A screen image recognition method, device, system and readable storage medium
A screen image and screen technology, which is applied in the field of screen image recognition methods, equipment, systems, and readable storage media, can solve problems such as low response speed, poor applicability, and insufficient stability of digital image processing technology, and achieve fast response capability, The effect of simplifying complexity, improving adaptability and intelligence
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0055] The embodiment of the present application discloses a screen image recognition method, referring to figure 1 , the method consists of,
[0056] 101. Acquire multiple reference images containing a target scene.
[0057] 102. Extract target areas in multiple reference images containing target scenes to obtain multiple reference templates.
[0058] 103. Extract multiple feature points of multiple reference templates.
[0059] 104. Train the neural network according to multiple feature points of multiple reference templates.
[0060] 105. Extract multiple feature points of the target image.
[0061] 106. Perform geometric registration calculation on multiple feature points of the target image and multiple feature points of multiple reference templates to obtain a similarity.
[0062] Specifically, a feature map of the target image is acquired according to multiple feature points of the target image.
[0063]According to the multiple feature points of the multiple refer...
Embodiment 2
[0068] The embodiment of the present application discloses a screen image recognition method, referring to figure 2 , the method includes:
[0069] 201. Acquire multiple reference images containing a target scene.
[0070] Specifically, the initial sample collection is performed on the liquid crystal display screen interface including the target scene, and stored in a temporary sample library as a reference image.
[0071] For different types of screens, the target scene may be a scene of a certain type of screen;
[0072] In practical applications, multiple different types of MLDs can be
[0073] Execute the operation described in step 201 for multiple target scenes respectively corresponding to the type screens.
[0074] Optionally, in practical applications, the process described in step 201 may be realized by shooting the target scene with a camera, and the process may specifically be:
[0075] Setting the exposure time, wherein the exposure time is less than the firs...
Embodiment 3
[0140] The embodiment of the present application discloses a screen image recognition device, refer to image 3 , the device consists of:
[0141] Reference extraction module 31, for extracting a plurality of feature points to a plurality of reference templates;
[0142] Target extraction module 32, for extracting a plurality of feature points to target image;
[0143] Registration calculation module 33: for performing geometric registration calculation on the plurality of feature points of the target image and the plurality of feature points of the plurality of reference templates to obtain similarity;
[0144] The first identification module 34: if the similarity is greater than or equal to the similarity threshold, output a first identification result according to the reference template;
[0145] The second identification module 35: if the similarity is smaller than the similarity threshold, identify multiple feature points of the target image through a neural network, an...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com