Image retrieval with deep learning

For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i.e., artifact-free). However, digital images are subject to a wide range of distortions in real application scenarios, while the practical issues regardi...

Full description

Saved in:
Bibliographic Details
Main Author: Tan, Joe Chin Yong
Other Authors: Lin Weisi
Format: Final Year Project
Language:English
Published: 2017
Subjects:
Online Access:http://hdl.handle.net/10356/72791
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-72791
record_format dspace
spelling sg-ntu-dr.10356-727912023-03-03T20:36:01Z Image retrieval with deep learning Tan, Joe Chin Yong Lin Weisi School of Computer Science and Engineering DRNTU::Engineering::Computer science and engineering For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i.e., artifact-free). However, digital images are subject to a wide range of distortions in real application scenarios, while the practical issues regarding image quality in visual system have been largely ignored. In this thesis, a study of performing image retrieval with deep learning via TensorFlow and the VGG Net is first reported; then we conduct an evaluation of which for image retrieval under quality distortions in terms of Gaussian Blur, Gaussian Noise and JPEG Compression. The features of the pristine image database are first extracted, then retrieval is performed using pristine query images to the database to attain the baseline mean average precision (mAP). The query images are distorted with the 3 methods mentioned with different values of sigma, variance and quality. Blur in images can occur when the camera is out of focus. Noise in images usually happens when shooting in low-light environments and JPEG compression takes place when the quality value is low. All the distorted query images are used to perform retrieval to see the effects of distortion query images to the performance of retrieval. Among the different distortion methods, Gaussian Noise drastically affects the performance, Gaussian Blur affects the performance linearly to the increasing value of sigma, and JPEG Compression does not affect much unless very low quality value is used. Actions can be done to fine-tune the feature extractor with distorted images to see whether it will be more resilient to these distortion methods. Further studies can be made on how reversing the distortion with techniques like image sharpening and noise reduction affects the performance. Bachelor of Engineering (Computer Science) 2017-11-17T09:48:58Z 2017-11-17T09:48:58Z 2017 Final Year Project (FYP) http://hdl.handle.net/10356/72791 en Nanyang Technological University 33 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Tan, Joe Chin Yong
Image retrieval with deep learning
description For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i.e., artifact-free). However, digital images are subject to a wide range of distortions in real application scenarios, while the practical issues regarding image quality in visual system have been largely ignored. In this thesis, a study of performing image retrieval with deep learning via TensorFlow and the VGG Net is first reported; then we conduct an evaluation of which for image retrieval under quality distortions in terms of Gaussian Blur, Gaussian Noise and JPEG Compression. The features of the pristine image database are first extracted, then retrieval is performed using pristine query images to the database to attain the baseline mean average precision (mAP). The query images are distorted with the 3 methods mentioned with different values of sigma, variance and quality. Blur in images can occur when the camera is out of focus. Noise in images usually happens when shooting in low-light environments and JPEG compression takes place when the quality value is low. All the distorted query images are used to perform retrieval to see the effects of distortion query images to the performance of retrieval. Among the different distortion methods, Gaussian Noise drastically affects the performance, Gaussian Blur affects the performance linearly to the increasing value of sigma, and JPEG Compression does not affect much unless very low quality value is used. Actions can be done to fine-tune the feature extractor with distorted images to see whether it will be more resilient to these distortion methods. Further studies can be made on how reversing the distortion with techniques like image sharpening and noise reduction affects the performance.
author2 Lin Weisi
author_facet Lin Weisi
Tan, Joe Chin Yong
format Final Year Project
author Tan, Joe Chin Yong
author_sort Tan, Joe Chin Yong
title Image retrieval with deep learning
title_short Image retrieval with deep learning
title_full Image retrieval with deep learning
title_fullStr Image retrieval with deep learning
title_full_unstemmed Image retrieval with deep learning
title_sort image retrieval with deep learning
publishDate 2017
url http://hdl.handle.net/10356/72791
_version_ 1759857919881379840