Title :
On using the CAM concept for parametric curve extraction
Author :
Meribout, Mahmoud ; Ogura, Takeshi ; Nakanishi, Mamoru
Author_Institution :
Integrated Inf. & Energy Syst. Lab., NTT, Kanagawa, Japan
fDate :
12/1/2000 12:00:00 AM
Abstract :
A parallel algorithm, in order to extract parametric curves from a two-dimensional (2-D) image space, is proposed. It is based on the Hough transform (HT) and uses the content addressable memory (CAM) as the main processor. A set of simulated results for circular shape extraction are presented in order to demonstrate its merit. Hence, voting, thresholding, and three-dimensional (3-D) peak extraction are efficiently performed within the CAM. In addition, and in order to reduce the quantization errors, a weighted AT algorithm (WHT), which uses a weighted voting is proposed. Experimental results indicate that a real-time shape extraction for an image 256×256 can be achieved within a small amount of hardware. Therefore, CAM-based HT can be considered as a promising attraction for next generation pattern recognition platforms.
Keywords :
Hough transforms; content-addressable storage; feature extraction; parallel algorithms; pattern recognition; 2D image space; 3D peak extraction; CAM concept; CAM-based HT; Hough transform; circular shape extraction; content addressable memory; experimental results; parallel algorithm; parametric curve extraction; pattern recognition platforms; processor; quantization errors reduction; real-time shape extraction; simulated results; thresholding; two-dimensional image space; weighted AT algorithm; weighted voting; Associative memory; CADCAM; Computer aided manufacturing; Hardware; Parallel algorithms; Pattern recognition; Quantization; Shape; Two dimensional displays; Voting;
Journal_Title :
Image Processing, IEEE Transactions on
