Palmprint Recognition Based on Local DCT Feature Extraction

Choge, H. Kipsang; Oyama, Tadahiro; Karungaru, Stephen; Tsuge, Shin; Fukumi, Minoru

doi:10.1007/978-3-642-10677-4_73

Cited by 5 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the proposed system is compared with the best known systems proposed in [6,7,14,16] for all three databases. The systems in [6,7] have used 2D-DCT to extract palmprint features.…”

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

“…The systems in [6,7] have used 2D-DCT to extract palmprint features. It is reported that systems in [6] and [7] are evaluated using 500 images and 198 images of PolyU database respectively. However, experiments for evaluating the performance of the systems in [6,7,14,16] are carried out on the same set of extracted and enhanced palmprint images used for the proposed system.…”

Section: Resultsmentioning

confidence: 99%

“…Furthermore, palmprint also serves as a reliable human identifier because the print patterns are found to be unique even in mono-zygotic twins [9]. There exist palmprint recognition systems which are based on Gabor filter [16], Ordinal code [14], Local binary pattern [15], 2D-DCT [6,7]. The system in [6] retains less than 50% of 2D-DCT coefficients of palmprint image as its features and it has used partial PolyU database.…”

Section: Introductionmentioning

confidence: 99%

“…There exist palmprint recognition systems which are based on Gabor filter [16], Ordinal code [14], Local binary pattern [15], 2D-DCT [6,7]. The system in [6] retains less than 50% of 2D-DCT coefficients of palmprint image as its features and it has used partial PolyU database. For the identification mode, this system performs with CRR of 99%.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

An Efficient Palmprint Based Recognition System Using 1D-DCT Features

Badrinath

Tiwari

Gupta

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper makes use of one dimensional Discrete Cosine Transform (DCT) to design an efficient palmprint based recognition system. It extracts the palmprint from the hand images which are acquired using a flat bed scanner at low resolution. It uses new techniques to correct the non-uniform brightness of the palmprint and to extract features using difference of 1D-DCT coefficients of overlapping rectangular blocks of variable size and variable orientation. Features of two palmprints are matched using Hamming distance while nearest neighbor approach is used for classification. The system has been tested on three databases, viz. IITK, CASIA and PolyU databases and is found to be better than the well known palmprint systems.

show abstract