Cash Currencies Recognition Using KNN Classifier

العناوين الأخرى

تمييز العملات النقدية باستخدام مميز (KNN)‎

مقدم أطروحة جامعية

al-Khayyat, Abrar

مشرف أطروحة جامعية

al-Hamami, Ala H.

أعضاء اللجنة

Utair, Muhammad
Riadh, Mayy Haikil

الجامعة

جامعة عمان العربية

الكلية

كلية العلوم الحاسوبية و المعلوماتية

القسم الأكاديمي

قسم علم الحاسوب

دولة الجامعة

الأردن

الدرجة العلمية

ماجستير

تاريخ الدرجة العلمية

2014

الملخص الإنجليزي

The technology development is witnessing expansion of knowledge area in the recent day and all of this is resulting from the application of theoretical ideas to the researchers, the development is not only on the scientific aspects, but expanded to include also the humanitarian aspects in addition to the common aspects between them.

This development has two aspects: the first is positive, which is the development of device and speed to get the results that are similar to the reality and the exploitation of these devices in the correct format for the benefit of all users, while the second aspect is negative, which is used incorrectly of the devices that resulting from the development.

The appearance of the currency is part of this development and it is affected directly, where there is exploited in incorrect form by copying the currency in a manner similar to the reality.

Therefore, it became necessary to submit a proposal for being a suitable as solution not inconsistent with the different cultures, time and place, to reduce the risk of problem that represented in distinguish between real and fake currency, this clear through add the watermarks inside currency, which is difficult to copy them.

at the same time, this watermarks may be visible to the naked eye so can easily inferred or it is invisible, However the high resolution imaging devices can copy these additions.

This thesis proposed model for distinguish the currencies by the program that working a submission inferred to the watermark through feature extraction determined the type of currency and is correctly or not.

In addition to, it is using (k-NN) algorithm to determine category of the currency.

Reducing the spread of counterfeit currency as much as possible can be beneficial and this model can be used by any user who wants to make sure whether the currency corrects or fake.

The proposed model applied on 100 banknote, the success rate was 91% and the failure rate was 9%.

التخصصات الرئيسية

الهندسة الكهربائية

الموضوعات

• الإلكترونيات الرقمية

عدد الصفحات

79

قائمة المحتويات

• APA
• MLA
• AMA

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-561799