![](/images/graphics-bg.png)
A study regarding the generalization capacity of image classification by using neuroal networks in Matlab
Author
Source
Journal of Babylon University : Journal of Applied and Pure Sciences
Issue
Vol. 26, Issue 4 (30 Apr. 2018), pp.45-56, 12 p.
Publisher
Publication Date
2018-04-30
Country of Publication
Iraq
No. of Pages
12
Main Subjects
Engineering & Technology Sciences (Multidisciplinary)
Abstract EN
The paper performs an algorithmic and experimental study regarding the generalization capacity of the scheme based on neuronal networks for the recognition of new images of the face.
This enables both a rendering of graphic representations and the classification of image classes in Matlab.
The purpose is to describe the recognition algorithm, to project and implement an application which proposes both the graphic representation of the images used by the neuronal training algorithm but also the implementation of the perceptron neuronal algorithm and the determination of the generalization capacity of the separating hyper plane of the considered image classes.
American Psychological Association (APA)
al-Rabii, Evan Madi Hamzah. 2018. A study regarding the generalization capacity of image classification by using neuroal networks in Matlab. Journal of Babylon University : Journal of Applied and Pure Sciences،Vol. 26, no. 4, pp.45-56.
https://search.emarefa.net/detail/BIM-1093482
Modern Language Association (MLA)
al-Rabii, Evan Madi Hamzah. A study regarding the generalization capacity of image classification by using neuroal networks in Matlab. Journal of Babylon University : Journal of Applied and Pure Sciences Vol. 26, no. 4 (2018), pp.45-56.
https://search.emarefa.net/detail/BIM-1093482
American Medical Association (AMA)
al-Rabii, Evan Madi Hamzah. A study regarding the generalization capacity of image classification by using neuroal networks in Matlab. Journal of Babylon University : Journal of Applied and Pure Sciences. 2018. Vol. 26, no. 4, pp.45-56.
https://search.emarefa.net/detail/BIM-1093482
Data Type
Journal Articles
Language
English
Notes
Record ID
BIM-1093482