A color vision approach for reconstructing color images in different lighting conditions based on auto encoder technique using deep neural networks
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2020.
| Main Authors: | , , , |
|---|---|
| מחברים אחרים: | |
| פורמט: | Thesis |
| שפה: | en_US |
| יצא לאור: |
Brac University
2021
|
| נושאים: | |
| גישה מקוונת: | http://hdl.handle.net/10361/14453 |
| id |
10361-14453 |
|---|---|
| record_format |
dspace |
| spelling |
10361-144532022-01-26T10:10:30Z A color vision approach for reconstructing color images in different lighting conditions based on auto encoder technique using deep neural networks Gomes, Paul Richie Uddin, Muhammad Arman Sabuj, Hasibul Hasan Faiz, Raian Ibn Alam, Md. Ashraful Department of Computer Science and Engineering, Brac University Autoencoder Image Reconstruction Deep Neural Networks Color Vision This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2020. Cataloged from PDF version of thesis. Includes bibliographical references (pages 40-43). We propose a color vision approach that enables normalizing images based on autoencoder technique using deep neural networks. The proposed model consists of three main different steps: image processing, encoding and decoding. In the image processing part, an efficient image processing method is used to resize acquired images into a finite image resolution equal to the number of input nodes of an autoencoder. Autoencoder comprises encoding and decoding processes. Secondly, the encoding process based on deep neural networks generates a code of an input image and finally the decoding process using deep neural networks reconstructs the original image from the code generated by the encoder. The autoencoder is trained with more than ten thousand resized image dataset using convolutional neural networks. The experimental results verified that the proposed model enables reconstructing predefined normalized images from original images which can be used in sophisticated color vision applications. Paul Richie Gomes Muhammad Arman Uddin Hasibul Hasan Sabuj Raian Ibn Faiz B. Computer Science 2021-05-30T05:50:56Z 2021-05-30T05:50:56Z 2020 2020-04 Thesis ID: 16101284 ID: 16101281 ID: 15301123 ID: 15201026 http://hdl.handle.net/10361/14453 en_US Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 43 Pages application/pdf Brac University |
| institution |
Brac University |
| collection |
Institutional Repository |
| language |
en_US |
| topic |
Autoencoder Image Reconstruction Deep Neural Networks Color Vision |
| spellingShingle |
Autoencoder Image Reconstruction Deep Neural Networks Color Vision Gomes, Paul Richie Uddin, Muhammad Arman Sabuj, Hasibul Hasan Faiz, Raian Ibn A color vision approach for reconstructing color images in different lighting conditions based on auto encoder technique using deep neural networks |
| description |
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2020. |
| author2 |
Alam, Md. Ashraful |
| author_facet |
Alam, Md. Ashraful Gomes, Paul Richie Uddin, Muhammad Arman Sabuj, Hasibul Hasan Faiz, Raian Ibn |
| format |
Thesis |
| author |
Gomes, Paul Richie Uddin, Muhammad Arman Sabuj, Hasibul Hasan Faiz, Raian Ibn |
| author_sort |
Gomes, Paul Richie |
| title |
A color vision approach for reconstructing color images in different lighting conditions based on auto encoder technique using deep neural networks |
| title_short |
A color vision approach for reconstructing color images in different lighting conditions based on auto encoder technique using deep neural networks |
| title_full |
A color vision approach for reconstructing color images in different lighting conditions based on auto encoder technique using deep neural networks |
| title_fullStr |
A color vision approach for reconstructing color images in different lighting conditions based on auto encoder technique using deep neural networks |
| title_full_unstemmed |
A color vision approach for reconstructing color images in different lighting conditions based on auto encoder technique using deep neural networks |
| title_sort |
color vision approach for reconstructing color images in different lighting conditions based on auto encoder technique using deep neural networks |
| publisher |
Brac University |
| publishDate |
2021 |
| url |
http://hdl.handle.net/10361/14453 |
| work_keys_str_mv |
AT gomespaulrichie acolorvisionapproachforreconstructingcolorimagesindifferentlightingconditionsbasedonautoencodertechniqueusingdeepneuralnetworks AT uddinmuhammadarman acolorvisionapproachforreconstructingcolorimagesindifferentlightingconditionsbasedonautoencodertechniqueusingdeepneuralnetworks AT sabujhasibulhasan acolorvisionapproachforreconstructingcolorimagesindifferentlightingconditionsbasedonautoencodertechniqueusingdeepneuralnetworks AT faizraianibn acolorvisionapproachforreconstructingcolorimagesindifferentlightingconditionsbasedonautoencodertechniqueusingdeepneuralnetworks AT gomespaulrichie colorvisionapproachforreconstructingcolorimagesindifferentlightingconditionsbasedonautoencodertechniqueusingdeepneuralnetworks AT uddinmuhammadarman colorvisionapproachforreconstructingcolorimagesindifferentlightingconditionsbasedonautoencodertechniqueusingdeepneuralnetworks AT sabujhasibulhasan colorvisionapproachforreconstructingcolorimagesindifferentlightingconditionsbasedonautoencodertechniqueusingdeepneuralnetworks AT faizraianibn colorvisionapproachforreconstructingcolorimagesindifferentlightingconditionsbasedonautoencodertechniqueusingdeepneuralnetworks |
| _version_ |
1814307796625129472 |