An automatic recognition method for waste paper categories based on fusion classification, detection and segmentation
An automatic identification, classification and detection technology, applied in the field of computer vision, can solve problems such as the inability to meet the needs of large quantities of sorted goods, and achieve the effects of high accuracy, convenient pricing, and improved efficiency.
Active Publication Date: 2021-07-09
CHANGSHA PENGYANG INFORMATION TECH
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the above sorting methods still cannot meet the uninterrupted and large-volume sorting needs of modern enterprises.
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
[0032] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings, but the present invention can be implemented in various ways defined and covered by the claims.
[0033] See figure 1 , the present embodiment provides a method for automatic recognition of waste paper categories fused with classification, detection and segmentation, comprising the following steps:
[0034] 1. Install the camera and lighting equipment above the conveyor belt, and adjust the position so that the camera can shoot images of the waste paper on the conveyor belt vertically from top to bottom to obtain predicted waste paper images; among them, the camera can use a high-definition dome camera.
[0035] 2. Divide the predicted waste paper image obtained in step 1 into n×n sub-predicted waste paper images, and use machine learning methods to classify each sub-predicted waste paper image to obtain the category of each sub-predicted waste paper i...
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 discloses an automatic recognition method of waste paper categories by fusion of classification, detection and segmentation, which comprises acquiring a predicted waste paper image; dividing the obtained predicted waste paper image into several blocks of predicted waste paper images, and for each block of predicted waste paper images, Use machine learning methods to classify, and obtain category information and confidence information of sub-predicted waste paper image blocks; use image detection technology based on machine learning to detect waste paper categories and corresponding location information in predicted waste paper images; Segment the obtained predicted waste paper image; fuse the classification, detection and segmentation results of the predicted waste paper image to obtain the final waste paper category recognition result; statistically predict the position and proportion of each waste paper category in the waste paper image To achieve automatic recognition of waste paper images. Compared with the traditional image classification method, the waste paper classification recognition method of the present invention greatly improves the waste paper classification efficiency and has high accuracy.
Description
technical field [0001] The invention relates to the field of computer vision and artificial intelligence technology, in particular to an automatic recognition method of waste paper classification integrated with classification, detection and segmentation. Background technique [0002] Waste paper refers to recyclable renewable resources that are discarded after use in production and life, including various high-grade paper, yellow cardboard, waste cartons, edge-cut paper, packing paper, paper for enterprises and units, engineering paper, books and periodicals Newspapers and more. Waste paper recycling can produce huge economic and environmental benefits in terms of reducing pollution, improving the environment, saving virgin fiber resources and energy, and protecting forest resources. aspect. [0003] The classification of waste paper plays a decisive role in the recycling and reuse of waste paper. It has a huge role in promoting the conservation of forestry resources in ...
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): G06K9/34G06K9/46G06K9/62
CPCG06V10/267G06V10/44G06F18/25G06F18/241
Inventor 涂丹徐新文朱为谢志恒胡青霞王涛徐东
Owner CHANGSHA PENGYANG INFORMATION TECH