Zagazig University Digital Repository
Home
Thesis & Publications
All Contents
Publications
Thesis
Graduation Projects
Research Area
Research Area Reports
Search by Research Area
Universities Thesis
ACADEMIC Links
ACADEMIC RESEARCH
Zagazig University Authors
Africa Research Statistics
Google Scholar
Research Gate
Researcher ID
CrossRef
Study Artificial Neural Networks Algorithms for Solving the Nonlinear Pattern Classification Problems
Faculty
Science
Year:
2011
Type of Publication:
Theses
Pages:
129
Authors:
Qamar Abd Elmotaleb Al Demerdash Awad
BibID
11301302
Keywords :
Networks (Geodesy
Abstract:
The main object of this thesis is Ato study artificial neural networks algorithms for solving the nonlinear pattern classification problems. This thesis consists of an introduction, four chapters, and three appendices . It is organizedas follows:In chapter 1, we introduced the basic concepts of the pattern classification and recognition problems. We alsoA introduced the traditional and advanced pattern recognition methods. Finally, we introduced the invariant feature extraction methods by using tIn Chapter 2, we have been used a supervised backprobagation learning process of neural network to recognize a set of patterns throughout determines their invariant features. Invariant features of the pattern can be determined by the seven invariant momenSo the feature extractor of windowed areas of images is a very good than traditional method in case of huge size of images to reduce the time of calculations. We also used the invariant Fourier descriptor FD and its Laplace transform of the edge detection
PDF
جامعة المنصورة
جامعة الاسكندرية
جامعة القاهرة
جامعة سوهاج
جامعة الفيوم
جامعة بنها
جامعة دمياط
جامعة بورسعيد
جامعة حلوان
جامعة السويس
شراقوة
جامعة المنيا
جامعة دمنهور
جامعة المنوفية
جامعة أسوان
جامعة جنوب الوادى
جامعة قناة السويس
جامعة عين شمس
جامعة أسيوط
جامعة كفر الشيخ
جامعة السادات
جامعة طنطا
جامعة بنى سويف