Image labeling using hopfield neural NE

المؤلفون المشاركون

Husayn, Lubna R.
Mahdi, Riyad A. K.
Naum, Riyad S.

المصدر

Iraqi Journal of Science

العدد

المجلد 45، العدد 1 (31 ديسمبر/كانون الأول 2004)، ص ص. 188-193، 6ص.

الناشر

جامعة بغداد كلية العلوم

تاريخ النشر

2004-12-31

دولة النشر

العراق

عدد الصفحات

6

التخصصات الرئيسية

تكنولوجيا المعلومات وعلم الحاسوب

الموضوعات

الملخص EN

Tlfis paper considers ،the application of neural networks to the problem ol image labeling.

It is assumed that an image has been segmented into regions and that predefined uniary properties as well as binaty relationships between these regions have been extracted from the segmented image.

It is also assumed that the knowledge base of object models contains corresponding unary features of object models.

A Hopfield optimization network is used as a matching mechanism based on an energy function that compute the hamming distance between tow neurons (nodes) based on the consistency between object models and image regions with regard to the unary and binary constraints.

A node represents an association between an image region with one of the possible labels.

The results presented in this paper indicate validity of the neural approach and the corresponding energy function used.

نمط استشهاد جمعية علماء النفس الأمريكية (APA)

Naum, Riyad S.& Mahdi, Riyad A. K.& Husayn, Lubna R.. 2004. Image labeling using hopfield neural NE. Iraqi Journal of Science،Vol. 45, no. 1, pp.188-193.
https://search.emarefa.net/detail/BIM-596208

نمط استشهاد الجمعية الأمريكية للغات الحديثة (MLA)

Naum, Riyad S.…[et al.]. Image labeling using hopfield neural NE. Iraqi Journal of Science Vol. 45, no. 1 (2004), pp.188-193.
https://search.emarefa.net/detail/BIM-596208

نمط استشهاد الجمعية الطبية الأمريكية (AMA)

Naum, Riyad S.& Mahdi, Riyad A. K.& Husayn, Lubna R.. Image labeling using hopfield neural NE. Iraqi Journal of Science. 2004. Vol. 45, no. 1, pp.188-193.
https://search.emarefa.net/detail/BIM-596208

نوع البيانات

مقالات

لغة النص

الإنجليزية

الملاحظات

Includes bibliographical references : p. 193

رقم السجل

BIM-596208