research centers


Search results: Found 2

Listing 1 - 2 of 2
Sort by

Article
Improved Feature Extraction Using Weightless Neural Networks(IWNC)

Author: Ikhlas Watan Ghindawi
Journal: Journal Of AL-Turath University College مجلة كلية التراث الجامعة ISSN: 20745621 Year: 2012 Issue: 12 Pages: 244-253
Publisher: Heritage College كلية التراث الجامعة

Loading...
Loading...
Abstract

The weightless neural classifier (WNC) is based on the collective response of RAM-based neurons. The ability of producing prototypes, analog to unconstrained images, from learned categories, was first introduced in the (IWNC) model. By counting the frequency of write accesses at each RAM neuron during the training phase, it is possible to associate the most accessed addresses to the corresponding input field contents that defined them. This work is about extracting information from such frequency counting in the form of fuzzy rules as an alternative way to describe the same images produced by (IWNC) as logical prototypes.

المصنف العصبي العديم الوزن ( اللاموزون ) يعتمد على الاستجابة المشتركة للاعصاب المعتمدة على ذاكرة الوصول العشوائي ( الذاكرة المؤقتة) . ان امكانية انتاج نماذج اولية تناضرية للصور غير المقيدة من تصانيف معلومة قد تم تقديمها بنموذج تحسين ميزة الاستخراج باستخدام الشبكات العصبية اللاموزونة ( عديمة بحساب تردد الكتابة على كل ذاكرة وصول عشوائية خلال طور التدريب . بالامكان ربط معظم عناوين الوصول مع محتويات مجال الادخال المناضرة . هذا البحث حول استخراج معلومات من قياسات التردد بشكل قواعد غامضة كطريقة بديلة لوصف نفس الصور المنتجة بواسطة تحسين ميزة الاستخراج باستخدام الشبكات العصبية اللاموزونة ( عديمة الوزن ) كنموذج اولي منطقي .

Keywords

Weightless --- Neural --- Networks --- IWNC


Article
Off-line Signature Recognition Using Weightless Neural Network and Feature Extraction

Author: Ali Al-Saegh
Journal: Iraqi Journal for Electrical And Electronic Engineering المجلة العراقية للهندسة الكهربائية والالكترونية ISSN: 18145892 Year: 2015 Volume: 11 Issue: 1 Pages: 124-131
Publisher: Basrah University جامعة البصرة

Loading...
Loading...
Abstract

The problem of automatic signature recognition and verification has been extensively investigated due to the vitalityof this field of research. Handwritten signatures are broadly used in daily life as a secure way for personal identification. In thispaper a novel approach is proposed for handwritten signature recognition in an off-line environment based on WeightlessNeural Network (WNN) and feature extraction. This type of neural networks (NN) is characterized by its simplicity in design andimplementation. Whereas no weights, transfer functions and multipliers are required. Implementing the WNN needs onlyRandom Access Memory (RAM) slices. Moreover, the whole process of training can be accomplished with few numbers oftraining samples and by presenting them once to the neural network. Employing the proposed approach in signature recognitionarea yields promising results with rates of 99.67% and 99.55% for recognition of signatures that the network has trained on andrejection of signatures that the network .has not trained on, respectively

Listing 1 - 2 of 2
Sort by
Narrow your search

Resource type

article (2)


Language

English (2)


Year
From To Submit

2015 (1)

2012 (1)