This study evaluates four image enhancement techniques---Bilateral Filtering, Contrast Limited Adaptive Histogram Equalization (CLAHE), Wavelet Denoising, and Super-Resolution---with respect to their impact on Convolutional Neural Network (CNN)-based body part classification from X-ray images. Image quality is quantified using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) across three datasets: LEG, CT Scan, and Chest X-ray. Bilateral Filtering consistently delivers superior performance to the other enhancement methods on all three datasets. On the LEG dataset, Bilateral Filtering achieved a PSNR of 51.78 and an SSIM of 0.99918, outperforming CLAHE, which yielded a... More >