Wood defect detection method based on deep learning and system thereof
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of deep learning and defect detection, applied in the field of visual inspection, to achieve the effects of high detection accuracy, fast speed and strong robustness
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
However, due to the complex texture and variety of defects on the surface of wood, according to national standards, wood defects can be divided into knots, discoloration, decay, insect holes, cracks, trunk shape defects, wood structure defects, scars (damages), and wood processing defects. There are 10 categories of deformation and deformation. Collecting images of wood through machine vision systems and using traditional image processing algorithms to detect wood defects will face huge challenges.
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0042] Embodiment 1: A wood defect detection method based on deep learning.
[0043] refer to figure 1 As shown, a wood defect detection method based on deep learning, specifically includes the following steps:
[0044] Step 1: The image acquisition module collects images, that is, uses a special light source for machine vision and an industrial camera to collect wood surface images;
[0045] Step 2: Divide the image into image blocks of the same size. The specific segmentation method is: take s / 2 as the step size, divide the collected image into square image blocks with the size of s*s, where the size s generally cannot Smaller than the size of the wood defect, the size of the image block can be 128*128, where 128 represents the pixel size of the side length of the divided image block;
[0046] Step 3: Select different types of defective image blocks and non-defective image blocks as training sample sets;
[0047]Among them, different types of defective image blocks and no...
Embodiment 2
[0060] Example 2: A wood defect detection system based on deep learning
[0061] A wood defect detection system based on deep learning, specifically including:
[0062] An image acquisition module, the image acquisition module is an industrial camera that adopts a linear array CCD, and can utilize a special light source for machine vision and an industrial camera to collect surface images;
[0063] Image processing module, described image processing module is the upper computer software that adopts industrial computer to carry image processing module, and this software includes image processing interactive interface, deep learning algorithm, database and communication module, can utilize deep learning algorithm to carry out wood processing to the image that collects Defect detection, and send the defect information to the control execution unit;
[0064] Control execution module: According to the defect information sent by the image processing module, the programmable logic c...
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 provides a wood defect detection method based on deep learning. The method comprises the following steps of collecting images; segmenting the images into image blocks with a same size; selecting defect image blocks with different types and non-defective image blocks as a training sample set; using the training sample set to train a deep learning algorithm in an off-line mode; and using a trained deep learning algorithm to detect and identify defects of a wood image in an online mode and the like. In the invention, through the powerful deep learning algorithm, defects on different complex texture wood surfaces are detected and identified in high precision and online modes and a problem that a traditional image processing algorithm can not solve is solved. The invention also provides a wood defect detection system based on deep learning. Through cooperation among an image acquisition module, a deep learning algorithm processing module and a control execution module, a detection speed can be effectively accelerated and practicality is increased.
Description
technical field [0001] The invention relates to the technical field of visual inspection, in particular to a method and system for detecting wood defects based on deep learning. Background technique [0002] With the intensive development of the wood processing industry, the production of wood products continues to increase significantly. In production, the high level of quality of wood surface processing, especially the requirement of consistency, makes the traditional manual detection methods incompetent. Now there is an urgent need for a high-efficiency detection method and system to realize the automation of wood defect detection. [0003] In recent years, machine vision technology has developed rapidly. In industrial production, people have successfully used this technology to automate the appearance inspection of various products. However, due to the complex texture and variety of defects on the surface of wood, according to national standards, wood defects can be div...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more