| Summary: | 碩士 === 元智大學 === 光電工程學系 === 102 === This research uses the minimum average correlation energy method and shifted training images to recognize the polychromatic images based on Mach-Zehnder joint transform correlator. It leads to that the correlation output peak is much sharper and the input is proper to the liquid crystal device of input plane. In our former research, the training images are displayed at the center position. However, the total sidelobe energy may not be the minimum. In order to solve the problem, we transform the color image into three HSL color space components. Then, three components are rotated from 0° to 360° in steps of 5° and shifted from -5 to 5 pixels in both of vertical and the horizontal directions to yield training images. The system can deal with rotated images.
|
|---|
