On latent fingerprint minutiae extraction using stacked denoising sparse AutoEncoders

Sankaran, Anush; Pandey, Prateekshit; Vatsa, Mayank; Singh, Richa

doi:10.1109/btas.2014.6996300

Cited by 36 publications

(27 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extracting reliable features from latent fingerprints is a challenging task [34]. Given the ground truth minutiae annotations, the performance of a minutiae extraction algorithm can be evaluated with good confidence.…”

Section: • Latent Fingerprint Feature Extraction and Matchingmentioning

confidence: 99%

Multisensor Optical and Latent Fingerprint Database

2015

Self Cite

View full text Add to dashboard Cite

Large-scale fingerprint recognition involves capturing ridge patterns at different time intervals using various methods, such as live-scan and paper-ink approaches, introducing intraclass variations in the fingerprint. The performance of existing algorithms is significantly affected when fingerprints are captured with diverse acquisition settings such as multisession, multispectral, multiresolution, with slap, and with latent fingerprints. One of the primary challenges in developing a generic and robust fingerprint matching algorithm is the limited availability of large data sets that capture such intraclass diversity. In this paper, we present the multisensor optical and latent fingerprint database of more than 19 000 fingerprint images with different intraclass variations during fingerprint capture. We also showcase the baseline results of various matching experiments on this database. The database is aimed to drive research in building robust algorithms toward solving the problem of latent fingerprint matching and handling intraclass variations in fingerprint capture. Some potential applications for this database are identified and the research challenges that can be addressed using this database are also discussed.INDEX TERMS Image databases, fingerprint recognition, forensics, feature extraction.

show abstract

Section: • Latent Fingerprint Feature Extraction and Matchingmentioning

confidence: 99%

Multisensor Optical and Latent Fingerprint Database

2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…This leads to extra processing time and produce wrong orientation patches as mentioned by Yang et al [28]. To define a minutiae and non minutiae in latent fingerprint image, Anush et al [27] worked towards automatically finding the feature and non feature value in latent image using a spectral analysis method, which is a neural network base learning approach.…”

Section: B Modern Approachmentioning

confidence: 98%

Latent Fingerprint preprocessing: Orientation field correction using region wise dictionary

Kumar

Velusamy

2015

2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI)

View full text Add to dashboard Cite

Latent Fingerprint Images have been extensively used by law enforcement agencies in investigating the crime spot and use the necessary information obtained as evidence to validate the criminal in Court. Although an important breakthrough in this direction has already been made in plain biometrics recognition, still identifying biometric such as Face in CCTV footage and Latent Fingerprint in uncontrolled, uncooperative, and hostile environment is an open research problem. Poor quality, lack of clarity, absence of proper mechanism make the latent fingerprint preprocessing problem one of the persistent and challenging problem to extract the reliable features. Dictionary based learning technique has given significant result, in contrast to conventional orientation field estimation methods by reconstructing orientation field to enhance the latent fingerprint image. Distorted orientation field is corrected using orientation patches of good quality fingerprint from region wise dictionary. This paper proposes a fresh idea to construct the dictionary by region wise to correct the orientation field in latent image. To verify the accuracy of enhanced image, a statistical observation has been done and got the promising results. This study concentrates on latent fingerprint preprocessing module towards reliable and efficient (optimal) Latent Fingerprint Identification.

show abstract

“…Unlike existing works using plain convolutional neural network [21,22] or sliding window [18,3] to process each patch with fixed size and stride, we use a deeper residual learning based network with more pooling layers to scale down the region patch. Specifically, we get the output after the 2 nd , 3 rd , and 4 th pooling layer to feed to an ASPP network [2] with corresponding rates for multiscale segmentation.…”

Section: Segmentation and Orientation Feature Sharingmentioning

confidence: 99%

“…Comparison of different methods for minutiae extraction on FVC 2004 and NIST SD27 datasets. Note that [18,21] reported their results only on subsets of FVC 2004 and NIST SD27 as mentioned in Table 1. " " means the authors neither provided these results in their paper nor made their code available.…”

Section: Datasetsmentioning

confidence: 99%

Robust Minutiae Extractor: Integrating Deep Networks and Fingerprint Domain Knowledge

Nguyen

Cao

Jain

2018

2018 International Conference on Biometrics (ICB)

View full text Add to dashboard Cite

We propose a fully automatic minutiae extractor, called MinutiaeNet, based on deep neural networks with compact feature representation for fast comparison of minutiae sets. Specifically, first a network, called CoarseNet, estimates the minutiae score map and minutiae orientation based on convolutional neural network and fingerprint domain knowledge (enhanced image, orientation field, and segmentation map). Subsequently, another network, called FineNet, refines the candidate minutiae locations based on score map. We demonstrate the effectiveness of using the fingerprint domain knowledge together with the deep networks. Experimental results on both latent (NIST SD27) and plain (FVC 2004) public domain fingerprint datasets provide comprehensive empirical support for the merits of our method. Further, our method finds minutiae sets that are better in terms of precision and recall in comparison with state-of-the-art on these two datasets. Given the lack of annotated fingerprint datasets with minutiae ground truth, the proposed approach to robust minutiae detection will be useful to train network-based fingerprint matching algorithms as well as for evaluating fingerprint individuality at scale. MinutiaeNet is implemented in Tensorflow: https://github.com/luannd/MinutiaeNet

show abstract

On latent fingerprint minutiae extraction using stacked denoising sparse AutoEncoders

Cited by 36 publications

References 14 publications

Multisensor Optical and Latent Fingerprint Database

Multisensor Optical and Latent Fingerprint Database

Latent Fingerprint preprocessing: Orientation field correction using region wise dictionary

Robust Minutiae Extractor: Integrating Deep Networks and Fingerprint Domain Knowledge

Contact Info

Product

Resources

About