Image Semantic Quality Evaluation Model for Human-Machine Hybrid Intelligence: A Gradient-based Uncertainty Calculation Method

With the advancement of human-machine hybrid intelligence technology, the importance of images in interaction becomes increasingly high. The accurate evaluation of image semantic quality becomes crucial. However, traditional evaluation models may be limited in this environment. New methods are needed to improve evaluation accuracy. Then, an evaluation model for gradient-based uncertainty calculation method was proposed. The study conducted semantic distortion perception analysis at two levels. Firstly, overall, the recognition ability was analyzed by analyzing the average recognition accuracy of the dataset. Secondly, recognition ability analysis was conducted based on the confidence level of a single sample. Experiments showed that machines had a higher tolerance for distortion compared to humans. However, these machines were 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 proposed framework reached 68.03%, which was significantly better than 59.83% for humans and 40.16% for machines. The results indicated 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. © 2024 Slovene Society Informatika. All rights reserved.