A method for improving recall rate of similar image retrieval by using edge enhancement technology
Aiming at the problem of low registration caused by image rotation or background transformation in large-scale image classification processing, a convolutional neural network image classification method based on edge enhancement was proposed.This method extracted image features through the VGG19 net...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Language: | zho |
Published: |
Beijing Xintong Media Co., Ltd
2021-01-01
|
Series: | Dianxin kexue |
Subjects: | |
Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021008/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1841529116077064192 |
---|---|
author | Jingcheng CAO Jidong ZHANG Guojie SHI |
author_facet | Jingcheng CAO Jidong ZHANG Guojie SHI |
author_sort | Jingcheng CAO |
collection | DOAJ |
description | Aiming at the problem of low registration caused by image rotation or background transformation in large-scale image classification processing, a convolutional neural network image classification method based on edge enhancement was proposed.This method extracted image features through the VGG19 network model, and used cosine similarity for image classification judgment, used edge enhancement to highlight the edge features of image subject, and reduced the impact of image rotation or background transformation on the classification performance of the VGG19 network.Experiments prove that this method can effectively improve the similarity between the same subject rotated image and background transformed image and the original image, and is suitable for the classification of various images. |
format | Article |
id | doaj-art-a9f5727942344b4783854efb7b29b5ad |
institution | Kabale University |
issn | 1000-0801 |
language | zho |
publishDate | 2021-01-01 |
publisher | Beijing Xintong Media Co., Ltd |
record_format | Article |
series | Dianxin kexue |
spelling | doaj-art-a9f5727942344b4783854efb7b29b5ad2025-01-15T03:25:42ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012021-01-0137768459806384A method for improving recall rate of similar image retrieval by using edge enhancement technologyJingcheng CAOJidong ZHANGGuojie SHIAiming at the problem of low registration caused by image rotation or background transformation in large-scale image classification processing, a convolutional neural network image classification method based on edge enhancement was proposed.This method extracted image features through the VGG19 network model, and used cosine similarity for image classification judgment, used edge enhancement to highlight the edge features of image subject, and reduced the impact of image rotation or background transformation on the classification performance of the VGG19 network.Experiments prove that this method can effectively improve the similarity between the same subject rotated image and background transformed image and the original image, and is suitable for the classification of various images.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021008/convolutional neural networkVGG19cosine similarityedge enhancement |
spellingShingle | Jingcheng CAO Jidong ZHANG Guojie SHI A method for improving recall rate of similar image retrieval by using edge enhancement technology Dianxin kexue convolutional neural network VGG19 cosine similarity edge enhancement |
title | A method for improving recall rate of similar image retrieval by using edge enhancement technology |
title_full | A method for improving recall rate of similar image retrieval by using edge enhancement technology |
title_fullStr | A method for improving recall rate of similar image retrieval by using edge enhancement technology |
title_full_unstemmed | A method for improving recall rate of similar image retrieval by using edge enhancement technology |
title_short | A method for improving recall rate of similar image retrieval by using edge enhancement technology |
title_sort | method for improving recall rate of similar image retrieval by using edge enhancement technology |
topic | convolutional neural network VGG19 cosine similarity edge enhancement |
url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021008/ |
work_keys_str_mv | AT jingchengcao amethodforimprovingrecallrateofsimilarimageretrievalbyusingedgeenhancementtechnology AT jidongzhang amethodforimprovingrecallrateofsimilarimageretrievalbyusingedgeenhancementtechnology AT guojieshi amethodforimprovingrecallrateofsimilarimageretrievalbyusingedgeenhancementtechnology AT jingchengcao methodforimprovingrecallrateofsimilarimageretrievalbyusingedgeenhancementtechnology AT jidongzhang methodforimprovingrecallrateofsimilarimageretrievalbyusingedgeenhancementtechnology AT guojieshi methodforimprovingrecallrateofsimilarimageretrievalbyusingedgeenhancementtechnology |