Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

AI (Artificial Intelligence) based low-confidence sample processing method and system of board sorting

A low-confidence, processing method technology, applied in the fields of instruments, character and pattern recognition, computer parts, etc., can solve the problems of low-confidence samples, limited source of wooden boards, judgment and classification, etc., to improve training efficiency and improve sorting. The effect of accuracy and high classification accuracy

Active Publication Date: 2018-03-23
BEIJING WOOD AI TECH LTD
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the above board sorting scenario, the classification of each factory is customized, and its board source is also limited
Therefore, the acquisition of training data is difficult to be easily satisfied
When the machine learning method is running, a sample with low confidence will be generated, that is, the classification algorithm cannot judge the classification of the sample with a high confidence
At this time, the confidence evaluation values ​​of the sample in multiple classifications are close, so the machine cannot give a classification judgment

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • AI (Artificial Intelligence) based low-confidence sample processing method and system of board sorting
  • AI (Artificial Intelligence) based low-confidence sample processing method and system of board sorting
  • AI (Artificial Intelligence) based low-confidence sample processing method and system of board sorting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] like figure 1 As shown, a wooden board is sent into the image acquisition area through the conveyor belt, and the image acquisition is completed during the moving process of the wooden board. The photographing device collects the image of the wooden board, and inputs the collected image into the trained machine learning model.

[0076] For the machine learning method, first, a part of wood samples need to be obtained inside the factory, and the classification of each wood sample. Since wood is a semi-natural product, it is impossible to have clear classification standards like industrial products such as steel. Therefore, currently in the factory, custom classification is carried out according to the actual situation of the factory. This self-defined classification method is more suitable for the actual situation of different board factories and the classification requirements, and the classification is more flexible and convenient. The specific implementation of the ...

Embodiment 2

[0098] In the process of manual labeling, due to the ambiguity of the samples with low confidence, even manual classification still faces certain challenges. Therefore, how to better present these samples to the operator determines the labeling accuracy of low confidence samples. Here, we introduce the following implementation manners to describe specific presentation manners.

[0099] like image 3 As shown, not only the image data of low-confidence samples but also the image data of high-confidence samples are presented at the same time. By comparing the high-confidence sample data and low-confidence sample data at the same time, it is easier for the operator to compare , to recalibrate the low-confidence sample image.

[0100] For a clearer comparison, low-confidence samples and high-confidence samples, or manually labeled samples, can be presented simultaneously in the same interface. In the interface of the method, a low-confidence sample is presented, and multiple hig...

Embodiment 3

[0103] There is a possibility that the generation of low-confidence samples may be caused by changes in external ambient light, such as insufficient light intensity, or other light pollution entering the captured image. Therefore, one method preprocesses the samples, such as by enhancing the original image based on the reference image, such as normalizing parameters such as brightness, white balance, and contrast.

[0104] In order to eliminate the impact of illumination changes on image quality in the later stage, a reference image can be set during image acquisition. For example, in the image acquisition area, a white reference object is provided to ensure that the image of the wood sample and the image of the white reference object are collected at the same time. White reference objects can be used to provide a reference for white balance, brightness or other image parameters. In one manner, an external light source, such as an LED light source, is used during image acquis...

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

No PUM Login to View More

Abstract

The invention provides an AI based low-confidence sample processing method and system of board sorting. Image data of at least one format of a low-confidence sample is obtained; an image of at least one format of the low-confidence sample is presented in a display device; a new class marked by the low-confidence sample is obtained; and a training method is input to the marked low-confidence sample, and a new classification model is obtained via re-training. According to the method and system, the low-confidence sample can be discovered continuously and utilized, so that the classification precision of a machine learning method is improved gradually.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a processing method and system for low-confidence samples in machine learning, a method for classifying and labeling image samples in machine learning, a system and a computer program product thereof. Background technique [0002] In the field of wood processing, wood sorting is an important link. After the logs are shaped, colored, dried and other processes, they become processed wood boards. Before wooden boards become commercialized products, they need to be classified according to different board characteristics. In traditional methods, the sorting of the boards is done manually. Trained workers, through observation, judge the color, texture, and defects of each plank, and then classify a plank into different categories based on experience. The wood boards in each category have closer characteristics, achieving higher consistency in product appe...

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
no application Login to View More
IPC IPC(8): G06K9/62
CPCG06F18/2415G06F18/214
Inventor 丁磊
Owner BEIJING WOOD AI TECH LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com