FSKD '07 Proceedings of the Fourth International Conference on Fuzzy Systems and Knowledge Discovery - Volume 01
No-reference image quality assessment based on DCT domain statistics
Signal Processing
No reference image quality assessment for JPEG2000 based on spatial features
Image Communication
No-reference image quality assessment using modified extreme learning machine classifier
Applied Soft Computing
A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms
IEEE Transactions on Image Processing
Hi-index | 0.00 |
Contourlet transform has excellent properties for image representation, such as multiresolution, localization and directionality, which are the key characteristics of human vision system. In this paper, a novel image quality assessment metric based on the characteristics of contourlet coefficients of images is proposed. Firstly, the original image and the distorted images are decomposed into several levels by means of contourlet transform respectively. The contourlet coefficients of the original image and the distorted images are as the referenced matrixes and the comparative matrixes respectively. Secondly, calculate the correlativity indexes between the referenced matrixes and the comparative matrixes respectively. Moreover, image quality assessment vector of every distorted image can be constructed based on the correlativity indexes values and image quality can be assessed. Performance experiments are made on image quality database with four different distortion types. Experimental results show that the proposed method improves accuracy and robustness of image quality prediction.