Image enhancement using artificial neural network and fuzzy logic

Abstract

Digital images are important source of information used for analysis and interpretation. During image acquisition image is degraded up to some extent. Thus we have to go through the process called image enhancement. It improves the visual appearance of an image. This paper presents a technique for image enhancement using artificial neural network and fuzzy logic. It denoise and enhance an image when it is corrupted by different noises such as salt and pepper, gaussian and nongaussian noises. In Image analysis, denoising and enhancing are most important pre-processing and post-processing steps. Several filters have been illustrated till date but have many limitations. In the proposed technique, Artificial neural network determines type of noises whereas Fuzzy logic used for denoising and enhancement purpose. Experimental results shows the effectiveness of the proposed method by quantitative analysis and visual illustration. Several parameters like PSNR, MSE, AD,NAE are used for performance evaluation.

Enhancement of Shadow Region in an Image using Artificial Neural Network

“…Back-Propagation (BP) neural network based enhancement technique was proposed in [8]. Combination of Artificial neural network and fuzzy logic based approach can also be used for image enhancement [9]. Back-propogation based neural network approach for removing impulsive noise was introduced in [10].…”