A method for improving recall rate of similar image retrieval by using edge enhancement technology

Jingcheng CAO; Jidong ZHANG; Guojie SHI

doi:10.11959/j.issn.1000-0801.2021008

您当前的位置：

首页 >

文章列表页 >

A method for improving recall rate of similar image retrieval by using edge enhancement technology

Research and Development | 更新时间：2024-06-05

- A method for improving recall rate of similar image retrieval by using edge enhancement technology
- Telecommunications Science Vol. 37, Issue 1, Pages: 76-84(2021)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2021008
  CLC： TP393
- Published Online：2021-01，
  
  Published：20 January 2021
- 稿件说明：
移动端阅览
Jingcheng CAO, Jidong ZHANG, Guojie SHI. A method for improving recall rate of similar image retrieval by using edge enhancement technology[J]. Telecommunications science, 2021, 37(1): 76-84.
DOI：

Jingcheng CAO, Jidong ZHANG, Guojie SHI. A method for improving recall rate of similar image retrieval by using edge enhancement technology[J]. Telecommunications science, 2021, 37(1): 76-84. DOI： 10.11959/j.issn.1000-0801.2021008.

摘要

针对大规模图像分类处理中图像旋转或背景变换导致的配准度较低问题，提出一种基于边缘增强的卷积神经网络图像分类方法。该方法通过VGG19网络模型提取图像特征，并使用余弦相似度进行图像分类判定，利用边缘增强突出图像主体的边缘特征，降低图像旋转或背景变换对VGG19网络分类性能带来的影响。实验证明，该方法可以有效地提高同一主体旋转图像和背景变换图像与原始图像的相似度，适用于各类图像的分类。

Abstract

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.

关键词

Keywords

references

苏赋 , 吕沁 , 罗仁泽 . 基于深度学习的图像分类研究综述 [J ] . 电信科学 , 2019 , 35 ( 11 ): 58 - 74 .

SU F , LV Q , LUO R Z . Review of image classification based on deep learning [J ] . Telecommunications Science , 2019 , 35 ( 11 ): 58 - 74 .

陈强普 , 桑军 , 项志立 , 等 . BN 对 VGG 神经网络的影响研究 [J ] . 合肥工业大学学报(自然科学版) , 2018 , 41 ( 1 ): 35 - 39 .

CHEN Q P , SANG J , XIANG Z L , et al . Research on the influence of BN on VGG neural network [J ] . Journal of Hefei University of Technology (Natural Science Edition) , 2018 , 41 ( 1 ): 35 - 39 .

唐浩漾 , 孙梓巍 , 王婧 , 等 . 基于VGG-19混合迁移学习模型的服饰图片识别 [J ] . 西安邮电大学学报 , 2018 , 23 ( 6 ): 87 - 93 .

TANG H Y , SUN Z W , WANG J , et al . Clothing image recognition based on VGG-19 hybrid transfer learning model [J ] . Journal of Xi’an University of Posts and Telecommunications , 2018 , 23 ( 6 ): 87 - 93 .

李校林 , 钮海涛 . 基于VGG-NET的特征融合面部表情识别 [J ] . 计算机工程与科学 , 2020 , 42 ( 3 ): 500 - 509 .

LI J L , NIU H T . Facial expression recognition based on feature fusion of VGG-NET [J ] . Computer Engineering and Science , 2020 , 42 ( 3 ): 500 - 509 .

谢新明 . 基于优化的 VGG 模型道路交通标志识别研究 [D ] . 长沙:长沙理工大学 , 2017 .

XIE X M . Research on road traffic sign recognition based on optimized VGG model [D ] . Changsha:Changsha University of Science and Technology , 2017 .

冯国徽 . 基于卷积神经网络VGG模型的小规模图像分类 [D ] . 兰州:兰州大学 , 2018 .

FENG G H . Small-scale image classification based on convolutional neural network VGG model [D ] . Lanzhou:Lanzhou University , 2018 .

CUBUK E D , ZOPH B , DANDELION M , et al . Auto augment:learning augmentation strategies from data [C ] // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway:IEEE Press , 2020 .

杨旺功 , 淮永建 . 基于深度卷积生成对抗网络的花朵图像增强与分类 [J ] . 计算机科学 , 2020 , 47 ( 6 ): 176 - 179 .

YANG W G , HUAI Y J . Flower image enhancement and classification based on deep convolution generative adversarial network [J ] . Computer Science , 2020 , 47 ( 6 ): 176 - 179 .

Views

155

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Deep learning based demodulation method for multiple access of visible light communication in 6G

A VVC intra coding method based on fast partition for coding unit

Research on vehicle feature recognition algorithm based on optimized convolutional neural network

A network traffic classification method based on random forest and improved convolutional neural network

A flexible pruning on deep convolutional neural networks

Related Author

WANG Liang

YAO Yao

SHAO Xinyu

HUANG Xiaofeng

YIN Haibing

LU Yu

ZHONG Hui

Jiyi WU

Related Institution

Jiangsu Vocational College of Business

College of Communication Engineering, Hangzhou Danzi University

Zhejiang Industry Polytechnic College

Zhejiang Federation of Artificial Intelligence

Intelligent Education Research Center, Zhejiang University

⁰