Device screen image transmission detection model training method and device screen image transmission detection method

Abstract

The invention relates to a device screen image transmission detection model training method and a device screen image transmission detection method. The method includes: after device attribute information of each intelligent device is obtained, adding the image transmission labels to the device attribute information; and then converting the equipment attribute information and the translucent graph label into attribute feature data, establishing a feature data set according to the attribute feature data, and training a classification model for detecting whether the equipment screen is translucent or not according to the feature data set. On the basis, the equipment attribute information and the predetermined image transmission label are used as historical data to train the classification model to detect whether the equipment screen is subjected to image transmission or not, interference factors encountered when image recognition is used for detection are avoided, and stability of image transmission detection is guaranteed. Meanwhile, the classification model can be continuously trained through the data volume of the intelligent equipment, so that the accuracy of the image penetration detection can be gradually improved, and the hardware cost of the image penetration detection can be effectively reduced.

Description

technical field [0001] The invention relates to the technical field of electronic products, in particular to a device screen perspective detection model training method and a device screen perspective detection method. Background technique [0002] With the development of electronic product technology, various smart devices emerge in an endless stream, such as smart phones, notebook computers and tablet computers. At present, with the rapid development of economy and technology, the popularization and upgrading of smart devices are also getting faster and faster. Taking smartphones as an example, the arrival of the 5G era has accelerated the replacement of smartphones. In the iterative process of smart devices, effective recycling is one of the effective means of utilizing the residual value of smart devices, which can reduce chemical pollution to the environment and reduce waste. [0003] Among them, the screen, as the display and human-computer interaction part of smart ...

AI Technical Summary

Problems solved by technology

However, in the field of self-service recycling and other recycling fields, the shooting of smart devices is often affected by the operator, which cannot meet the operational requirements of traditional perspective detection, and produces interference such as too dark the device screen, light influence or angle influence, which leads to camera acquisition The device screen perspective feature is not available, even if the details are enhanced, it is impossible to identify whether the device screen has a perspective

At the same time, the camera requirements for shooting the device screen are also relatively high, which increases the recycling cost of smart devices

Images