TRANSFORM EDGE-DETECTION

The blockwise transform edge detection method consists of segmenting the image into a number of small blocks, with neighboring blocks overlapping slightly; transforming each block by a fast transform; multiplying the transform coefficients of each block by a bandpass mask; inverse transforming the modified transform coefficients; detecting zero crossings and deciding an edge according to a thresholding scheme. Simulation results with the blockwise transform edge detection method in comparison to other bandpass filtering techniques indicate that higher performance is achieved with the new technique on the average. This is believed to result from the use of blockwise generalized filtering with appropriate transforms rather than linear convolutional filtering, as in other bandpass filtering techniques. The new method also has less computational complexity and is well-suited to parallel processing.