Curve Detection in VLSI

Abstract

Four VLSI designs for a line and curve detection chip are presented. Each method is based on Montanari’s dynamic programming algorithm [9.1]. The output of each system is the sequence of coordinates or chain code of the optimal curve(s) detected. One method uses a systolic array of size proportional to the number of rows in the image to detect the optimal curve. To detect a curve of length m requires m passes through the systolic array, taking time proportional to m times the number of columns in the image. A second systolic array design consists of a linearly tapering pipeline of cells. The length of the pipeline is equal to m and the total number of cells in the pipeline is proportional to m³. Time proportional to the image area is required during a single pass through the image. The third systolic approach uses an array of cells of size proportional to m times the number of rows in the image. Only one pass through the image is required to detect the curve, taking time proportional to the number of image columns. Details are given for a VLSI chip design using the third approach. The fourth method describes an algorithm for an SIMD array machine.