Adaptive latent fingerprint segmentation using feature selection and random decision forest classification

Sankaran, Anush; Jain, Aayush; Vashisth, Tarun; Vatsa, Mayank; Singh, Richa

doi:10.1016/j.inffus.2016.05.002

Cited by 54 publications

(24 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modified RELIEF formulation [8] was proposed for segmenting latent finger prints to distinguish between ridge and non-ridge patterns. It performed the feature selection and classification using Random Decision Forest(RDF).RDF used repetitive random sub-sampling strategy to provide strong and faster results for overlapping features SRF method was proposed for feature subspace selection for high dimensional data [9].…”

Section: Literature Surveymentioning

confidence: 99%

Machine Learning Models for Relevant Feature Identification and Classification of Thyroid Data

Nandhinidevi*,

Poorani,

Brindha

2020

IJITEE

View full text Add to dashboard Cite

Inappropriate creation of thyroid glands turn into prime subject of concern amongst Indian women. The two key chaos of thyroid which ought to be taken care at the earliest are hypothyroidism and hyperthyroidism. The improper secretion of thyroid may leads to obesity, fertility related problems, feeling depressed, etc,. Most of the thyroid problems can be managed if it has been properly treated. In recent years a number of models have been developed to investigate the thyroid-disorder. The laboratory tests are conducted to find the levels of the hormones and some of the physical examinations are used to identify the presences of thyroid. These examinations and test results are taken as the feature for developing the model. The feature importance can promote the performance of ML algorithms. The core intention of this study is to improve the classification performance by identifying the relevant features before classification. In this work, random-forest model is considered for identifying the important features and KNN algorithm is implemented for multiclass-classification to envisage the kind of thyroid chaos. Applying KNN after the feature selection improves the prediction accuracy. The developed model can be used to predict the presence of thyroid so that it can be treated accordingly.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Machine Learning Models for Relevant Feature Identification and Classification of Thyroid Data

Nandhinidevi*,

Poorani,

Brindha

2020

IJITEE

View full text Add to dashboard Cite

show abstract

“…The average number of minutiae in the latents was 13 and that of tenprints was 125. There exists automated algorithms to perform segmentation for latent fingerprints [35], but in this work, we relied on the manually extracted minutiae alone.…”

Section: Databasementioning

confidence: 99%

Improving automated latent fingerprint identification using extended minutia types

et al. 2019

View full text Add to dashboard Cite

Latent fingerprints are usually processed with Automated Fingerprint Identification Systems (AFIS) by law enforcement agencies to narrow down possible suspects from a criminal database. AFIS do not commonly use all discriminatory features available in fingerprints but typically use only some types of features automatically extracted by a feature extraction algorithm. In this work, we explore ways to improve rank identification accuracies of AFIS when only a partial latent fingerprint is available. Towards solving this challenge, we propose a method that exploits extended fingerprint features (unusual/rare minutiae) not commonly considered in AFIS. This new method can be combined with any existing minutiae-based matcher. We first compute a similarity score based on least squares between latent and tenprint minutiae points, with rare minutiae features as reference points. Then the similarity score of the reference minutiae-based matcher at hand is modified based on a fitting error from the least square similarity stage. We use a realistic forensic fingerprint casework database in our experiments which contains rare minutiae features obtained from Guardia Civil, the Spanish law enforcement agency. Experiments are conducted using three * Corresponding author Email addresses: ram.krish@dcu.ie (Ram P. Krish), julian.fierrez@uam.es (Julian Fierrez), daniel.ramos@uam.es (Daniel Ramos), feralo@hh.se (Fernando Alonso-Fernandez), josef.bigun@hh.se (Josef Bigun) 2018. This manuscript version is made available under the CC-BY-NC-ND 4.0 license. http://creativecommons.org/licenses/by-nc-nd/4.0/ The final version is available online at: https://doi.minutiae-based matchers as a reference, namely: NIST-Bozorth3, VeriFinger-SDK and MCC-SDK. We report significant improvements in the rank identification accuracies when these minutiae matchers are augmented with our proposed algorithm based on rare minutiae features.

show abstract

“…The foreground consists of the fingerprint and the background consists of the noise or unwanted region. A few methods on latent fingerprint segmentation [1,2,3,4,5,6,7,8,10] have been purposed. In Zhang et al [5], the author used the Adaptive Total Variation Model for fingerprint image decomposition and feature selection of the multiscale image.…”

Section: Literature Reviewmentioning

confidence: 99%

“…For segmentation, it requires accurate confidence measures. Vatsa et al [2], purposed Adaptive latent fingerprint segmentation using feature selection and random decision forest classification. In this paper, the author used a machine learning algorithm, feature selection technique and novel SIVV based metric for latent fingerprint segmentation.…”

Section: Literature Reviewmentioning

confidence: 99%

Segmentation of Latent Fingerprint u sing Neural Network

Chaudhary*,

Dimri,

Singh

2019

IJEAT

View full text Add to dashboard Cite

Latent fingerprints are the fingerprints that are left by the criminal unintentionally on the surface of the crime scene. The qualities of the latent fingerprints are very poor due to the overlapping patterns and structured noises. Latent fingerprint segmentation is a difficult task due to low visibility, structured noise, and complex structure. In this paper, a fusion of morphological and neural network approach is purposed for latent fingerprint segmentation. This method automatically segments the fingerprints and non-fingerprints patterns without human intervention. The morphological method is used for segmentation of the fingerprint region. Fingerprint region then divides into y*y blocks and extracts the features of each block and uses them as an input of NN to classify the blocks into fingerprint and non-fingerprint blocks. We are using the IIIT-D database and the shows that this model batters then the existing model.

show abstract

Adaptive latent fingerprint segmentation using feature selection and random decision forest classification

Cited by 54 publications

References 24 publications

Machine Learning Models for Relevant Feature Identification and Classification of Thyroid Data

Machine Learning Models for Relevant Feature Identification and Classification of Thyroid Data

Improving automated latent fingerprint identification using extended minutia types

Segmentation of Latent Fingerprint u sing Neural Network

Contact Info

Product

Resources

About