A general theory for the morphological representation of discrete and binary images is presented. Particular cases of the general scheme are shown to yield a number of useful image representations. The effect of noise...
详细信息
A general theory for the morphological representation of discrete and binary images is presented. Particular cases of the general scheme are shown to yield a number of useful image representations. The effect of noise degradation is studied. It is proven that, under certain assumptions, the general reduced morphological skeleton is the best morphological representation among a collection of invertible morphological image representations. This representation results in a minimal upper-bound on the average probability of error of reconstructing a binary image from its noisy representation.< >
A projection-space approach for reconstruction from projections is presented. This approach uses the known convex support of the object both as a penalty term in a variational problem defined in projection-space and a...
A projection-space approach for reconstruction from projections is presented. This approach uses the known convex support of the object both as a penalty term in a variational problem defined in projection-space and as a guide to the specification of optimal smoothing coefficients that may vary spatially. Partial consistency of the sinogram is provided by including mass and center-of-mass constraints in the variational formulation. An outline of the general approach and calculations for a specific example are provided. computer simulations are provided for evaluation of the performance in this special case
We examine the tracking of 3-dimensional targets moving in a complex (e.g. highly textured) visual environment, which makes the application of methods relying on static segmentation and feature correspondence very pro...
详细信息
The Multiport Array Receptor (MAR), a system which combines optical sensing with integrated focal-plane processing capabilities, is described. Its central element is a photosensor array with hexagonal tesselation and ...
详细信息
The Multiport Array Receptor (MAR), a system which combines optical sensing with integrated focal-plane processing capabilities, is described. Its central element is a photosensor array with hexagonal tesselation and complex peripheral selection logic which provides parallel analog readout over prescribed areas. An external computing module performs real-time spatial convolution at multiple resolutions while a closed-loop microprogrammed controller addresses regions of interest and supervises communication between the camera and the host computer. This integrated image sensor and processor implements programmed sequences of instruction primitives and yields a complete state description of each processed pixel. It is capable of automatic edge tracking and returns lists of connected pixels.< >
Texture analysis algorithms that decompose images into oriented spatial frequency channels are studied. Optimality properties for texture segmentation filters are considered using idealized (narrowband) image texture ...
详细信息
Texture analysis algorithms that decompose images into oriented spatial frequency channels are studied. Optimality properties for texture segmentation filters are considered using idealized (narrowband) image texture models. The functional uncertainty of the channel filters is shown to define a tradeoff between spectral selectivity and accuracy in boundary localization that is optimized by the 2-D Gabor functions. The idealized texture model is then relaxed to analyze the effects of textural perturbations interpreted as localized amplitude and phase variations on the segmentation. The effects of these perturbations are found to be effectively ameliorated with postdetection smoothing.< >
Visual pattern image coding (VPIC) is a flexible image coding device offering excellent visual fidelity at high compression ratios with unprecedented, extremely low coding complexity. Hierarchical visual pattern image...
详细信息
Visual pattern image coding (VPIC) is a flexible image coding device offering excellent visual fidelity at high compression ratios with unprecedented, extremely low coding complexity. Hierarchical visual pattern image coding (HVPIC) schemes which achieve significantly increased compression (approaching 35:1) with improved fidelity and the very low complexity associated with VPIC are described. HVPIC employs standard VPIC embedded in a multiresolution (pyramid) structure. Low-resolution images coded at the upper levels augment coding of the higher-resolution images. Interactions between resolution levels is simple and efficient, yielding little increase in complexity relative to VPIC.< >
We describe a system that performs model‐based recognition of the projections of generalized cylinders, and present new results on the final classification of the feature data. Two classification methods are proposed...
A particular form of parallelism, called bit-parallelism, is introduced. A bit-parallel organization distributes each bit of a data item to a different processor. Bit-parallelism allows computation that is sublinear w...
详细信息
A particular form of parallelism, called bit-parallelism, is introduced. A bit-parallel organization distributes each bit of a data item to a different processor. Bit-parallelism allows computation that is sublinear with word size for such operations as integer addition, arithmetic shifts, and data moves. The implications of bit-parallelism for system architecture are analyzed. An implementation of a bit-parallel architecture based on a mesh with a bypass network is presented. Using a conservative estimate for cycle time, a Silt processor performs 64-b integer additions more than 10 times faster than the Connection Machine-2. Using current CMOS technology, a 16 M processor Silt system would be capable of nearly 500 billion 32-b adds per second. The application of the architecture to low-level vision algorithms is discussed.< >
作者：
JOU, JYBOVIK, ACLaboratory for Vision Systems
Computer and Vision Research Center Department of Electrical and Computer Engineering The University of Texas at Austin Austin Texas 78712-1084 USA
Techniques are described for improving the speed and accuracy of iterative visible-surface reconstruction algorithms. In particular, the importance of obtaining accurate early information is emphasized, both in the in...
详细信息
Techniques are described for improving the speed and accuracy of iterative visible-surface reconstruction algorithms. In particular, the importance of obtaining accurate early information is emphasized, both in the initial surface approximation and in the early localization of surface discontinuities. The first of these goals is attained using a simple technique known as constraint expansion , which yields a good initial approximation while accounting for detected discontinuities. The second goal is attained by using the locations of the image irradiance edges as a guide in locating potential discontinuities. Discontinuity detection in later stages of computation is augmented by a double-thresholding strategy and discontinuity backtracking.
暂无评论