Problem Low-contrast MRI and CT images are hard to interpret, and existing techniques often fail to improve contrast and highlight edges. This paper proposes multi-feature linear Laplacian pyramid fusion (MFL-LPF) for joint contrast and edge enhancement.Approach Two enhanced images are obtained using k-means-based local histogram equalization and fast discrete curvelet transform. Both images are decomposed into a k-level Laplacian pyramid, and fusion is guided by Local Energy, Absolute Coefficient Magnitude, Gradient Magnitude, and Spatial Frequency. Hard-decision fusion retains high-frequency details, while weighted averaging preserves low-frequency brightness consistency.Results MFL-LPF achieved the best performance on 253 brain MRI images using entropy (6.95), PSNR (36.4 dB), MI (4.68), average gradient (11.25), QABF (0.96), and SSIM (0.78) with minimal artefacts.Conclusion MFL-LPF is a training-free, GPU-independent framework for efficient medical image enhancement, supporting real-time diagnostics and future multimodal fusion and tumour segmentation applications.
In the field of computer vision, traditional image dehazing methods are difficult to balance detail restoration and colour reproduction. Therefore, this study proposes a hybrid defogging method based on deep multi-shard layered networks. This method innovatively combines multi-shard with layered network technology, utilizing gated convolution technology to achieve fine-grained processing of image data. Finally, the depth image prior algorithm, edge connection algorithm and partial convolution algorithm were used as comparative algorithms for experimental verification. The results showed that the proposed method learned a similarity of 0.024 for the perceived image blocks, while the similarities of the compared algorithms were 0.148, 0.058, and 0.041, respectively. In empirical analysis, the proposed method has an average information entropy of 7.594 on five types of fog images. The above results indicate that this study provides an efficient and high-quality solution for image dehazing.
