Walking to singular points of fingerprints

Abstract

Singular point is an essential global feature in fingerprint images. Existing methods for singular points detection generally visit each pixel or each small image block to determine the singular point. That is to say, existing methods require scanning the image to compute a quantity at each pixel or block, and hence they are inevitably time-consuming. We propose a fast algorithm for detecting singular points by walking directly to them instead of scanning the image. Walking Directional Fields (WDFs) are established from the orientation field. Then following the walking directions on WDFs, we can rapidly walk to the singular points. The walking algorithm is extremely fast and easily implemented with acceptable accuracy. Further more, its accuracy can also be improved by combining with state-of-the-art methods: we can rapidly walk to a candidate singular point, then refine its location using existing more accurate method in the local area. Experimental results on datasets of SPD2010 and FVC validate the high efficiency and satisfactory accuracy of the proposed algorithm.

Robust technique for fingerprint template protection

“…By using the trial version of VeriFinger SDK [46], minutiae points are extracted from the fingerprint images. The approach mentioned in [47] is utilised for the detection of delta and core type singular points in a fingerprint, whereas for arch-type singular points technique proposed in [48] is used. For the evaluation of the performance of the proposed technique, false rejection rate (FRR), false acceptance rate (FAR), genuine acceptance rate (GAR), and equal error rate (EER) are computed.…”

Classificação de Singularidades em Imagens de Impressão Digital Baseada em Redes Neurais Convolucionais

“…Nos métodos baseados em template, para cada tipo de singularidade, há um filtro (ou template) que é convolucionado sobre a imagem de impressão digital para extrair singularidades [14,15]. Considerado o estado da arte [16], Awad e Baba [17] apresentaram um método baseado em 2 filtros complexos que captura as propriedades de simetria de laço e delta, respectivamente, então convoluciona cada filtro com a imagem de orientação e o ponto que obtiver a reposta mais alta do filtro é considerado ponto singular. Os algoritmos fundamentados na curvatura da orientação de regiões de pontos singulares são bons para detectar e classificar pontos singulares, visto que as áreas onde encontram-se tais pontos são marcadas pela grande mudança de orientação [18,19].…”

“…Os algoritmos fundamentados na curvatura da orientação de regiões de pontos singulares são bons para detectar e classificar pontos singulares, visto que as áreas onde encontram-se tais pontos são marcadas pela grande mudança de orientação [18,19]. Neste sentido, o trabalho de Qi e Liu [19], considerado estado da arte [16], apresenta um método sensível a ruído e falsas singularidades são extraídas.…”

Fusion Based Multimodel Biometric Authentication System using Ear and Fingerprint

“…Subsequently, in this examination, a quick algorithm for recognizing singular focuses is proposed by strolling straightforwardly to pictures instead of checking the pictures. Walking Directional Fields (WDFs) are set up from the orientation field [21]. Then, following the walking directions on WDFs, the method can quickly walk to the singular focuses.…”

“…In addition, an appearance term, ( , ) , measuring pixel intensity similarity and a bending energy term, ( , ) = , can be added to the similarity score. Afterward, the similarity measure was modified as * = + (21) Although this measure does not consider the strict one-to-one mapping of minutiae, through experimentation, this strategy turned out to be great, giving worthy execution in ear and fingerprint similarity assessment. But, the outcomes of minutiae mapping from the use of the Hungarian calculation on the contextually based cost histograms produced some un-normal sets.…”