Artificial Neural Networks Applied to Digital Images with MATLAB Code

Artificial Neural Networks have broad applications in real-world business problems and have been successfully applied across many industries. As they excel at identifying patterns and trends in data, they are well suited for prediction and forecasting tasks such as sales forecasting, industrial process control, customer research, data validation, risk management, and target marketing. This work examines the use of Artificial Neural Networks in the field of image processing. One of the applications studied is edge detection, which significantly reduces data volume and filters out irrelevant information while preserving essential structural features of an image. Edge detection is widely used in various fields, ranging from real-time video surveillance and traffic management to medical imaging. The study presents both entropy-based and neural network-based edge detection methods, specifically using Rényi's entropy and convolutional neural networks, and compares their performance.