Gaussian Multiscale Aggregation Applied to Segmentation in Hand Biometrics

Alberto de Santos Sierra, Carmen Sánchez Ávila, Javier Guerra Casanova, Gonzalo Bailador del Pozo
2011 Sensors  
This paper presents an image segmentation algorithm based on gaussian multi-1 scale aggregation oriented to hand biometric applications. The method is able to isolate the 2 hand from a wide variety of background textures such as carpets, fabric, glass, grass, soil 3 or stones. The evaluation was carried out by using a publicly available synthetic database 4 with 408000 hand images in different backgrounds, comparing the performance in terms of 5 accuracy and computational cost to two
more » ... segmentation methods existing in liter-6 ature, namely Lossy Data Compression (LDC) and Normalized Cuts (NCuts). The results 7 highlight that the proposed method outperforms current competitive segmentation methods 8 with regard to computational cost, time performance, accuracy and memory usage. 9
doi:10.3390/s111211141 pmid:22247658 pmcid:PMC3251975 fatcat:qb4xdbkv3baophxhpzpqucrw2e