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

Intelligent classification method of solid wood board color

A classification method and plate technology, applied in the field of image recognition, can solve the problems of high image feature dimension, false detection, unfavorable retrieval, etc., and achieve the effect of low feature vector dimension

Active Publication Date: 2022-02-01
NANJING FORESTRY UNIV
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Quantization processing can easily lead to false detection, and the generated image feature dimension is high, which is not conducive to retrieval

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
  • Intelligent classification method of solid wood board color
  • Intelligent classification method of solid wood board color
  • Intelligent classification method of solid wood board color

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The specific embodiment of the present invention is described further below according to accompanying drawing:

[0031] An intelligent classification method for solid wood board color, such as figure 2 shown, including:

[0032] Step 1: Collect multiple pictures of solid wood panels, and preprocess the pictures of solid wood panels.

[0033] During the acquisition process of the solid wood panel image, the background information of the solid wood panel will also be stored in the picture, which will have a certain impact on the feature extraction of the solid wood panel image, so a series of preprocessing is performed on the solid wood panel image, including Image smoothing, image sharpening, image morphological operations, and image background removal for solid wood panels. The specific preprocessing process is as follows figure 1 shown.

[0034] Step 2: Transform each solid wood panel picture from RGB color space to Lab color space and HSV color space respectively...

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 discloses a method for intelligently classifying the color of solid wood boards, which includes: preprocessing the pictures of solid wood boards; converting RGB color space to Lab color space and HSV color space; obtaining the first-order moment sum of colors in Lab color space and HSV color space The second moment; use the K-Means clustering algorithm to cluster the pictures; use the main color extraction method based on the K-Means clustering algorithm to extract the main colors of the solid wood board pictures after low-pass filtering, and grade according to the content of the main colors Divide; perform high-pass filtering on the picture to obtain texture information, and divide the picture into straight or curved lines; label the pictures of solid wood panels to make a sample set; input the pictures of solid wood panels to be classified into the optimal color classification obtained by training and verification In the model, the color classification of solid wood boards is realized; the invention can effectively classify the image colors of solid wood boards, and the method does not need color space quantization and has low dimensionality of feature vectors.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to an intelligent color classification method for solid wood boards. Background technique [0002] Color moments are a simple and effective representation method of color features. There are first-order moments (mean, mean), second-order moments (variance, variance) and third-order moments (slope, skewness), etc. Since color information is mainly distributed in low-order Moments, so the first-order moment, second-order moment and third-order moment are sufficient to express the color distribution of the image, and the color moment has been proved to be effective in representing the color distribution in the image. [0003] Color is one of the most important contents of color images and is widely used in image retrieval. However, when extracting color features from an image, many algorithms must first quantify the image. Quantization processing is easy to caus...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/90G06V10/56G06V10/762G06V10/764G06V10/82G06K9/62G06N3/08G06N20/00
CPCG06T7/0004G06T7/90G06N20/00G06N3/088G06T2207/10024G06T2207/20081G06T2207/30161G06V10/56G06F18/23213G06F18/241
Inventor 刘英王争光丁奉龙杨雨图倪超庄子龙周海燕费叶琦唐敏缑斌丽
Owner NANJING FORESTRY UNIV
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