Certificate sample generation method and device, electronic equipment and storage medium
A certificate and sample technology, applied in the field of image recognition, can solve the problems of occupation, large computing resources and human resources, and achieve the effect of reducing the process of manual marking and simplifying the process of sample generation
Pending Publication Date: 2022-03-04
BEIJING TRANWISEWAY INFORMATION TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The problem solved by the present invention is that the generation method of the existing sample pictures takes up a large amount of computing resources and human resources
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
[0049] In order to make the above objects, features and advantages of the present invention more comprehensible, specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.
[0050] At present, image-based text recognition models require a large number of training samples, and the quantity and quality of training samples directly affect the accuracy of text recognition models. However, for the identification of certificates (such as vehicle driver's licenses), a lot of personal privacy content will be recorded on the current certificates, and this part of the image is easy to involve personal privacy, so it is difficult to obtain a large number of training samples, and it can even be said that , it is difficult to obtain training samples.
[0051] The existing solutions to the lack of sample images generally provide a batch of sample images first, perform more complex feature extraction, and obtain new image sa...
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 invention provides a certificate sample generation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a certificate character set, and generating a background-free first character image; randomly generating a Gaussian kernel, and performing Gaussian filtering and labeling on the first character image according to the Gaussian kernel to obtain a second character image; acquiring a certificate background image; embedding the second character image into the certificate background image to generate a certificate sample image; and outputting all the certificate sample images and the labels thereof. Therefore, the first character image is directly generated through the character set, the plurality of labeled second character images are directly obtained through Gaussian filtering, and more certificate sample images are generated by embedding the certificate background image; thus, sample pictures related to personal privacy do not need to be obtained, complex feature extraction occupying a large number of computing resources does not need to be carried out, and manual annotation occupying a large number of manual resources does not need to be carried out.
Description
technical field [0001] The present invention relates to the technical field of image recognition, in particular to a method, device, electronic device and storage medium for generating a certificate sample. Background technique [0002] At present, image-based text recognition models require a large number of training samples, and the quantity and quality of training samples directly affect the accuracy of text recognition models. But for the identification of documents, this part of the image is easy to involve personal privacy, so it is difficult to obtain a large number of training samples. [0003] The existing solutions generally provide a batch of sample pictures first, perform complex feature extraction to obtain new picture samples, and then use them as training samples after manual labeling. However, in this way, in order to obtain a sufficient number of training samples, it is still necessary to provide a large number of sample pictures, and the feature extraction...
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 IPC IPC(8): G06V30/42G06V10/774G06V10/30
CPCG06F18/214
Inventor 陈卓孙智彬夏曙东杨晓明胡道生
Owner BEIJING TRANWISEWAY INFORMATION TECH