WCSE

Research on Visual Effect of Enhancing Image

Abstract— The visual effect of an image is affected by many factors. In order to get a better visual effect, it is necessary to pre-process the collected image to improve the number of image feature points matched. In this paper, histogram equalization, homomorphic filtering based on illumination-reflection model and enhancement method based on Retinex theory are utilized to pre-process the collected images, so as to enhance the contrast of the images. And Scale Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF) and Affine Scale Invariant Feature Transform (ASIF) are applied to extract and match the image features of the pre-processed images. The results show that the number of feature points of the image processed by enhancement methods is much higher than that of the image without enhancement.

Index Terms— histogram equalization, homomorphic filter, Retinex, enhancement

Chao Huang
School of Information Science and Engineering, Zaozhuang University, CHINA

[Download]

Cite: Chao Huang, "Research on Visual Effect of Enhancing Image," Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, pp. 207-212, Hong Kong, 15-17 June, 2019.