Image retrieval method, device and equipment and readable storage medium

An image retrieval and image technology, applied in the field of image processing, can solve the problems of reducing the difference between vehicles, the difficulty of retrieval accuracy to meet the retrieval requirements, and the difficulty of accurately extracting vehicle image feature descriptions, etc.

Active Publication Date: 2019-06-07
SUZHOU KEDA TECH
View PDF5 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since different vehicles have roughly the same appearance, the distinction between vehicles is reduced. In addition, the images captured by the camera are also affected by light, viewing angle, cluttered background, low resolution, and line of sight occlusion. The same vehicle has multiple states, so it is difficult to accurately extract the feature descriptor of the vehicle image
Vehicle image retrieval based on inaccurate feature descriptors, the retrieval accuracy is difficult to meet the retrieval requirements

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image retrieval method, device and equipment and readable storage medium
  • Image retrieval method, device and equipment and readable storage medium
  • Image retrieval method, device and equipment and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Please refer to figure 1 , figure 1 It is a flowchart of an image retrieval method in an embodiment of the present invention, and the method includes the following steps:

[0050] S101. Acquire a target image to be retrieved, and input the target image into a target deep learning model.

[0051]In the embodiment of the present invention, a target deep learning model can be set in advance, and the model is specifically a model capable of extracting features from an image, and a feature refers to a model capable of extracting global features and local features of an image. For example, the target deep learning model can be a model based on a deep neural network (such as VGG-16). The deep neural network can automatically learn the characteristics of images, avoiding the problems of manual intervention and feature selection depending on the level and experience of personnel. , which can extract more feature information of the image, including global features and local fea...

Embodiment 2

[0084] In order to facilitate those skilled in the art to better understand the image retrieval method provided by the embodiment of the present invention, the following training such as figure 2 The shown target deep learning model, and the process of retrieving vehicle images based on the trained target deep learning model, implement the image retrieval method provided by the embodiment of the present invention as an example, and describe in detail.

[0085] The basic process of vehicle retrieval is: training network, feature extraction of query image and library image, similarity measurement, and return of retrieval results. The details are as follows:

[0086] Among them, the data set used for training and testing uses VehicleID. The training set contains 113,346 images of 13,164 vehicles, and the image size during training is 224x224x3. The test set includes 6,493 images of 800 vehicles, and each vehicle is randomly selected. One image is used as the query image, and the...

Embodiment 3

[0099] Corresponding to the above method embodiments, an embodiment of the present invention also provides an image retrieval device, and the image retrieval device described below and the image retrieval method described above can be referred to in correspondence.

[0100] see Figure 5 As shown, the device includes the following modules:

[0101] The target image acquisition module 101 is used to acquire the target image to be retrieved, and input the target image into the target deep learning model;

[0102] The image feature extraction module 102 is used to extract the features of the target image by using the target deep learning model to obtain the image features of the target image; the image features include global features, local features and multi-scale global features, and the multi-scale global features are global feature extraction The features obtained after the weighted calculation of multiple intermediate stage features generated in the process;

[0103] The ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an image retrieval method, and the method comprises the following steps: obtaining a to-be-retrieved target image, and inputting the target image into a target deep learning model; utilizing the target deep learning model to perform feature extraction on the target image to obtain image features of the target image; wherein the image features comprise global features, localfeatures and multi-scale global features, and the multi-scale global features are features obtained by performing weighted calculation on a plurality of intermediate-stage features generated in the global feature extraction process; respectively calculating similar distances between the target image and the images in the image library by utilizing the image features according to a distance calculation rule; and determining and outputting a similar image of the target image by using the similar distance. According to the method, the image retrieval accuracy can be improved. The invention further discloses an image retrieval device and equipment and a readable storage medium which have corresponding technical effects.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image retrieval method, device, equipment and readable storage medium. Background technique [0002] Image retrieval is widely used in pedestrian re-identification, vehicle recognition, image search of websites and product retrieval of e-commerce. [0003] At present, for image retrieval, there are two major problems, one is how to extract more discriminative feature descriptors to describe images, and the other is how to effectively measure the similarity between features and features. For example, vehicle image retrieval belongs to the problem of vehicle re-identification. This problem is based on target detection. The detector defines and extracts the position and size of the target object in the image with a bounding box, which is used as the data source of the re-identification technology. By inputting the image to be recognized, the system retrieves an ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/583G06F16/53
Inventor 沈文超邹文艺晋兆龙
Owner SUZHOU KEDA TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap