公开(公告)号：US20220092359A1

公开(公告)日：2022-03-24

申请号：US17477070

申请日：2021-09-16

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Libo ZHANG ,  Yuanyuan LU ,  Wangqiang HE ,  Dong CHAI ,  Hong WANG

IPC: G06K9/62 ,  G06T7/00

Abstract: The present disclosure relates to an image data classification method, device and system, and relates to the field of computer technology. The method includes: inputting test image data into a neural network model trained by using an original training sample set for classification, and determining an image type to which the test image data belongs and a membership probability of the image data belonging to the image type; establishing an easy-to-classify data set, according to test image data with a membership probability greater than a first threshold; adding test image data in the easy-to-classify data set that has a classification accuracy rate less than or equal to a second threshold and a correct classification result to the original training sample set to generate an augmented training sample set; and using the augmented training sample set to train the neural network model so as to determine an image class

公开(公告)号：US20220138899A1

公开(公告)日：2022-05-05

申请号：US17490754

申请日：2021-09-30

Applicant: Beijing Zhongxiangying Technology Co., Ltd. ,  BOE Technology Group Co., Ltd.

Inventor： Xiaohui ZHAO ,  Wangqiang HE ,  Libo ZHANG ,  Dong CHAI ,  Hong WANG

IPC: G06T3/40 ,  G06T5/50 ,  G06T11/60 ,  G06T3/00

Abstract: The present disclosure relates to methods and apparatuses for processing an image, training an image recognition network and recognizing an image. The method of processing an image includes: obtaining a plurality of original images from an original image set, where at least one of the plurality of original images includes an annotation area; obtaining at least one first image by splicing the plurality of original images; for each of the at least one first image, adjusting a shape and/or size of the first image based on the plurality of original images to form a second image; obtaining respective positions of the at least one annotation area in the second image by converting respective positions of the at least one annotation area in the plurality of original images.