A Study of Column & Row power function Image Contrast Enhancement Technique based on Image Segment

碩士 === 國立勤益科技大學 === 資訊工程系 === 106 === Internet and digital imaging technology was development. Image processing has been widely used. A lot of information must be analyzed through image processing. Therefore, the quality of image presentation has different effects due to the distribution of differen...

Full description

Bibliographic Details
Main Authors: Yu-min Su, 蘇昱明
Other Authors: Dr. Hsueh-Yi Lin
Format: Others
Language:zh-TW
Published: 2018
Online Access:http://ndltd.ncl.edu.tw/handle/7a2752
Description
Summary:碩士 === 國立勤益科技大學 === 資訊工程系 === 106 === Internet and digital imaging technology was development. Image processing has been widely used. A lot of information must be analyzed through image processing. Therefore, the quality of image presentation has different effects due to the distribution of different light sources. Such as, Overexposed, Underexposed, Insufficient contrast & Contrast is too strong. The image area details are lost. However, image enhancement technology is to solve the image with weak details. Common image enhancement techniques include Histogram Equalization, Anti-hyperbolic image enhancement, Power function. This study is based on an adaptive power function (APF). Perform image enhancement analysis and research, the main content is that the row-area enhancement and the combined Power Function algorithm cannot meet the human visual needs when the brightness distribution of the image is too extreme. The difference in brightness between the pixels at the same position in the two images is sensitively reflected by the change in Signal-to-Noise Ratio (SNR)/Peak Signal-to-Noise Ratio (PSNR). And change the structural information of the image surface brightness and contrast through the Structural Similarity Quality Index (SSIM). Perform an evaluation of the visual quality of the image. In the experimental results of this paper, We successfully applied the power function of row and column to image contrast enhancement. At the same time, we also prove through experiments that our proposed algorithm can make the details of the brightness distribution in the original image properly preserved. And improve the image quality.