Unlock instant, AI-driven research and patent intelligence for your innovation.
Image evaluation method and system
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
An image evaluation and image technology, which is applied in the field of image processing, can solve problems such as large evaluation differences, and achieve the effect of reducing evaluation differences and making evaluations reasonable and reliable
Active Publication Date: 2022-03-15
CTRIP COMP TECH SHANGHAI
View PDF4 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0009] The technical problem to be solved by the present invention is to provide an image evaluation method and system in order to overcome the defect that the image evaluation in the prior art is quite different from the environment evaluation
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0055] In this embodiment, an image evaluation method is provided, and an image evaluation method can be applied to an image evaluation of any class. This embodiment is applied to the evaluation of the hotel image, and the image evaluation method can make an image of an image of an image of the hotel category to perform US sensitivity score.
[0056] The sample image library contains some other category images in some hotel images and public aesthetics (AADB) in OTA (online travel agency) website.
[0057] Such as figure 1 As shown, the image evaluation method includes:
[0058] Step 101, set the category of a number of images, including the class to be evaluated;
[0059] Several images from the sample image library, the plurality of images in this embodiment include images of hotel class and non-hotels, each image sets a category tag, category tag for tagging the category belonging, which is a hotel image setting category The label is 1, and it is 0.
[0060] Step 102, a conjunc...
Embodiment 2
[0088] This embodiment provides an image evaluation system, an image evaluation system can be applied to an image evaluation of any class, and the present embodiment is applied to the hotel image, and the image evaluation method can make an image of an image of the hotel category to perform US sensitivity score.
[0089] The sample image library contains some other category images in some hotel images and public aesthetics (AADB) in OTA (online travel agency) website.
[0090] Such as figure 2 As shown, the image evaluation system includes: category training module 200, preset module 201, conversion module 202, evaluation model training module 203, score module 204, display module 205.
[0091] Category Training Module 200 is used to set the category of several images, and categories include class to be evaluated; also used to obtain an image category judgment model based on several images and categories.
[0092] Several images from the sample image library, several images in thi...
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
Login to View More
Abstract
The invention discloses an image evaluation method and system, wherein the image evaluation method includes: S1, pairing several images to obtain paired images, and setting evaluation scores for the images; S2, using the paired images and evaluation scores to train a twin network to obtain image evaluation Model; S3. Input the evaluation image to the image evaluation model to obtain a score. The image evaluation method of the present invention uses the image evaluation model obtained after the twin network training to evaluate the evaluation image, and the mean square error between the evaluation score after evaluation and the evaluation score of the real environment is lower than 1.6, compared with the direct use of convolutional neural network Compared with the mean square error between the evaluation score and the evaluation score of the real environment of 2.53, the difference between the evaluation result of the image evaluation method of the present invention and the evaluation of the real environment is significantly reduced, and the evaluation is more reasonable and reliable.
Description
Technical field [0001] The present invention belongs to the field of image processing, more particularly to a method and system for image evaluation. Background technique [0002] With the rapid development in recent years, the Internet and information technology, OTA (online travel provider) provides users with a real-time diversify tourism products and services, has undoubtedly become one of the most popular services among areas. It promotes innovative integration of tourism, and as a microcosm of the online travel industry has become an indispensable part of people's lives. [0003] When customers get the travel services and products through an online travel booking OTA platform, it will produce large amounts of interactive data. How to prevent information overload problem, to help customers in a growing number of tourism products and services to discover their needs to be a worthwhile research work. By recommending a more satisfactory products and services to users, can effec...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More