Training data generation method and device for screen abnormal picture detection

Abstract

The embodiment of the invention provides a training data generation method and device for screen abnormal image detection, and aims to solve the problem that a large number of screen abnormal images are difficult to manually collect. In the embodiment of the invention, a large number of screen abnormal images can be generated according to the normal seed images, and the problem that a large numberof screen abnormal images are difficult to manually collect is solved. Meanwhile, in the embodiment of the invention, the simulation degree of the final screen abnormal image can be calculated, and when the simulation degree meets the preset condition, the simulation degree is used as training data to be put into the screen abnormal image set, so that the quality of the training data is ensured.Furthermore, in the method, a surface layer abnormal feature and depth abnormal feature fusion mode is adopted. After the surface layer abnormal features are added into the normal seed image, the normal seed image is sent into the depth abnormal feature generation network, and the network output is the final screen abnormal image.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and a device for generating training data for abnormal screen detection. Background technique [0002] Mobile phone manufacturers, LCD screen manufacturers, etc. have a large number of business needs related to screen abnormality detection. The business requirement for screen abnormality detection is to detect whether there is an abnormality in the captured screen by providing only a photo of the screen without using additional hardware devices. [0003] The realization of the above business requirements mainly relies on the screen anomaly detection technology based on deep learning. This new technology requires a large number of abnormal screen images as training data to build a training set to train a deep model for abnormal screen detection. [0004] The collection of abnormal screen images can be achieved by manually taking pictures of mobile terminals with abnor...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiments of the present invention provide a method and device for generating training data for detecting abnormal screen images, so as to solve the problem of difficulty in manual collection of a large number of abnormal screen images

Images