MINU-EXTRACTNET: Automatic Latent Fingerprint Feature Extraction System Using Deep Convolutional Neural Network

j. of Comput. sci. res.

2022

Self Cite

Latent fingerprints are the unintentional impressions found at the crime scenes and are considered crucial evidence in criminal identification. Law enforcement and forensic agencies have been using latent fingerprints as testimony in courts. However, since the latent fingerprints are accidentally leftover on different surfaces, the lifted prints look inferior. Therefore, a tremendous amount of research is being carried out in automatic latent fingerprint identification to improve the overall fingerprint recognition performance. As a result, there is an ever-growing demand to develop reliable and robust systems. In this regard, we present a comprehensive literature review of the existing methods utilized in latent fingerprint acquisition, segmentation, quality assessment, enhancement, feature extraction, and matching steps. Later, we provide insight into different benchmark latent datasets available to perform research in this area. Our study highlights various research challenges and gaps by performing detailed analysis on the existing state-of-the-art segmentation, enhancement, extraction, and matching approaches to strengthen the research.

“…Researchers' contributions are summarized in Table 1. In comparison to the other algorithms, the stateof-the-art [22,34,36,38] algorithms perform better.…”

Section: Latent Fingerprint Feature Extractionmentioning

confidence: 93%

Section: Latent Fingerprint Feature Extractionmentioning

confidence: 99%

A Study on Automatic Latent Fingerprint Identification System

Deshpande¹,

j. of Comput. sci. res.

2022

Self Cite

“…Hence, the fingerprints need to be pre-processed to remove background noise and bring out important foreground ridge information. We use the deep neural network model called "Pre-ProcessNet" [33] to perform automatic segmentation (ROI cropping), and enhancement operations. Pre-ProcessNet generates orientation maps from the learned dictionary of orientation patches.…”

Section: Latent Minutiae Feature Extractionmentioning

confidence: 99%

“…To increase the size of the background database, we extract the minutiae features from different extraction methods and store them in the gallery database. We accomplish this task by extracting fingerprint features from a MATLAB application called "Simple Fingerprint Matching (SFM)" [32] and a deep neural network model called "ExtractNet" [33] as shown in Fig. 10b, c.…”

Section: Fvc 2004 Setupmentioning

confidence: 99%

See 1 more Smart Citation

Latent Fingerprint Identification System Based on a Local Combination of Minutiae Feature Points

Deshpande¹,

Patil

et al. 2021

SN COMPUT. SCI.

Self Cite

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 (

CNNAI: A Convolution Neural Network-Based Latent Fingerprint Matching Using the Combination of Nearest Neighbor Arrangement Indexing

Deshpande¹,

Patil

et al. 2020

Front. Robot. AI

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.