A Triple Approach To Digital Image Processing: Enhancement, Encryption And Compression Using Artificial Intelligence

Digital image processing serves a vital function in medical imaging, multimedia and cybersecurity. But common approaches seem too rigid. Though AI-inclined approaches may enhance the encryption and compression processes an all-included prediction model is not yet utilized. This study forms a model that is AI-inclined with the use of Random Forest, Gradient Boosting, Neural Networks and XGBoost. It asserts that Gradient Compression ratio, PSNR, and SSIM can improve precision via stacked ensemble learning, as well as test performance with the use of R² Score, MAE, and MSE. A dataset comprising of 300 images with elements like the Encryption Strength, Noise Level, Resolution, Entropy, and Sharpening Factor was applied. The models were tried and put to training in an 80-2- way, containing hyperparameters tuned for optimization. The feature vitality was analysed via XGBoost and Random Forest to find out the essential predictors. The model used obtained splendid precision ofr PSNR (96.70%) and SSIM (((>(&%). To validate its efficacy in the image quality estimate. Compression proportion was at 14.07% the lowest indicating a dependency and structural complexity of the compression. Entropy and resolution width indicated the major predictors of PNSR and SSIM, while Encryption power was predicted Compression Ratio. This study offers an AI-prediction framework that provide a detailed image processing structure with image processing quality. It attains high precision for PNSR and SSIM as a result it enhances image quality evaluation. The paper finds fundamental qualities which impacts the image processing function, to facilitate practical optimization. It can also highlight the basic challenges in compression proportion prediction to suggest enhancements via deep learning. The projected AI-framework improves the image processing with maximum high precision, consistently to predict PSNR and SSIM. However, the ratio of the prediction needs to be fine-tuned, which emphasizes the execution of deep learning approaches. The utilization of AI models should be added to in the learning procedures as well as deep learning procedures to enhance accuracy and increase its usage in the medical imaging, multimedia and cybersecurity processing.