A novel artificial intelligence model for color image quality assessment for security enhanement weighted by visual saliency

Abstract

Artificial Intelligence (AI) is the enhancement and method of computer system that handles tasks which requires human like intelligence such as recognition, language translation and visual interpretation. Subjective image quality assessment (IQA) is difficult to be implemented in real-time systems, methodology for enhancing the involvement in producing IQA model is to improve the quality of image by significant evaluation. Intuitively, human eyes are not sensitive to the distortion and damage from the area with lesser visual saliency (VS), VS is closely related to IQA. With this consideration, an effective IQA was proposed, which involved two processes. The local quality map of a distorted image was computed using the structural similarity function of its feature attributes, such as brightness, chrominance and gradient. Second, the local quality map was weighted with visual saliency (VS) to get the objective evaluation of image quality. The VS was modeled by extracting the saliency of low-level features of the image, wiping off the molestation information from these saliency based on an apriori threshold, and combining the effective information to construct the saliency map. Image processing using fuzzy is gathering features and segments as fuzzy set while processing images. The experiments on the two largest database for six classical IQA metrics demonstrate that performance of weighted-VS IQA metrics is superior to the performance of no weighted-VS IQA metrics, and the proposed IQA method has higher computational accuracy than the other IQA metrics under a moderate computational complexity, especially for two types of distortion images, such as local block-wise (Block) and fast-fading (FTF).