Local image features play an important role in many classification tasks as translation and rotation do not severely deteriorate the classification process. They have been commonly used for medical image analysis. In medical applications, it is important to get accurate diagnosis/aid results in the fastest time possible.

This dissertation tries to tackle these problems, first by developing a localized feature-based classification system for medical images and using these features and to give a classification for the entire image, and second, by improving the computational complexity of feature analysis to make it viable as a diagnostic aid system in practical clinical situations.

For local feature development, a new approach based on combining the rising deep learning paradigm with the use of handcrafted features is developed to classify cervical tissue histology images into different cervical intra-epithelial neoplasia classes. Using deep learning combined with handcrafted features improved the accuracy by 8.4% achieving 80.72% exact class classification accuracy compared to 72.29% when using the benchmark feature-based classification method.