Abstract
This article studies the perceptual quality evaluation method of humanistic images based on the characteristics of human vision. First, this study obtained the disparity map of the human visual cultural image and used the edge map and saliency map to correct the weight of the disparity map. The weighted disparity map was then integrated into a perceptible score using a Minkowski fused deep neural network. A multi-scale method was employed to process the image to obtain the visual effect score. Taking Polytechnic University of Lausanne (EPFL) as an example, an experimental study was conducted on the three dimensional visual quality assessment method proposed in this article. The test results with the EPFL library show that the target score obtained by this method has good consistency and monotonicity with the subjective score of the EPFL library. The article's results verify the effectiveness of the visual effects and aesthetics evaluation method proposed in this article.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call