Limits...
Two-level evaluation on sensor interoperability of features in fingerprint image segmentation.

Yang G, Li Y, Yin Y, Li YS - Sensors (Basel) (2012)

Bottom Line: Features used in fingerprint segmentation significantly affect the segmentation performance.The proposed method is performed on a number of fingerprint databases which are obtained from various sensors.Experimental results show that the proposed method can effectively evaluate the sensor interoperability of features, and the features with good evaluation results acquire better segmentation accuracies of images originating from different sensors.

View Article: PubMed Central - PubMed

Affiliation: School of Computer Science and Technology, Shandong University, Jinan 250101, Shandong, China. gpyang@sdu.edu.cn

ABSTRACT
Features used in fingerprint segmentation significantly affect the segmentation performance. Various features exhibit different discriminating abilities on fingerprint images derived from different sensors. One feature which has better discriminating ability on images derived from a certain sensor may not adapt to segment images derived from other sensors. This degrades the segmentation performance. This paper empirically analyzes the sensor interoperability problem of segmentation feature, which refers to the feature's ability to adapt to the raw fingerprints captured by different sensors. To address this issue, this paper presents a two-level feature evaluation method, including the first level feature evaluation based on segmentation error rate and the second level feature evaluation based on decision tree. The proposed method is performed on a number of fingerprint databases which are obtained from various sensors. Experimental results show that the proposed method can effectively evaluate the sensor interoperability of features, and the features with good evaluation results acquire better segmentation accuracies of images originating from different sensors.

No MeSH data available.


Features’ histograms of 10 fingerprints in FVC2000 DB2.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3376633&req=5

f1-sensors-12-03186: Features’ histograms of 10 fingerprints in FVC2000 DB2.

Mentions: We first investigate the histograms of fingerprints from same sub-database. A sample result is given in Figure 1 which shows the histograms of mean, variance, contrast, gradient of 10 fingerprints in FVC2000 DB2. We can see that under the view of mean (variance, contrast or gradient), the foreground and background blocks are statistically separable. Actually, the foreground and background blocks of fingerprints from same sub-database can be separated by most segmentation features, and thus for most segmentation features, they have good discriminating abilities and can achieve favorable segmentation performance in images derived from the same sensor.


Two-level evaluation on sensor interoperability of features in fingerprint image segmentation.

Yang G, Li Y, Yin Y, Li YS - Sensors (Basel) (2012)

Features’ histograms of 10 fingerprints in FVC2000 DB2.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3376633&req=5

f1-sensors-12-03186: Features’ histograms of 10 fingerprints in FVC2000 DB2.
Mentions: We first investigate the histograms of fingerprints from same sub-database. A sample result is given in Figure 1 which shows the histograms of mean, variance, contrast, gradient of 10 fingerprints in FVC2000 DB2. We can see that under the view of mean (variance, contrast or gradient), the foreground and background blocks are statistically separable. Actually, the foreground and background blocks of fingerprints from same sub-database can be separated by most segmentation features, and thus for most segmentation features, they have good discriminating abilities and can achieve favorable segmentation performance in images derived from the same sensor.

Bottom Line: Features used in fingerprint segmentation significantly affect the segmentation performance.The proposed method is performed on a number of fingerprint databases which are obtained from various sensors.Experimental results show that the proposed method can effectively evaluate the sensor interoperability of features, and the features with good evaluation results acquire better segmentation accuracies of images originating from different sensors.

View Article: PubMed Central - PubMed

Affiliation: School of Computer Science and Technology, Shandong University, Jinan 250101, Shandong, China. gpyang@sdu.edu.cn

ABSTRACT
Features used in fingerprint segmentation significantly affect the segmentation performance. Various features exhibit different discriminating abilities on fingerprint images derived from different sensors. One feature which has better discriminating ability on images derived from a certain sensor may not adapt to segment images derived from other sensors. This degrades the segmentation performance. This paper empirically analyzes the sensor interoperability problem of segmentation feature, which refers to the feature's ability to adapt to the raw fingerprints captured by different sensors. To address this issue, this paper presents a two-level feature evaluation method, including the first level feature evaluation based on segmentation error rate and the second level feature evaluation based on decision tree. The proposed method is performed on a number of fingerprint databases which are obtained from various sensors. Experimental results show that the proposed method can effectively evaluate the sensor interoperability of features, and the features with good evaluation results acquire better segmentation accuracies of images originating from different sensors.

No MeSH data available.