Enhanced method for handwritten signature recognition

العناوين الأخرى

طريقة محسنة لتمييز التوقيع اليدوي

مشرف أطروحة جامعية

al-Ani, Muzhir Shaban

أعضاء اللجنة

al-Bahadili, Husayn
Kakish, Malik

الجامعة

جامعة عمان العربية

الكلية

كلية العلوم الحاسوبية و المعلوماتية

القسم الأكاديمي

قسم علم الحاسوب

دولة الجامعة

الأردن

الدرجة العلمية

ماجستير

تاريخ الدرجة العلمية

2011

الملخص الإنجليزي

Electronic biometric systems became available in last few decades.

Handwriting signature recognition as a behavioral biometric plays an important role in our life, because of its widespread acceptance among people, especially in security transactions.

In this thesis, an enhanced method for handwritten signature recognition has been developed and implemented in a comprehensive system for handwritten signature recognition.

The system includes many elements that are integrated to generate the entire system.

Database of 1000 Arabic and English signatures has been introduced.

The system has been separated into two important phases: training and testing. In the training phase, preprocessing process is applied firstly for signatures enhancement, then feature extraction process is applied using discrete wavelet transform (DWT) and vectors fusion.

In enrollment process, after support vector machine (SVM) is trained, an individual template is stored in the database.

In the testing phase, two recognition processes have been introduced: verification and identification.

In each process, SVM classifier makes a decision for classification. The system indicates good results for verification and identification compared to other approaches

التخصصات الرئيسية

الهندسة الكهربائية

الموضوعات

• الكتابة
• معالجة البيانات

عدد الصفحات

63

قائمة المحتويات

• APA
• MLA
• AMA

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-528949