Wooden board sorting method and system based on machine learning

Abstract

The invention provides a wooden board sorting method and system based on machine learning. The method comprises steps that firstly, image samples of wooden boards having different moving speeds are acquired under the different environments, secondly, free definition classification of the wooden boards is carried out, and the corresponding relationship between the image sample and free definition classification is established; images of the wooden boards are acquired, the acquired wooden board images are analyzed through the learned neural network, wooden board classes and the classification operation execution time are determined, and classification operation of the wooden boards is carried out at the time to classify the wooden boards to the determined classes. The method and the system are advantaged in that an automatic sorting machine is made to rapidly adapt to continuously changing product classification demands, the changeable disposition environment, high-difference timber materials and the paint spray process.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a method and system for sorting wood boards based on machine learning. Background technique [0002] In the field of wood processing, wood sorting is an important link. Whether it is a semi-finished product or a finished product after molding, coloring, drying and other processes, it needs to be classified according to different wood characteristics and quality standards. In traditional methods, the sorting of the boards is done manually. Trained workers, through observation, judge the color, texture, defects, etc. of each board, and classify a board into different categories based on experience. The wood boards in each category have closer characteristics, achieving higher consistency in product appearance and quality. [0003] However, the manual sorting method consumes a lot of human resources, and because the material and coloring process of eac...

AI Technical Summary

Problems solved by technology

[0006] However, the inventor discovered in the process of realizing the present invention that the existing machine learning method only partially solves the problem of standardization, and fails to solve the most critical adaptability problem in wood classification

Specifically, the current standard of wood board classification is usually defined by the manufacturer, which means that the current wood board classification is essentially non-standardized; the machine learning method in the prior art adopts a pre-training method, which can only train a specific wood board for a specific manufacturer. model, obviously cannot be used universally among multiple manufacturers

In addition, wood is essentially produced in batches, and each batch of betta products is highly related to the log material and painting process of the batch, and there may be huge differences between different batches; but the training in the existing technology The model is completely dependent on the sample batch and cannot be dynamically adjusted for different batches

Finally, the change of natural light will have a great impact on visual recognition. The existing technology does not consider the standardization under the change of ambient light, and cannot adapt to the detection of different environments.

[0007] Therefore, there is currently a lack of adaptive detection methods, and existing technologies cannot meet the needs of rapid deployment, nor can they run robustly in changing operating environments.

Images