A model for handwriting recognition using wavelet function and genetic algorithm

العناوين الأخرى

نموذج لتمييز الكتابة اليدوية باستخدام الدالة الموجية و خوارزمية التوريث

مقدم أطروحة جامعية

al-Alusi, Ali Ibrahim

مشرف أطروحة جامعية

al-Shammari, Husayn Hadi Uwayyid

أعضاء اللجنة

al-Jarrah, Muzaffar Munir
al-Hammami, Ala Husayn

الجامعة

جامعة الشرق الأوسط

الكلية

كلية تكنولوجيا المعلومات

القسم الأكاديمي

قسم نظم المعلومات الحاسوبية

دولة الجامعة

الأردن

الدرجة العلمية

ماجستير

تاريخ الدرجة العلمية

2013

الملخص الإنجليزي

One of the main problems of pattern recognition is focused on character recognition.

There are many researches involved to find better way, to increase the accuracy of matched characters and digits in different languages, besides the techniques and methods used in pattern recognition are variety in different stages of character recognition processes.

This thesis presents the design and implementation of handwritten text recognition model using a hybrid technique, which consists of the Mayer wavelet function and genetic algorithms, to recognize the handwriting characters.

The model design consists of many parts, these are; image loading, selection part of an interesting phrases, cropping and separating each character alone, applying median and thinning filter to enhance an image, resizing an image, feature vector by extraction features of each character based on Meyer wavelet, and finally in the recognition stage applying a Genetic algorithm.

This thesis is concerned with the Pattern recognition of (isolated English characters) using wavelet and genetic algorithm to satisfy a successful recognition operation.

The unknown character is read out from an image and from many operations to manipulate it and extract its features, to compare these features with saved chromosome database features.

This thesis we have selected the Meyer wavelet transformation to extract features handwriting characters.

In extraction procedure, image, which maybe attacked, is pre-filtered by combination of median and thinning filters to increase distinction information.

The extracted result for each character using the Mayer wavelet is represented as a chromosome of (3422) bits.

The model is implemented and tested by using Matlab2012.

التخصصات الرئيسية

تكنولوجيا المعلومات وعلم الحاسوب

عدد الصفحات

77

قائمة المحتويات

• APA
• MLA
• AMA

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-694263