Fuzzy Relational Image Compression for Face Recognition Tasks

Abstract

Data compression is always advisable when it comes to handling and processing information quickly and efficiently. There are two main problems that need to be solved when it comes to handling data; store information in smaller spaces and processes it in the shortest possible time. When it comes to face recognition tasks, there is always the need to construct large image repositories from people. Images that have to occupy more and more space, and makes the image processing a complicated task; given the rapidly increase in the image resolution every day. In this work, we show a simple and efficient method that uses Fuzzy Relational Product (FRP) to compresses the information inside an image, building with this a compressed relational matrix that holds enough information to reconstruct a lossy representation of the original image, or to perform face recognition tasks. We describe the feature extraction, based on overlapped frames, which generates vectors that will later be fed to an Artificial Neural Network, in the pattern recognition stage. We also show the image repository construction and finally, the performance of the face recognition task that goes up to 97.5%.