Research on Image Semantic Quality Evaluation Model for Human Machine Hybrid Intelligence: A Gradient Based Uncertainty Calculation Method

Abstract

With the advancement of human-machine hybrid intelligence technology, the importance of images in interaction has become increasingly high, and accurate evaluation of image semantic quality has become crucial. However, traditional evaluation models may be limited in this environment and new methods are needed to improve evaluation accuracy. On the ground of this, an evaluation model for gradient based uncertainty calculation method has been proposed. The study conducts semantic distortion perception analysis at two levels. Firstly, at the overall level, the recognition ability is analyzed by analyzing the average recognition accuracy of the dataset. Secondly, at the sample level, recognition ability analysis is conducted on the ground of the confidence level of a single sample. Experiments have shown that compared to humans, machines have a higher tolerance for distortion, but are weaker in terms of generalization and stability. The proposed method performed well on the complex CIFAR100 dataset, achieving the lowest FPR of 95%, the highest TPR of 528%, and the lowest error detection rate of 3.65%. In addition, the accuracy of the framework proposed by the research institute reached 68.03%, which is significantly better than 59.83% for humans and 40.16% for machines, indicating its ability to effectively combine the advantages of different decision-makers. This study is expected to provide new ideas for image quality evaluation, improving the application performance and user experience of images in multiple fields.