Image super-resolution reconstruction method and device based on quantum efficiency
By generating an X-ray standing wave field and performing sub-pixel displacement in an X-ray imaging system to obtain the quantum efficiency distribution matrix, the problem of resolution limitation due to focal size is solved, high-precision image super-resolution reconstruction is achieved, and the performance of the X-ray imaging system is improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ZHONGBEI UNIV
- Filing Date
- 2026-04-27
- Publication Date
- 2026-07-17
AI Technical Summary
In existing X-ray imaging techniques, the focal size limits the improvement of image resolution, and super-resolution reconstruction methods based on convolutional neural networks rely on large-scale paired datasets that are difficult to obtain, resulting in limited algorithm generalization ability, inability to optimize quantum efficiency, and a lack of physical realism in reconstructed details.
By generating an X-ray standing wave field and driving it to undergo sub-pixel displacement on the detector, a quantum efficiency distribution matrix is obtained. Based on this matrix, the observed image is reconstructed and fused, eliminating detector response non-uniformity and noise distortion, and realizing subwavelength-level precise optical field excitation and a high-precision system response model.
It significantly improves the physical fidelity and spatial resolution of the image, eliminates detector non-uniformity and noise distortion, reconstructs the true incident photon distribution, and generates higher resolution X-ray images.
Smart Images
Figure CN122415798A_ABST