Image sample set generation method, device, computer equipment and storage medium
A technology of image generation and sample collection, which is applied in the field of character recognition, can solve the problems of improvement, cost more computing resources, and difficulty in significantly improving recognition accuracy, so as to achieve the effect of improving recognition accuracy and improving recognition ability
Active Publication Date: 2022-03-08
中电金信软件有限公司
View PDF15 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, randomly adding character pictures will easily lead to the need for more computing resources in the training process of the picture recognition model. Moreover, since there are usually many characters to be recognized, when it is necessary to improve the recognition accuracy of the picture recognition model, it often occurs Even if the image samples are increased and more computing resources are spent, it is difficult to significantly improve the recognition accuracy
[0004] Therefore, the current image sample generation technology used for image recognition models has the problem of being difficult to significantly improve the recognition accuracy.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0048] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.
[0049] In one embodiment, such as figure 1 As shown, a method for generating a picture sample set is provided, which can be applied to a terminal or a server, wherein the terminal can be but not limited to various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server can be It can be implemented with an independent server or a server cluster composed of multiple servers. Taking this method applied to the server as an example for illustration, it includes the following steps:
[0050] Step S110, generating a t...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present application relates to a method, device, computer equipment and storage medium for generating a picture sample set. The method includes: generating a test sample set based on an object; the test sample set includes at least one test sample; performing a recognition operation on the at least one test sample through the image recognition model, and determining that the recognition of the object is accurate according to the recognition result rate; use the object corresponding to the recognition accuracy rate that meets the preset conditions as the object to be strengthened; perform a strengthening operation on at least one object to be strengthened to obtain a strengthened sample set, so as to use the strengthened sample set to carry out the image recognition model train. The method can be used to strengthen the object to be strengthened, and the picture recognition model can be trained by using the strengthened picture sample set, which can improve the recognition ability of the picture recognition model for the object to be strengthened, so that the recognition accuracy of the picture recognition model can be significantly improved.
Description
technical field [0001] The present application relates to the technical field of character recognition, in particular to a method, device, computer equipment and storage medium for generating a picture sample set. Background technique [0002] With the development of image recognition technology, Optical Character Recognition (OCR, Optical Character Recognition) technology has emerged. Optical character recognition can use pre-trained image recognition models to identify characters in pictures, and use character pictures as training samples to character models. For training, the picture recognition model can be obtained by training a certain number of character pictures. Usually, the improvement of the recognition accuracy depends on the increase of the number of picture samples. The more picture samples, the higher the recognition accuracy. [0003] At present, the number of image samples in the image recognition model is increased by randomly adding character images. Howe...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06V10/774
CPCG06F18/214
Inventor 刘洋
Owner 中电金信软件有限公司