Finger image quality assessment features – definitions and evaluation

Olsen, Martin Aastrup; Šmida, Vladimír; Busch, Christoph

doi:10.1049/iet-bmt.2014.0055

Cited by 49 publications

(22 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, features which influence these quality classes must be considered as a quality predictor of fingerprint images. Hence, two features namely, uniformity and contrast from [17] and four features namely, radial power spectrum (RPS), ridge valley thickness uniformity (RVU), gabor and gabor-shen from [18] are considered in the candidate feature vector for quality prediction of fingerprint images. This feature vector is fed as input to feature selection unit to select most discriminative feature subset for quality clustering of fingerprint images.…”

Section: Feature Extractionmentioning

confidence: 99%

“…• The proposed FQA method incorporates a new set of features namely, moisture, mean, variance, RVAU and RLC with the other existing features uniformity and contrast from NFIQ 2.0 [17] and RPS, RVU, Gabor and Gabor-Shen from Olsen et al [18]. These eleven features are used to select most influential feature set which affect the fingerprint image quality.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Two-stage quality adaptive fingerprint image enhancement using Fuzzy C-means clustering based fingerprint quality analysis

Sharma

Dey

2019

Image and Vision Computing

View full text Add to dashboard Cite

Fingerprint recognition techniques are immensely dependent on quality of the fingerprint images. To improve the performance of recognition algorithm for poor quality images an efficient enhancement algorithm should be designed. Performance improvement of recognition algorithm will be more if enhancement process is adaptive to the fingerprint quality (wet, dry or normal). In this paper, a quality adaptive fingerprint enhancement algorithm is proposed. The proposed fingerprint quality assessment algorithm clusters the fingerprint images in appropriate quality class of dry, wet, normal dry, normal wet and good quality using fuzzy c-means technique. It considers seven features namely, mean, moisture, variance, uniformity, contrast, ridge valley area uniformity and ridge valley uniformity into account for clustering the fingerprint images in appropriate quality class. Fingerprint images of each quality class undergo through a two-stage fingerprint quality enhancement process. A quality adaptive preprocessing method is used as front-end before enhancing the fingerprint images with Gabor, short term Fourier transform and oriented diffusion filtering based enhancement techniques. Experimental results show improvement in the verification results for FVC2004 datasets. Significant improvement in equal error rate is observed while using quality adaptive preprocessing based approaches in comparison to the current stateof-the-art enhancement techniques.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Two-stage quality adaptive fingerprint image enhancement using Fuzzy C-means clustering based fingerprint quality analysis

Sharma

Dey

2019

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…Fingerprints are unique in nature. The property of uniqueness of fingerprints is determined by the characteristics of ridges and their relationships [27] [28]. Ridges are collection of patterns present on the surface of fingertips.…”

Section: B What Is the Need Of Fingerprint Image Enhancement?mentioning

confidence: 99%

“…Ridges are collection of patterns present on the surface of fingertips. More than 100 ridge characteristics have been identified including ridge ending, island and short ridge but the two most eminent characteristics are: ridge ending and ridge bifurcation [28] (also called as minutiae) as presented in fig 4.…”

Section: B What Is the Need Of Fingerprint Image Enhancement?mentioning

confidence: 99%

Filters to Dictionary based Enhancement Techniques for Latent Fingerprints Matchingc

Jindal¹

2018

IJRASET

View full text Add to dashboard Cite

Latent fingerprints are the finger skin impressions in a groove and ridge pattern left when fingertips come in contact with any surface. In forensics investigation, latent fingerprints plays as principal evidence to identify and convict criminals. Due to the presence of overlapping noisy patterns and complex ridge structure, they are usually unclear and of poor quality. The discipline of latent fingerprint detection has gain attention of many researchers over the years and many advances have been made but it is still challenging to accomplish the task by offering a quick, reliable and accurate latent fingerprint detection system. The presence of spoiled minutiae information, ridge and overlapping patterns make the task more complicated. The latent fingerprints do not serve any purpose before the enhancement and reconstruction of the ridge patterns, minutiae information and their quality. Prior to latent fingerprint detection and feature extraction, latent fingerprint enhancement is absolutely requisite to improve the quality for accurate fingerprint detection. This paper presents an analysis of various latent fingerprint enhancement techniques by comparing the work of numerous researchers. The paper sheds some light on the issues and challenges in the process of latent fingerprint detection. In addition, the paper also presents various datasets available for latent fingerprint detection.

show abstract

“…those specified in ISO/IEC 29794-4 [13] and those which are candidates considered for NFIQ 2.0 [14], the successor of NIST Finger Image Quality (NFIQ) [15] quantify sample x quality q via image analysis as q = QMA(x).…”

Section: Fingerprint Sample Qualitymentioning

confidence: 99%

Fingerprint skin moisture impact on biometric performance

Olsen

Dusio

Busch

2015

3rd International Workshop on Biometrics and Forensics (IWBF 2015)

Self Cite

View full text Add to dashboard Cite

Dry or wet fingers have an impact on biometric performance and the measurement of skin characteristics is important for actionable quality. We collected a ground truth fingerprint skin moisture dataset containing 6600 samples from 33 subjects using 5 optical sensors, two claimed to work well in extreme skin moisture conditions. Controlling conditions by applying cream, alcohol and water we performed objective measurements of skin moisture prior to each fingerprint capture. Analyzing the relationship between measured moisture and biometric performance across five sensors and comparison scores from 3 commercial providers confirms claims to resistance to excessive moisture. Results indicate that sensors resistant to excessive moisture perform worse on dry fingerprints than sensors not resistant to excessive moisture. The collected dataset is made available as an in-house dataset.Index Termsfingerprint, dataset, biometric performance, fingerprint image quality 978-1-4799-8105-2/15/$31.00 c 2015 IEEE

show abstract

Finger image quality assessment features – definitions and evaluation

Cited by 49 publications

References 22 publications

Two-stage quality adaptive fingerprint image enhancement using Fuzzy C-means clustering based fingerprint quality analysis

Two-stage quality adaptive fingerprint image enhancement using Fuzzy C-means clustering based fingerprint quality analysis

Filters to Dictionary based Enhancement Techniques for Latent Fingerprints Matchingc

Fingerprint skin moisture impact on biometric performance

Contact Info

Product

Resources

About