According to the principle of speckle photography, CCD(Charge-Coupled Device) as a recorder, and EALCD(Electrically Addressed Liquid Crystal Display) as a read-out element, which makes the speckle photography to digital. Recording light path of the subjective and the objective speckle and observation light path of full-field analysis and point-by-point analysis for fringe reconstruction have been respectively researched. At the same time, measuring by speckle photography, the fringes in the interometry pattern must be carefully analyzed. Since the speckle noise can greatly infect the signals. Thus to de-noising the speckle fringe by a suitable filter before processing is expected. The mathod of digital filter enhancement, smooth denoising be used to reduce the influence of the high noise and the inhomogeneous grey of the speckle interferogram. Finally the thinning fringe is acquired, the fringe spacing is extracted accurately, the three-dimensional measurement of a deformed object is realized with mathematical morphological thinning algorithm.

<div> <p class="9"><span>Machine vision means to carry out measurement or judgment with machine instead of human eyes. In the field of target recognition, optical correlation technology is a main way to realize machine vision. Targets can be recognized and located with high precision</span><span> </span><span>taking advantage of optoelectronic hybrid joint </span><span>transform</span><span> correlator (OHJTC). However, when scale or angular distortion of the detected target exists relative to the reference template, the intensity of correlation peaks will decrease to a great extent, which restricted the recognition results greatly. In this paper, the development and principle of maximum average correlation height (MACH)</span><span> </span><span>algorithm is introduced. Through amounts of experiments, t</span><span>he control</span><span>ling</span><span> parameters</span><span> </span><span>of the synthesized filter</span><span> are optimized</span><span>, which makes MACH filter suppress background noise and widen recognition range of targets</span><span>. To show the feasibility of this algorithm, simulative and optical experiments of the improved MACH filter are carried out. As an example, the recognition results of a fighter target in sky</span><span> </span><span>are given, which shows </span><span>the </span><span>scale</span><span> </span><span>distortion tolerance can reach up </span><span>to </span><span>±</span><span>23%</span><span>. The actual effect of the improved MACH filter algorithm has been confirmed very well</span><span>.</span><span> <o:p></o:p></span></p> </div>

By comparing the similarity of their contour information, hybrid photoelectric joint transform correlator (JTC) is used to recognize the specific target. An effective method to increase the recognition rate is to extract the contour information of target and template and decrease the noise interference in image background. The principle of joint transform correlator is given in this paper. To increase the recognizing rate, a mask algorithm is presented, with which the coordinate of the correlation peaks can be located precisely. Before the mask algorithm, edge extraction with Robert operator is carried out to enhance the target contour information and reduce the background noise. Amounts of experiments prove the mask algorithm can locate the correlation peaks precisely. As an example, an experimental result is given with a car as the detected target. The coordinate of this car is (362, 438). Experimental results confirm the feasibility and effectiveness of the mask algorithm.

Hybrid optoelectronic joint transform correlator is a very effecitve tool to recognize a target, which has important application in military and industry field. However, in actual applications, under some situations, such as complex target background or insufficient contour information etc., the intensity of correlation peaks will be weak. Sometimes, the weak intensity of correlation peaks can not be recognized by joint transform correlator. Wavelet transform is adopted to process the joint target image. The principles of joint transform correlator and wavelet transform are given in this paper. As an actual example, a tank target is adopted to test the feasibility and effectiveness of this method. From computer simulation, we can get good experimental effect. After wavelet transform of joint target image, the intensity of correlation peaks has been increased obviously. Optical experiments confirm the feasibility and effectiveness of this method further. Amounts of experiments prove wavelet transform can extract the target contour effectively. Based on the principle of the proposed algorithm, the target recognizing rate can be increased to a higher level.