图像特征信息提的算法研究.pdf

万方数据 Subject: Study on Extracting Image Feature Information Algorithm Specialty: Communication and Information System Name: Wang Yiting (Signature)_______________ Instructor:Zeng Zhaohua Zhao Qian (Signature)_______________ ABSTRACT With the rapid development of computer vision and computer graphics, based on image feature information, exploring the imaging object has become a hot topic and has been also important role in the development of stereo vision. Therefore, describing the characteristical information points of the target based on the angle of the target image has been extracted through edge detection of the image, feature point extraction, and feature points matching. Considering effect from factors like environmental noise, in order to be able to obtain the appropriate description information of the target object image, the paper proposed improved algorithm of image edge detection, the algorithm can extract accurate the image edge for the fuzzy image. Respectively, Harris algorithm and SIFT algorithm extract the feature points in the image information, according to different description information of image feature points: the traditional gray correlation method under gray information and Euclidean distance matching of the descriptor information will be considered to produce larger defects of mismatch. Therefore, the improvement different feature point description information of matching algorithm is put forward, more and correct matching points is able to be get. Based on the research of the theory of Stereop