| 摘要 |
An estimation system provides quality measure of a given image for image/video applications to determine if the image needs to be enhanced or not. The system systemically measures the image quality by estimating quantization parameter of the compressed digital image. This allows estimating the image quantization parameter effectively in the pixel domain. Because block artifact are caused by image compression transforms, especially in flat image region, the estimation system first detects the suspicious regions of the image for the block artifacts by calculating a variance for each location in the image. Next, noise power is computed by using the detected regions. Then, the estimated noise power is compared with the statistical model to calculate the quantization parameter that is used in the encoder side when the input image is compressed. Finally, a quantization parameter is used as a quality measure of the input image.
|
