基于自适应双通道特征融合的色彩图像评价方法及装置
By using an adaptive dual-channel feature fusion method, which combines feature maps and weight parameter matrices of color and grayscale channels, the problem of inaccurate color image evaluation in existing technologies is solved, and a more efficient art scoring system is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SOUTH CHINA NORMAL UNIV
- Filing Date
- 2023-12-19
- Publication Date
- 2026-07-17
AI Technical Summary
Existing art scoring systems rely on manual feature extraction algorithms, which are difficult to accurately represent the high-level semantic features of color images, resulting in inaccurate and inefficient evaluation results and failing to effectively assist professional art schools in their grading work.
An adaptive dual-channel feature fusion method is adopted, which extracts feature maps through color channels and grayscale channels, calculates an adaptive weight parameter matrix, and fuses the feature maps to suppress inconsistency conflicts and improve the accuracy of color evaluation.
By using an adaptive dual-channel feature fusion method, the accuracy and efficiency of color image evaluation are improved, which can better represent classification information, assist in the marking process, and reduce the burden of manual marking.
Smart Images
Figure CN117830653B_ABST