Low computational cost multilayer graph-based segmentation algorithms for hand recognition on mobile phones

Unconstrained and contact-free hand recognition problem with mobile devices is not solved yet because these systems have to deal with hard problems like different backgrounds and illumination. Algorithms to perform an image segmentation in order to create regions in the image with the same semantic meaning are a work in progress. Graph theory has been used successfully in order to reach a good image segmentation in many fields but these algorithms are computational demanding (time and memory) making it very difficult to use on mobile platforms. New algorithms to perform image segmentation are needed in order to adapt biometric technologies to mobile devices. This paper presents a segmentation algorithm based on multilayer graphs. We compared our results with other known segmentation algorithms (NCuts and KMeans) by using a synthetic database with over 400000 images. Our results show that the optimized implementation of the proposed algorithm makes this a powerful tool with high accuracy and low computational cost, improving the accuracy and the execution time of the two other algorithms.