Automatic fingerprint identification systems (AFIS) make use of global fingerprint information like ridge flow, ridge frequency, and delta or core points for fingerprint alignment, before performing matching. In latent fingerprints, the ridges will be smudged and delta or core points may not be available. It becomes difficult to pre-align fingerprints with such partial fingerprint information. Further, global features are not robust against fingerprint deformations; rotation, scale, and fingerprint matching using global features pose more challenges. We have developed a local minutia-based convolution neural network (CNN) matching model called "Combination of Nearest Neighbor Arrangement Indexing (CNNAI)." This model makes use of a set of "n" local nearest minutiae neighbor features and generates rotation-scale invariant feature vectors. Our proposed system doesn't depend upon any fingerprint alignment information. In large fingerprint databases, it becomes very difficult to query every fingerprint against every other fingerprint in the database. To address this issue, we make use of hash indexing to reduce the number of retrievals. We have used a residual learning-based CNN model to enhance and extract the minutiae features. Matching was done on FVC2004 and NIST SD27 latent fingerprint databases against 640 and 3,758 gallery fingerprint images, respectively. We obtained a Rank-1 identification rate of 80% for FVC2004 fingerprints and 84.5% for NIST SD27 latent fingerprint databases. The experimental results show improvement in the Rank-1 identification rate compared to the state-of-art algorithms, and the results reveal that the system is robust against rotation and scale.

Latent fingerprints are the fingerprint traces obtained from various surfaces of objects found at the crime scene. Latent fingerprint quality is, therefore, poor and they suffer from non-linear distortions. This is why latent fingerprints contain partial or incomplete minutia information. Developing an automatic fingerprint identification system (AFIS) for latent fingerprints becomes a major challenge because of a small number of minutia features. Moreover, currently developed AFIS for latent fingerprints are not robust against geometric transformations. In this article, based on the existing partial minutiae characteristics, we propose a method for detecting latent fingerprints. To identify an individual with existing nearest neighbor minutia structures, we develop a scale and rotation invariant algorithm called "Ratio of Minutiae Triangles (RMT)". The algorithm utilizes the features which are based on the local minutiae arrangements around a reference minutia. To deal with missing minutiae in latent fingerprints, we consider minutiae clusters based on nearest minutiae neighborhood relation to form hash structures. In the fingerprint retrieval process, these hash structures are used. On the FVC2004 (

No abstract

No abstract

No abstract