Research Of Image Enhancing Of Vein Based On Fuzzy Theory

With the development of society and the progress of science and technology, biological recognition technology (such as the iris, hand vein, fingerprints, etc.) for feature recognition has become the hotspot of research. Among them, the vein recognition has been giving more and more attention for the unique advantages, which is difficult to counterfeit and non-touch acquisition. But, for the influences of the equipment and lighting factors, the contrust of vein image is lower, and the vein images has more noise, that bring a lot of inconvenience to the recognition. So the image preprocessing is very necessary, before the recognition of vein image. Aiming at the vein preprocessing, the vein image de-noising and contrast enhancement was researched respectively, and a vein image pre-processing system was achieved.In denoising, while processing the vein image, amying at the mixed noise which is a mixture noise of the impulse noise and the gaussion noise,firstly, a specified template is used to detect whether a pixel is a impulse noise and then using a median filter to process the image. Secondly, the improved fuzzy weighted mean algorithm is used to restrain the uncertainly of gray value which is caused by the gaussion noise. At last, the experiment in the paper show the effect of the algorithm which is based on fuzzy reasoning.In enhancement, analyzing the typical fuzzy enhancement algorithm and considering the characteristic of the near imfrared vein image, image enhancement algorithm based on fuzzy contrast is raised. Firstly, the vein images are mapped from space field to fuzzy field. In the fuzzy field, A equation which is used to calculate the Image fuzzy contrast of the vein image is defined. Secondly, the improved fuzzy contrast enhancement operator is used to achieve the Contrast non-linear transformation. Then, the vein images are mapped from fuzzy field to space field. At last, complete the whole process of the vein image contrast enhancement.Otherwise, this paper realized the vein image preprocessing system. This system includes standardization, denoising, contrast enhancement and so on. In part of standization, this paper mainly process the size and grayscale of the vein image. Denoising and enhancement part of this system mainly adopts algorithms which studying in this paper. At last classical image threshold and regional denoising method were taken in the system. Through experiments, the result of the processing is verified in line with the need of regional feature extraction, for the improvement of vein recognition system laid the foundation.