texture segmentation

Abstract: This paper describes segmentation phenomena of superimposed textures and the Linking phenomena. These phenomena provide us with information about the mechanism of a late stage of segmenting textures. The late stage takes place after the segmentation process forms regions in feature maps such that parameter values in one region are substantially different from those in the neighboring regions. At the stage, the segmentation process merges the regions across the feature maps to determine output regions by integrating information about how the regions occupy two-dimensional space. The segmentation process gets such information both from local areas and from areas far away from the local areas where it determines the output regions and boundaries.

Object detection and recognition via stochastic model-based image segmentation

Abstract: Summary form only given. A stochastic model-based image segmentation technique that utilizes the tone descriptor for object detection and recognition has been developed. The image regions are characterized by region-dependent constant mean (average-gray level) and variance (variation of gray level), and the distribution of the regions is modeled by a stochastic model. For a nondiffracting computed tomography (CT) image it has been proved that (1) at the pixel level, the pixel images are the asymptotic normal random variables, (2) at the class level, the regions are a normal random field, and (3) at the picture level, the observed image is a finite normal mixture. >

Discriminating regions of an image

Abstract: A method of discriminating between regions of an image. The image is represented by values defining the colour component content of pixels of the image and the method comprises comparing a value from each pixel with those of its neighbours to locate pixels whose values define turning points. Parts of the image where the density of turning points is greater than a threshold (19) are defined as screened regions of the image.

Method of and apparatus for processing and reproducing image information

Abstract: Image information relating to an image is printed in a laser printer by forming image elements according to a raster pattern of image points and printing dots in only part a fixed number N of the image points within each image element, N being smaller than the total number of image points in an image element. The image wherein a dot is to be printed are arranged into a cluster with a minimal perimeter. The dots printed within an image element are all printed with the same intensity and thus have the same diameter, and may overlap contiguous image points in order to fill up the total area of the image element. In an embodiment the position of the cluster within each image element is selected according to the image information.