Image evaluation method and device, server and storage medium

An evaluation method and image technology, applied in the field of image processing, can solve problems such as low accuracy, low hit rate of recommended images, and inability to meet user needs, and achieve the effect of improving accuracy and solving low hit rate

Inactive Publication Date: 2018-04-20
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF4 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the process of realizing the present invention, the inventors found the following technical problems: the current evaluation of images is only considered from the perspective of image quality, and the accuracy of the evaluation is low, resulting in a low hit rate of recommended images generated according to the evaluation results. Meet the needs of users

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 evaluation method and device, server and storage medium
  • Image evaluation method and device, server and storage medium
  • Image evaluation method and device, server and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] figure 1 It is a flow chart of the image evaluation method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of evaluating existing images. The method can be executed by an image evaluation device, and specifically includes the following steps:

[0027] Step 110, acquire a feature set of the image, wherein the feature set includes: image subjective parameter features and / or image objective parameter features.

[0028] An image is a picture with visual effects, which may include various graphics and images. The feature set may be a collection of various attributes and characteristics used to characterize graphics and images in the image. For example: the color features used to describe the expressive nature of the scene corresponding to the image, the shape features of the graphics in the image, and the spatial relationship features that describe the spatial position and relative orientation relationship between multiple o...

Embodiment 2

[0045] figure 2 It is a schematic flowchart of the image evaluation method provided by Embodiment 2 of the present invention. This embodiment is optimized on the basis of the above-mentioned embodiments. In this embodiment, the image subjective parameter characteristics of the image are obtained, and the specific optimization is as follows: using the preset preference evaluation neural network model to output the image preference.

[0046] Correspondingly, the image evaluation method provided in this embodiment includes:

[0047] Step 210, acquiring image objective parameter features of the image.

[0048] Step 220, using the preset preference evaluation neural network model to output the image liking degree, and\or using the preset sharpness neural network model to output the image definition.

[0049] The image liking degree may be an intuitive subjective evaluation of the image by the user. For some images, it may not be possible to directly obtain the user's image pref...

Embodiment 3

[0058] image 3 It is a schematic flowchart of the image evaluation method provided by Embodiment 3 of the present invention. This embodiment is optimized on the basis of the above embodiments. In this embodiment, before training the deep learning model, the following steps are added: collecting user operations on the sample image; generating an evaluation of the sample image according to the operation result.

[0059] Correspondingly, the image evaluation method provided in this embodiment includes:

[0060] Step 310, acquire a feature set of the image, wherein the feature set includes: image subjective parameter features and / or image objective parameter features.

[0061] Step 320, collecting user operations on the sample image.

[0062] When training the deep learning model, it is necessary to input the feature set of the sample image and the evaluation of the sample image. so that the deep learning model generates a corresponding evaluation method through training. Si...

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 present invention discloses an image evaluation method and device, a server and a storage medium. The method comprises the steps of: obtaining a feature set of an image, wherein the feature set comprises image subjective parameter features and/or image objective parameter features; and inputting the image feature set into a deep learning model which completes training, and obtaining an evaluation result of the image, wherein the deep learning model is obtained through training according to the feature set of a sample image and an evaluation result of the sample image. The accuracy of the image evaluation is improved to allow an evaluation result to better meet users' actual demands, and the technical problem is solved that a hit rate of a recommend image generated according to the evaluation result is low.

Description

technical field [0001] Embodiments of the present invention relate to image processing technologies, and in particular, to an image evaluation method, device, server, and storage medium. Background technique [0002] Image refers to all pictures with visual effects, and is a general term for various graphics and images. With the rapid development of the Internet, the number of images shows a trend of massive growth. It is becoming more and more difficult to select suitable images to recommend to users from a large number of images. Usually, images are evaluated in advance, and images with better evaluation results are recommended to users. [0003] Currently, image quality parameters are usually used to evaluate images. Generally, the image can be evaluated by using image characteristic parameters such as image clarity and contrast. In the process of realizing the present invention, the inventors found the following technical problems: the current evaluation of images is...

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): G06T7/00
CPCG06T7/0002G06T2207/20081G06T2207/30168
Inventor 王加明苏春波
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
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