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!

Neural Network Based Feature Extraction for Handwritten Digit Recognition

BROWSE_DETAIL_CREATION_DATE: 05-04-2017

BROWSE_DETAIL_IDENTIFIER_SECTION

BROWSE_DETAIL_TYPE: Thesis

BROWSE_DETAIL_SUB_TYPE: EngD

BROWSE_DETAIL_PUBLISH_STATE: Unpublished

BROWSE_DETAIL_FORMAT: PDF Document

BROWSE_DETAIL_LANG: English

BROWSE_DETAIL_SUBJECTS: TECHNOLOGY, Communication of technical information, Electrical engineering. Electronics. Nuclear engineering,

BROWSE_DETAIL_CREATORS: Günler, Mine Altınay (Author),

BROWSE_DETAIL_CONTRIBUTERS: Tora, Hakan (Advisor),

BROWSE_DETAIL_TAB_KEYWORDS

Hidden layer output vectors, principle component analysis, neural network, support vector machines, Euclidean distance classifier and multilayer perceptron


BROWSE_DETAIL_TAB_ABSTRACT

In this dissertation, it is proposed that hidden layer output weights of semi-trained neural network to be used as feature vectors. In pattern recognition neural network is a training algorithm which provides classification. In this thesis in addition to this fact, it has been shown that semi-trained neural network can be used as a tool to extract hidden layer output vectors that are used as features of the image. The system is mainly composed of three steps: preprocessor, feature extractor, and classifier. Only the classifier layer differs for each experiment, the other two layers are used as default for all experiments. Support vector machine, neural network, and Euclidean distance classifiers are utilized. The experiments were conducted on MNIST and USPS benchmark datasets to evaluate the performance of the proposed approach.


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: 2417
  • TEXT_ONLINE_STATS
    • TEXT_ONLINE_STATS_TOTALONLINEVISITOR: 13
    • TEXT_ONLINE_STATS_TOTALONLINEUSER: 0
    • TEXT_STATS_TOTAL: 13

LINK_STATS