A Comparative Evaluation of Gaussian Multiscale Aggregation for Hand Biometrics
The process of segmentation consists of dividing the image in regions with similar characteristics. In other words, segmentation is the partitioning of digital images into several regions, according to a given criteria . In addition, applying biometrics to daily scenarios involves difficult and challenging requirements in terms of software and hardware. On the contrary, current biometric techniques are also being adapted to present-day devices, like mobile phones, laptops and the like, which are considered to be unconstrained and contact-less. In fact, achieving a combination of both necessities is one of the most difficult problems at present in biometrics. Segmentation in these kind of environments require special effort and attention, since although there exist an obvious difficulty in providing accurate segmentation to these scenarios, the constraints in terms of software and hardware are important and affect the segmentation performance. Therefore, this paper presents a segmentation algorithm able to provide suitable solutions in terms of precision for hand biometric recognition, considering a wide range of backgrounds like carpets, glass, grass, mud, pavement, plastic, tiles or wood. Results highlight that segmentation accuracy is carried out with high rates of precision (F-measure≥ 88%), presenting competitive time results when compared to state-of-the-art segmentation algorithms time performance. Finally, the accuracy of the proposed method is compared to the performance of Normalized Cuts in terms of segmentation accuracy and time performance.