Semantic image segmentation method and system based on deep learning and clustering

An image segmentation and deep learning technology, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve the problems of complex calculation, inconvenient extraction of feature data, complex calculation, etc., to improve robustness, avoid operation, reduce The effect of feature data noise

Active Publication Date: 2020-06-09
SOUTHWEAT UNIV OF SCI & TECH
View PDF12 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is that in the existing semantic image segmentation technology, the system data volume is large and the calculation is complicated and the feature data is difficult to form clusters, which is not convenient for extracting feature data The purpose is to provide a semantic image segmentation method and system based on deep learning and clustering to solve the problem of how to avoid complex calculations and better extract feature data

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
  • Semantic image segmentation method and system based on deep learning and clustering
  • Semantic image segmentation method and system based on deep learning and clustering
  • Semantic image segmentation method and system based on deep learning and clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] This embodiment is a semantic image segmentation method based on deep learning and clustering, the design principle is as follows figure 1 shown. That is, firstly, the deep learning method is used to realize the hierarchical nonlinear transformation of the feature data of the original image through the encoding layer of the convolutional neural network (CNN), and then transmit it to the subspace clustering layer through the highest pooling layer. The clustering method realizes the feature data clustering. Finally, in order to improve the segmentation accuracy, the present invention uses a decoding layer composed of a deep neural network to restore the original pixels of the segmented image and then output it.

Embodiment 2

[0039] This embodiment is based on Embodiment 1, and elaborates the principle of the coding layer of the deep neural network in detail. The deep neural network of this encoding layer can choose BP neural network, RNN neural network, CNN and other neural network architectures. In the present invention, the powerful function of using convolutional neural network (CNN) to extract data features from image information is adopted in the deep neural network encoder layer. Convolutional neural network (CNN) architecture, convolutional layer 1-pooling layer 1-volume Convolutional layer 2-pooling layer 2-convolutional layer 3-pooling layer 3-convolutional layer 4-pooling layer 4... Convolutional layer n-pooling layer n and other layers, through multiple convolution kernels, etc. Realize the data feature extraction and information filtering of the input image, and stop the convolution operation until the data with higher information value and cleaner is obtained. Compared with the usual...

Embodiment 3

[0041] This embodiment is based on Embodiment 1, and elaborates the subspace clustering layer design method in detail, and uses the sparse subspace clustering method to replace the fully connected layer of the CNN deep neural network. The network parameters of the fully connected layer are very large, even much larger than the parameters of multiple convolutional layers. image 3For example, if the maximum pooling is to output 20 images of 12*12, after the action of 100 neurons in the first fully connected layer, the entire image will have 100*20*12*12=288000 parameters, which undoubtedly increases Calculate time and difficulty. The present invention avoids the classification mode generated by the full connection, adopts the sparse subspace clustering method introduced into the deep neural network structure, and uses the sparse subspace clustering method to classify the feature data on the feature matrix output by the top convolution layer of the front end. Make the subspace ...

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 semantic image segmentation method and system based on deep learning and clustering, and the method comprises the following steps: S1, carrying out the convolution and pooling of an original image through a convolution neural network, and obtaining a linear feature matrix of the original image; S2, performing subspace clustering on the linear feature matrix to obtain clustered feature data; and S3, performing deconvolution and up-sampling on the clustered feature data, and processing the clustered feature data to pixels the same as those of the original image to obtain a segmented image. According to the method, the convolutional neural network (CNN) in the deep neural network is combined with subspace clustering, and the sparse subspace is used for replacing a full connection layer in the CNN, so that the problems of complex semantic image segmentation calculation, large data volume and poor information in the prior art are solved. A subspace clustering method is introduced into the neural network, so that a large amount of marking data required by the CNN during working is reduced, and unsupervised learning of the CNN neural network is realized.

Description

technical field [0001] The invention relates to the field of machine vision, in particular to a semantic image segmentation method and system based on deep learning and clustering. Background technique [0002] The purpose of semantic image segmentation is to classify the semantics of each area, that is, what is the object in this area, that is, to point out all the objects in the image to their respective categories and segment them out. At present, the methods of segmentation are usually implemented by using deep learning neural network tools to realize image segmentation and subspace clustering. But they each have advantages and disadvantages. [0003] The deep learning neural network method extracts feature data by allowing the computer to automatically learn, integrates feature learning into the process of building a model, reduces the incompleteness caused by artificially designed features, and has achieved the characteristics of better classification performance. Go...

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 Applications(China)
IPC IPC(8): G06K9/34G06K9/62G06N3/04G06N3/08
CPCG06N3/088G06V10/267G06N3/045G06F18/23G06F18/24
Inventor 郭丽刘知贵张小乾白克强薛旭倩刘道广李理张活力吴均付聪喻琼
Owner SOUTHWEAT UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap