Emerald product identification method, system, terminal, computer equipment and storage medium
An identification method and emerald technology, applied in the fields of systems, computer equipment and storage media, terminals, and emerald product identification methods, can solve the problems of difficulty in dealing with occlusion, noise sensitivity, slow speed, etc. The effect of wide space and improved accuracy
Active Publication Date: 2022-06-24
深圳市对庄科技有限公司
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] (1) However, the HOG emerald product identification method is lengthy, slow, and poor in real-time performance; it is difficult to deal with occlusion problems
[0006] (2) Due to the nature of the gradient, it is quite sensitive to noise
And can not identify specific jadeite product category objects
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
[0037] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.
[0038] Aiming at the problems existing in the prior art, the present invention provides a method for identifying jadeite products, a data processing terminal, a computer device and a storage medium. The present invention is described in detail below with reference to the accompanying drawings.
[0039] The present invention provides a method for identifying jadeite products based on machine learning, which is applied to a data processing terminal. The method for identifying jadeite products based on machine learning includes:
[0040] Obtain the positive and negative sample data in the jade product pictures as samp...
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 belongs to the technical field of pre-processing of jadeite product classification, and discloses a jadeite product identification method, system, terminal, computer equipment and storage medium for obtaining positive sample data and negative sample data in pictures of jadeite product, according to a certain sample ratio, the The positive sample data and the negative sample data are made into labels as the sample data of the training network; the pre-trained SSD training network is used to find out the emerald product object in the image in the sample data, and determine the category and position of the object at the same time. The invention can detect whether the jadeite product is contained in the picture, thereby effectively improving the classification accuracy of the jadeite product. Compared with various algorithms of traditional digital image processing, the present invention has higher accuracy, wider applicable places and shorter recognition time.
Description
technical field [0001] The invention belongs to the technical field of pre-processing of jadeite product classification, and in particular relates to a jadeite product identification method, system, terminal, computer equipment and storage medium. Background technique [0002] At present, most of jadeite product identification uses traditional digital image processing. On the one hand, it is not applicable to a wide range of scenarios, mainly for single and simple scenarios. Therefore, it is outdated in today's need for accurate and fast image recognition of jadeite products. [0003] HOG features (prior art) are used for object detection, and in order to find a local object, its contours must be found. Generally speaking, there is a relatively obvious gradient at the edge of the object, and the color change of the background or the interior of the object is not obvious, so the gradient is not obvious, so the appearance and shape of the object can be better described by the...
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): G06V10/764G06V10/82G06K9/62G06N3/08G06N20/00
CPCG06N3/084G06N20/00G06V2201/07G06F18/24133
Inventor 孙操易金鹏王秀辉
Owner 深圳市对庄科技有限公司