Please use this identifier to cite or link to this item:
http://dspace.univ-tiaret.dz:80/handle/123456789/5482
Title: | Recognition of house numbers by artificial neural networks |
Authors: | Chedad, Soumia Kertel, Chahrazad |
Keywords: | Digital image processing,convolutional neural networks CNNs , Multi-layer perceptron , Street view house number SVHN |
Issue Date: | 2021 |
Publisher: | Université Ibn Khaldoun -Tiaret- |
Abstract: | Digital image processing is usually done using convolutional neural networks that reduce the size of images with increasing their depth .as it uses different designs of multilayer perceptron. with different architectures , including street view house number datasets. This thesis we try to obtain similar results to the state of the art by appling some deep convolutional neural network to the problem of classifying single digits in street view images of house numbers datasets format 2 ,with also introduce three class(class 1,2 and 3) to the SVHN dataset background to aid in the problem of image classification, and are implemented in TensorFlow using Google Colaboratory that help us to minimize time of execution As much as possible. |
URI: | http://dspace.univ-tiaret.dz:80/handle/123456789/5482 |
Appears in Collections: | Master |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
TH.M.INF.FR.2021.11.pdf | 6 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.