A corner strength based Fingerprint segmentation algorithm with dynamic thresholding

Baig, Asim; Bouridane, Ahmed; Kurugöllü, Fatih

doi:10.1109/icpr.2008.4761871

Cited by 8 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some pixel-wise¯ngerprint segmentation methods compute only one feature at every pixel location, and threshold this feature to obtain the segmentation. 1,20,22,28 Typically, the features computed are limited to¯ltering operators, or combination thereof, to limit the computational complexity. Obviously, the main drawback of using only one feature is that the results are directly tied to the expressiveness of the feature, and given the ad-hoc selection or construction of features in the literature, the results have tended to be unsatisfactory.…”

Section: Background and Previous Workmentioning

confidence: 99%

Fingerprint Image Segmentation Using Data Manifold Characteristic Features

Paiva

Taşdizen

2012

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

Automatic¯ngerprint identi¯cation systems (AFIS) have been studied extensively and are widely used for biometric identi¯cation. Given its importance, many well-engineered methods have been developed for the di®erent stages that encompass those systems. The¯rst stage of any such system is the segmentation of the actual¯ngerprint region from the background. This is typically achieved by classifying pixels, or blocks of pixels, based on a set of features. In this paper, we describe novel features for¯ngerprint segmentation that express the underlying manifold topology associated with image patches in a local neighborhood. It is shown that ngerprint patches seen in a high-dimensional space form a simple and highly regular circular manifold. The characterization of the manifold topology suggests a set of optimal features that characterize the local properties of the¯ngerprint. Thus,¯ngerprint segmentation can be formulated as a classi¯cation problem based on the deviation from the expected topology. This leads to features that are more robust to changes in contrast than mean, variance and coherence. The superior performance of the proposed features for¯ngerprint segmentation is shown in the eight datasets from the 2002 and 2004 Fingerprint Veri¯cation Competitions.

show abstract

Section: Background and Previous Workmentioning

confidence: 99%

Fingerprint Image Segmentation Using Data Manifold Characteristic Features

Paiva

Taşdizen

2012

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…This feature extractor provides a stable set of minutiae points even in noisy input images. † Feature extractor 2 (FE2): A simple binarisation and thinning-based minutia extractor consisting of a segmentation stage [19], an enhancement stage utilising high-boosting filtering approach, a binarisation stage using Niblack approach [20], an eight-connected minutiae detector and a line tracing approach to remove spurious minutiae [21]. This feature extractors providing spurious minutiae in noisy images but has the same performance as the first feature extractor for good quality images.…”

Section: Feature Extractorsmentioning

confidence: 99%

“…The code for this feature extractor was provided by the Centre of Unified Biometrics and Sensors (CUBS) at the University of New York at Buffalo. This feature extractor provides a stable set of minutiae points even in noisy input images. Feature extractor 2 (FE 2 ): A simple binarisation and thinning‐based minutia extractor consisting of a segmentation stage [19], an enhancement stage utilising high‐boosting filtering approach, a binarisation stage using Niblack approach [20], an eight‐connected minutiae detector and a line tracing approach to remove spurious minutiae [21]. This feature extractors providing spurious minutiae in noisy images but has the same performance as the first feature extractor for good quality images. It is important to point out here that, as per the second reason given above for the selection of fingerprint modality as part of this test bed, FE2 was implemented.…”

Section: Experimental Test Bedmentioning

confidence: 99%

Cascaded multimodal biometric recognition framework

et al. 2014

View full text Add to dashboard Cite

A practically viable multi-biometric recognition system should not only be stable, robust and accurate but should also adhere to real-time processing speed and memory constraints. This study proposes a cascaded classifier-based framework for use in biometric recognition systems. The proposed framework utilises a set of weak classifiers to reduce the enrolled users' dataset to a small list of candidate users. This list is then used by a strong classifier set as the final stage of the cascade to formulate the decision. At each stage, the candidate list is generated by a Mahalanobis distance-based match score quality measure. One of the key features of the authors framework is that each classifier in the ensemble can be designed to use a different modality thus providing the advantages of a truly multimodal biometric recognition system. In addition, it is one of the first truly multimodal cascaded classifier-based approaches for biometric recognition. The performance of the proposed system is evaluated both for single and multimodalities to demonstrate the effectiveness of the approach.

show abstract

“…The paper proposes one segmentation method and one filtering technique in the gradient domain in order to first segment the content (images and text) from noise and background and then to reconstruct the segmented content on a clean background. Extending an earlier work [26], a multistage filtering algorithm based on the gradient strengths is proposed to perform a robust segmentation. A clean image is then reconstructed from the segmented gradients onto a white background.…”

Section: Introductionmentioning

confidence: 99%