This book introduces novel Genetic Programming (GP) methodologies for enhancing feature learning in image classification tasks. The authors address the inherent challenges of image classification, stemming from high image variability, by proposing GP-based approaches to automatically evolve effective feature representations. The book details the integration of techniques such as image operators, ensembles, and surrogates to boost both the accuracy and computational efficiency of GP in this domain. It is structured to demonstrate the application and interpretability of these learned models across various image classification challenges.

The book presents a focused exploration of advanced Genetic Programming techniques applied to the critical field of image classification. It highlights the novelty of its proposed methods, aiming to improve both accuracy and efficiency in feature learning. The content is structured to serve as a comprehensive resource for advanced students and researchers in artificial intelligence, machine learning, computer vision, and evolutionary computation. The authors demonstrate the practical application and interpretability of their models across various image classification scenarios.