Bu kaydın yasal hükümlere uygun olmadığını düşünüyorsanız lütfen sayfa sonundaki Hata Bildir bağlantısını takip ederek bildirimde bulununuz. Kayıtlar ilgili üniversite yöneticileri tarafından eklenmektedir. Nadiren de olsa kayıtlarla ilgili hatalar oluşabilmektedir. MİTOS internet üzerindeki herhangi bir ödev sitesi değildir!

Palm Print Identification

BROWSE_DETAIL_CREATION_DATE: 19-06-2018

BROWSE_DETAIL_IDENTIFIER_SECTION

BROWSE_DETAIL_TYPE: Thesis

BROWSE_DETAIL_SUB_TYPE: Masters

BROWSE_DETAIL_PUBLISH_STATE: Unpublished

BROWSE_DETAIL_FORMAT: PDF Document

BROWSE_DETAIL_LANG: English

BROWSE_DETAIL_SUBJECTS: TECHNOLOGY, Electrical engineering. Electronics. Nuclear engineering,

BROWSE_DETAIL_CREATORS: Jebriel, Belal Ali Mesbah (Author),

BROWSE_DETAIL_CONTRIBUTERS: Tora, Hakan (Research Responsible),

BROWSE_DETAIL_TAB_KEYWORDS

palm print identification, local binary pattern (LBP), histogram oforiented gradients (HOG), neural networks, support vector machine (SVM).


BROWSE_DETAIL_TAB_ABSTRACT

This thesis explores the appropriateness of identifying palm prints through a standarddatabase and a classifier. This study uses two sets of databases, CASIA and IIT,which contain left hand and right hand images. The features of the local binarypattern (LBP) and histogram of oriented gradients (HOG) are extracted from theimages by MATLAB. Training and testing sets are created from these features. Amultilayer neural network and support vector machines (SVM) with two separatekernels, linear and quadratic, are trained and tested on the selected databases. Thechosen features are empirically compared with one another. Better results have beenaccomplished in HOG for both classifiers. In addition, the performance of theclassifiers are evaluated. It has been observed that the neural network achieves betterresults than SVM for LBP features of both datasets. On the other hand, for HOGfeatures, they do not display many advantages over one another.


BROWSE_DETAIL_TAB_TOC



BROWSE_DETAIL_TAB_DESCRIPTION



BROWSE_DETAIL_TAB_RIGHTS



BROWSE_DETAIL_TAB_NOTES



BROWSE_DETAIL_TAB_REFERENCES


BROWSE_DETAIL_TAB_REFERENCED_BYS

BROWSE_DETAIL_GOTO_LIST

 

TEXT_STATS

  • TEXT_RECORD_STATS
    • TEXT_STATS_THIS_MONTH: 3
    • TEXT_STATS_TOTAL: 2444
  • TEXT_ONLINE_STATS
    • TEXT_ONLINE_STATS_TOTALONLINEVISITOR: 64
    • TEXT_ONLINE_STATS_TOTALONLINEUSER: 0
    • TEXT_STATS_TOTAL: 64

LINK_STATS