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!

Handwriting Recognition of Arabic Letters Using Pattern Recognition Approaches

BROWSE_DETAIL_CREATION_DATE: 18-09-2017

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BROWSE_DETAIL_PUBLISH_STATE: Unpublished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,

BROWSE_DETAIL_CREATORS: Douma, Aisha Ahsein Mohamed (Author),

BROWSE_DETAIL_CONTRIBUTERS: Şengül, Gökhan (Advisor),

BROWSE_DETAIL_TAB_KEYWORDS

Arabic Alphabet, Artificial Neural Network, Local Binary Pattern,Histogram of Oriented Gradient, Gray Level Co-occurrence Matrix


BROWSE_DETAIL_TAB_ABSTRACT

Handwriting recognition is the process of detecting and converting letters writtenby humans into machine-encoded forms to improve the interaction betweenhumans and machines in many fields like office automation, banking andbusiness. In this thesis, we apply four recognition methods for Arabic lettersrecognition, namely gray level co-occurrence matrix (GLCM), local binary patternrecognition (LBP), artificial neural network (ANN) and histogram of orientedgradients (HOG). The three methods, GLCM, LBP and HOG are used for featureextraction. In ANN we use the intensity values of pixels for input of the neuralnetwork. For classification the K-Nearest Neighbor (KNN) is used for the LBP,GLCM and HOG. To evaluate the results of each method, Confusion Matrix (CM)technique is used. The results show that HOG have the highest accuracy, whilethe least accuracy is achieved by GLCM.


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: 18
    • TEXT_ONLINE_STATS_TOTALONLINEUSER: 0
    • TEXT_STATS_TOTAL: 18

LINK_STATS