A method and system for extracting screens of smart devices based on positioning images

Abstract

The invention discloses a method for extracting the screen of an intelligent device based on a positioning image, which comprises steps: 100: displaying the positioning image on the screen of the intelligent device; 200: collecting the screen image of the intelligent device and transmitting it to the extraction server; 300: extracting the service The terminal identifies the positioning image to determine the original coordinates of the positioning image; 400: the extraction server corrects the screen image of the smart device; 500: the extraction server searches out from the positioning image and extracts the smart device displayed in the screen image of the smart device Inner frame of the screen; 600: The extraction server extracts the screen image of the smart device within the range of the inner frame of the smart device screen. In addition, the present invention also provides corresponding systems and applications. The invention can automatically and conveniently extract the screen image of the smart device within the range of the inner frame of the screen of the smart device. Further, the screen image of the smart device within the range of the outer frame of the screen of the smart device may also be extracted.

Description

Technical field [0001] The present invention relates to a method and system for extracting a device screen, in particular to a method and system for extracting a smart device screen. Background technique [0002] Smart devices such as mobile phones and tablets have become an indispensable part of people's daily lives. With more and more smart devices, there are more and more services related to device screens, such as device screen insurance and image recognition of device screen content. These services related to the device screen usually need to extract the device screen image automatically and conveniently, for example, the device's screen area image is quickly extracted by the machine combined with the prompt, and the screen content in the image is inspected to determine whether the screen is good or bad. , Or identify related content in the screen area. [0003] Generally, extracting the device screen image requires taking a front photo of the device, and then extracting the...

AI Technical Summary

Problems solved by technology

[0005] (2) Different people and different environments cause the background of the device screen to be completely different. These backgrounds are not conducive to determining whether the screen is good or bad, or identifying relevant content in the screen area, and need to be removed

For example, when using a model to determine whether the screen is good or bad, it will be very costly to consider these diverse backgrounds when constructing training samples.

Images