DenoiseNet: An Efficient Image Denoising Using Convolutional Neural Networks

Image denoising is a crucial research area in image processing, with significant advancements made over the past decade. Recently, this field has gained renewed attention due to the advancement of deep learning method. With this work, we have proposed an optimized Convolutional Neural Network (CNN) architecture for image denoising (DenoiseNet). The model is designed to handle various types of noise, i.e. Gaussian, Poisson, and salt-and-pepper noise. To evaluate its performance, we tested DenoiseNet on the publicly available Flickr2k dataset, achieving high Peak Signal-to-Noise Ratio (PSNR) while preserving image quality. Moreover, DenoiseNet emphasizes computational efficiency, making it highly suitable for real-time applications where both speed and accuracy are critical. The results affirm that DenoiseNet is a robust solution for contemporary image denoising challenges.