A Palmprint Classification Scheme using Heart Line Feature Extraction

Negi, Atul; Panigrahi, Bhawani Sankar; Prasad, Munaga V. N. K.; Das, Madhabananda

doi:10.1109/icit.2006.17

Cited by 4 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The classes 1345, 236, 346, 13456, 1236 and 2346 have broken heart lines for both the groups. Out of 500 images randomly selected from the database 498 images are correctly classified and only 2 images are misclassified that shows a classification accuracy of 99.6%.The accuracy rate is much improved than Negi et al [15] and Wang et al [14] because here the right hand images and left hand images are considered separately and accordingly alignment of heart line is considered to classify the palmprint database.…”

Section: Resultsmentioning

confidence: 97%

“…Thus, for left and right hand palmprint groups the number of categories is 128 (64+64). By following this methodology, the classification rate is much improved in comparison to Negi et al [15]. The accuracy of the system is also much improved than Negi et al and Wang et al as the right hand and left hand palms are considered separately and accordingly the alignment of the heart line is considered differently for both the groups.…”

Section: Related Workmentioning

confidence: 94%

“…In his approach the matching process may still have to search through 78.12% of the original database samples before finding a match. In another approach Negi et al divided the ROI into 8 groups and classified the groups into 257 categories [15]. They considered the alignment of the heart line in both hands to be same.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Classification of Palmprint Using Principal Line

Prasad

Kumar

Sharma

2009

Information Systems, Technology and Management

View full text Add to dashboard Cite

Abstract. In this paper, a new classification scheme for palmprint is proposed. Palmprint is one of the reliable physiological characteristics that can be used to authenticate an individual. Palmprint classification provides an important indexing mechanism in a very large palmprint database. Here, the palmprint database is initially categorized into two groups, right hand group and left hand group. Then, each group is further classified based on the distance traveled by principal line i.e. Heart Line During pre processing, a rectangular Region of Interest (ROI) in which only heart line is present, is extracted. Further, ROI is divided into 6 regions and depending upon the regions in which the heart line traverses the palmprint is classified accordingly. Consequently, our scheme allows 64 categories for each group forming a total number of 128 possible categories. The technique proposed in this paper includes only 15 such categories and it classifies not more than 20.96% of the images into a single category.

show abstract

Section: Resultsmentioning

confidence: 97%

Section: Related Workmentioning

confidence: 94%

See 1 more Smart Citation

Classification of Palmprint Using Principal Line

Prasad

Kumar

Sharma

2009

Information Systems, Technology and Management

View full text Add to dashboard Cite

show abstract

“…Mongkon et al [8] work classifies palm prints into six classes based on the characteristic of principal lines. Classification algorithm proposed by Atul negi et al [9] classifies palm prints into 257 categories based on heart line feature extracted from palm print images captured using a peg free scanner. Sobel gradient thresholds are used to extract heart line and images are classified based on the regions that the heart line traverses horizontally.…”

Section: Related Workmentioning

confidence: 99%

An efficient approach for classification of palmprint images using heart line features

Anitha¹,

Rao²

2015

2015 International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT)

View full text Add to dashboard Cite

Palm print is one of the important hand related biometrics characteristics with high user acceptance. A new classification approach using heart line feature of palm print is proposed in this paper. The hand image captured from digital camera is preprocessed to find palm print Region of interest (ROI). Gabor filters are applied on palm print ROI and line detection operation is proposed to extract heart line features. Then the palm print images are classified based on the shape feature of the heart line. Proposed classification approach categories palm print images into four categories. Testing of the proposed approach on the database collected at our institute shows that the identification accuracy of 94% is obtained. Palm print features are extracted by applying local binary descriptor on palm print ROI and matched with euclidean distance in the most potential palm print category and if necessary matching process continues orderly to less potential categories. Identification experiment results show that the proposed approach can reduce the number of templates considered for matching from 100% as in the case of conventional approaches to a range of 30% to 60% while maintaining the same accuracy as the that of conventional approaches.

show abstract