Method and device for acquiring training sample data set of image segmentation model
A sample data set and image segmentation technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of asymmetric stitching combined image recognition and poor segmentation effect, and reduce the manual review rate and manual review. cost, improve audit efficiency, and avoid the effect of audit results errors
Pending Publication Date: 2021-06-11
上海眼控科技股份有限公司
View PDF0 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The purpose of this application is to provide an image segmentation model training sample data set acquisition method and equipment to solve the technical problem in the prior art that the identification and segmentation of asymmetric spliced combined images are not good
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
[0057] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0058] In a typical configuration of the present application, each module and trusted party of the system includes one or more processors (CPU), input / output interface, network interface and memory.
[0059]Memory may include non-permanent storage in computer readable media, in the form of random access memory (RAM) and / or nonvolatile memory such as read only memory (ROM) or flash RAM. Memory is an example of computer readable media.
[0060] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can be implemented by any method or technology for storage of information. Information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynami...
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
According to the method and device for obtaining the training sample data set of the image segmentation model, a plurality of sample images are obtained firstly, each sample image is composed of a plurality of spliced images, then boundary areas between the spliced images in each sample image are determined, each sample image is labeled with a label, and then noise reduction processing is performed on each sample image after labeling, and finally all the sample images after noise reduction processing and the corresponding labels are determined as a training sample data set of the image segmentation model. The training sample data set obtained by the method is used for training the classification regression neural network model to obtain the image segmentation model, so that each spliced image in the image formed by combining a plurality of spliced images in a splicing combination mode can be accurately identified and segmented, and the subsequent image auditing efficiency can be improved; the manual rechecking rate and the manual rechecking cost are reduced, and meanwhile, the defect that rechecking results are wrong due to the fact that rechecking personnel are prone to fatigue can be avoided.
Description
technical field [0001] The present application relates to the technical field of computer image processing, and in particular to a technique for acquiring image segmentation model training sample data sets. Background technique [0002] In the field of transportation, in order to save storage space and not occupy too much transmission bandwidth, images captured by cameras installed at road checkpoints and other places are usually spliced into one image and then stored locally or transmitted to the backend. Check for violations of laws and regulations. There are various splicing and combination modes for such images, such as figure 1 shown. [0003] Reviewers are prone to fatigue after working for a long time, which affects the accuracy of the review, and manual review needs to be arranged, which requires more human resource investment. At present, a neural network model based on deep learning is also used to intelligently identify and segment each spliced image for ma...
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 Applications(China)
IPC IPC(8): G06K9/34G06K9/62G06K9/46G06K9/40
CPCG06V10/267G06V10/30G06V10/44G06F18/24G06F18/214
Inventor 黎阳申影影潘柳华徐麟
Owner 上海眼控科技股份有限公司