Satpute Yuvraj Suryabhan , Vaishali Mangesh Dhede , Rahul M Mulajkar

The demand for high-resolution images has significantly increased across various fields such as medical diagnostics, surveillance, satellite imaging, and digital restoration. This paper proposes a novel histogram-based resolution enhancement method using advanced image processing and machine learning techniques. The approach incorporates fuzzy logic and adaptive histogram equalization to improve the visibility and detail of low-resolution images while mitigating artifacts and noise. By leveraging neural networks, specifically a backpropagation model, this method learns and processes histogram features to enhance image quality. Experimental results on MRI brain images demonstrate superior performance, showing improvements in Peak Signal-to-Noise Ratio (PSNR) and Root Mean Squared Error (RMSE). This work contributes to the advancement of high-resolution imaging by providing a robust and computationally efficient solution that can be applied in critical areas like medical imaging and forensic analysis

https://doi.org/10.58357/jedcs.2025.v4.i1.6