An approach to 2-D model-based object recognition is developed, suitable for implementation on a highly parallel SIMD (single-instruction, multiple data stream) computer. Object models and image data are represented a...
详细信息
ISBN:
(纸本)0818608625
An approach to 2-D model-based object recognition is developed, suitable for implementation on a highly parallel SIMD (single-instruction, multiple data stream) computer. Object models and image data are represented as contour features. Transformation sampling is used to determine the optimal model-feature-to-image-feature transformation by sampling the space of possible transformations. Only a small part of this space need actually be sampled due to the constraints placed on transformations by individual matches of image features to model features. The procedure requires O(Kmn) processors and O(log2 (Kmn)) time, where m is the number of model features, n is the number of image features, and K depends on the size of the image. The procedure works well and is extremely robust in the presence of occlusion. An implementation of the procedure on the Connection Machine is described, and some experimental results given.
Various types of moments have been used to recognize imagepatterns in a number of applications. The authors evaluate a number of moments and address some fundamental questions, such as image representation ability, n...
详细信息
ISBN:
(纸本)0818608625
Various types of moments have been used to recognize imagepatterns in a number of applications. The authors evaluate a number of moments and address some fundamental questions, such as image representation ability, noise sensitivity, and information redundancy. Moments considered here include regular moments, Legendre moments, Zernike moments, pseudo-Zernike moments, rotational moments and complex moments. Properties of these moments are examined in detail, and the interrelationships among them are discussed. Both theoretical and experimental results are presented.
To simulate the edge perception ability of human eyes and detect scene edges from an image, context information must be used in the edge detection process. To accomplish the optimal use of context, the authors introdu...
详细信息
ISBN:
(纸本)0818608625
To simulate the edge perception ability of human eyes and detect scene edges from an image, context information must be used in the edge detection process. To accomplish the optimal use of context, the authors introduce an edge detection scheme which uses the context of the whole image. The edge context for each pixel is the set of all row monotonically increasing paths through the pixel. The edge detector assigns a pixel that edge state having highest edge probability among all the paths. Experiments indicate the validity of the edge detector. Upon comparing the performance of the context dependent edge detector with the context free second directional derivative zero-crossing edge operator, the authors find that the context dependent edge detector is superior.
An efficient mapping frame a tree structure into a pipelined array of 2log N stages is presented for processing an N × N image. In the proposed mapping structure, the identification of the information growing pro...
详细信息
ISBN:
(纸本)0818608625
An efficient mapping frame a tree structure into a pipelined array of 2log N stages is presented for processing an N × N image. In the proposed mapping structure, the identification of the information growing property inherent in feature-extraction algorithms allows bit-level concurrency to be exploited in the architectural design. Accordingly, the design of each staged pipelined processor is simplified.
The conventional least-squares distance method of fitting a line to a set of data points is unreliable when the amount of random noise in the input (such as an image) is significant compared with the amount of data co...
详细信息
ISBN:
(纸本)0818608625
The conventional least-squares distance method of fitting a line to a set of data points is unreliable when the amount of random noise in the input (such as an image) is significant compared with the amount of data correlated to the line itself. Points which are far away from the line are usually just noise, but they contribute the most to the distance averaging, skewing the line from its correct position. The author presents a statistical method of separating the data of interest from random noise, based on a maximum-likelihood principle.
The authors present a linear feature-reduction technique for multicomponent or textured image segmentation. The transformation matrix is computed by simultaneously diagonalizing scatter matrices evaluated at two diffe...
详细信息
ISBN:
(纸本)0818608625
The authors present a linear feature-reduction technique for multicomponent or textured image segmentation. The transformation matrix is computed by simultaneously diagonalizing scatter matrices evaluated at two different spatial resolutions. Under reasonable conditions, this transform closely approximates the generalized Fisher linear disciminants which are optimal for region separability. Experimental examples suggest that this technique is superior to the Karhunen-Loeve transform for texture segmentation.
A method is presented for depth recovery through the analysis of scene sharpness across changing focus position. Modeling a defocused image as the application of a low pass-filter on a properly focused image of the sa...
详细信息
ISBN:
(纸本)0818608625
A method is presented for depth recovery through the analysis of scene sharpness across changing focus position. Modeling a defocused image as the application of a low pass-filter on a properly focused image of the same scene, the authors can compare the high spatial frequency content of regions in each image and determine the correct focus position. Recovering depth in this manner is inherently a local operation, and can be done efficiently using a pipelined imageprocessor. Laplacian and Gaussian pyramids are used to calculate maps which are collected and compared to find the focus position that maximizes high spatial frequencies for each region.
Using fundamental operators from image algebra, the authors present simple closed-form expressions for dilation, erosion, and convolution. Algebraically, these expressions appear as terms within the algebra. Moreover,...
详细信息
ISBN:
(纸本)0818608625
Using fundamental operators from image algebra, the authors present simple closed-form expressions for dilation, erosion, and convolution. Algebraically, these expressions appear as terms within the algebra. Moreover, the methodology for obtaining the expressions reveals a universal operational structure within image algebra, of which the three aforementioned operations are particular instances. The result is a natural parallel mechanism for computation and a representation of convolution that naturally overcomes the difficulties arising from the variability of image domains in the defining relation.
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
ISBN:
(纸本)0818608625
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 intensity edges as a guide in locating potential discontinuities.
The intensive use of the connected-components algorithms in image analysis and robot vision calls for a very fast implementation of such algorithms suitable for real-time applications. A hardware design is presented w...
详细信息
ISBN:
(纸本)0818608625
The intensive use of the connected-components algorithms in image analysis and robot vision calls for a very fast implementation of such algorithms suitable for real-time applications. A hardware design is presented which implements the algorithm due to J. T. Schwartz, M. Sharir, and A. Siegel (1985). A prototype board, which does not use special VLSI chips, had been constructed previously that can compute the connected components in a 512 × 512 binary image in few video frame times (about 300 ms). A real-time version (video speed) in VLSI is proposed.
暂无评论