Artificial neural network for defect detection in CT images of wood

The timely detection of defects in wood helps optimize operation of sawmills and find effective log processing solutions. This paper aims to develop effective method for automated wood defect detection and recognition in CT images using a multiple-layer convolutional neural network and a reinforceme...

Full description

Saved in:

Bibliographic Details
Published in:	Computers and electronics in agriculture 2021-08, Vol.187, p.1
Main Authors:	Pan, Ligong, Rogulin, Rodion, Kondrashev, Sergey
Format:	Article
Language:	eng
Subjects:	Applications programs Artificial neural networks Computed tomography Learning theory Neural networks Object recognition Performance measurement Prediction models Research facilities Sawmills Tomography Training
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	The timely detection of defects in wood helps optimize operation of sawmills and find effective log processing solutions. This paper aims to develop effective method for automated wood defect detection and recognition in CT images using a multiple-layer convolutional neural network and a reinforcement learning strategy. The data augmentation technique was proposed to increase the volume of training, validation, and test sets. The network can achieve sufficient accuracy up to 98.7% at a total set of 500 images. The study shows a direct non-linear relationship between the dimension of the training set and the recognition rate. The results of calculating performance metrics for the developed method indicate the high accuracy of the ANN prediction model. The study results will be useful in designing software applications for industrial and laboratory CT scanners that are used in lumber production and R&D centers. The proposal can be improved to perform wood defect detection and recognition in color and 3D CT images of logs.
ISSN:	0168-1699 1872-7107