Image Quality Assessment Based on Measuring the Degradation in Geometrical Structural Information
A new image quality metric based on measuring the loss of the structural information inherent in digital images is presented in this paper. The structural information is defined statistically and geometrically in a block basis. Statistical structure information includes luminance means and contrast. Geometrical structure information is extracted from the binary quantization that preserves the first two moments of the image block. To verify the validity of the proposed metric is evaluated against a large amount of test images in LIVE database and compared with that of the famous MSSIM. The cross-distortion test results show that the proposed metric outperforms MSSIM in judging the distorted images corrupted by JPEG2000, Gaussian blurring and fast fading and has the performance close to MSSIM in judging the distorted images corrupted by JPEG and white noises.
Chun-Hsien Chou Yun-Hsiang Hsu
Tatung University, Taipei
国际会议
2011亚太信号与信息处理协会年度峰会(APSIPAASC 2011)
西安
英文
1-4
2011-10-18（万方平台首次上网日期，不代表论文的发表时间）