1.

Record Nr.

UNINA9910709935903321

Titolo

Slap fingerprint segmentation evaluation 2004 analysis report / / Bradford Ulery [and others]

Pubbl/distr/stampa

[Gaithersburg, MD] : , : U.S. Dept. of Commerce, National Institute of Standards and Technology, , [2005]

Descrizione fisica

1 online resource (8 pages) : illustrations

Collana

NISTIR ; ; 7209

Altri autori (Persone)

HicklinR. Austin

IndovinaMichael

KwongKayee

UleryBradford

WatsonC. I (Craig I.)

Soggetti

Fingerprints - Identification - Automation

Image processing - Testing

Lingua di pubblicazione

Inglese

Formato

Materiale a stampa

Livello bibliografico

Monografia

Note generali

"8 March 2005."

Contributed record: Metadata reviewed, not verified. Some fields updated by batch processes.

Title from page 1, viewed March 13, 2007.

Sommario/riassunto

The Slap Fingerprint Segmentation Evaluation 2004 (SlapSeg04) was conducted to assess the accuracy of algorithms used to segment slap fingerprint images into individual fingerprint images. Thirteen slap segmentation applications from ten different organizations were evaluated using data from seven government sources. The source of data, the segmentation software used, and the scoring criteria used were each found to have a significant impact on accuracy. The most accurate segmenters produced at least three highly matchable fingers and correctly identified finger positions in from 93% to over 99% of the slap images, depending on the data source. The data source had a much greater effect on success rate than whether the images were collected using livescan devices or paper. Most segmenters achieved comparable accuracies on the better quality data, but there were



significant differences among segmenters when processing poor quality data. Some segmenters are capable of identifying many, but not all, problem slaps: failure rates could be cut substantially by allowing some of the slaps to be recaptured or rejected.