Dual-channel output contour detection method based on encoding and decoding structures

A contour detection, dual-channel technology, applied in the field of image processing and computer vision, can solve the problems of rough contour lines, inaccurate positioning, unbalanced training samples, etc., achieve fine contour lines, reduce feature information loss, and increase generalization ability Effect

Active Publication Date: 2020-09-18
NANKAI UNIV
View PDF9 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At this stage, the contour detection algorithm based on convolutional neural network mainly has difficulties such as rough contour line detection, inaccurate positioning, and unbalanced training samples.

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
  • Dual-channel output contour detection method based on encoding and decoding structures
  • Dual-channel output contour detection method based on encoding and decoding structures
  • Dual-channel output contour detection method based on encoding and decoding structures

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention uses the GeForce GTX1080Ti model GPU of NVIDIA Corporation to train the contour detection model, the operating system is 64-bit Ubuntu 16.04, and the video memory is 10G. The programming language is Python 3.6, and the deep learning framework is TensorFlow 1.14 and Keras 2.2.5.

[0027] The following is a detailed introduction to the core module composition and loss function fusion strategy of the present invention in conjunction with the accompanying drawings. At the same time, taking the BSDS500 public data set as an example, the specific implementation steps of model training and detection are introduced.

[0028] The present invention uses the modified VGG16 as a feature extraction network, removes the fully connected layer and the final pooling layer of VGG16, and divides the encoding stage into five feature map extraction modules. Through bottom-up layer-by-layer decoding to fuse feature maps of different scales, the loss of image feature inf...

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 provides a dual-channel output contour detection method based on encoding and decoding structures. In the encoding stage, image feature information is extracted through an improved VGG16network, in the decoding stage, feature information of different scales is fused from bottom to top, and the same label is used for carrying out deep supervision on output contour images of two channels. According to the method, the feature maps of different scales are fused in a bottom-up layer-by-layer decoding mode, so that the extracted image feature information is richer; adding a channel attention structure in a feature fusion stage, and performing feature map sampling by using sub-pixel convolution; a proper loss function is designed to solve the problem of imbalance of training samples; and a data set is amplified by using a data enhancement method, so that the generalization ability of the model is improved. According to the method, the target contours of the BSDS500 public dataset and the customized woodcarving contour detection data set can be effectively extracted, and the detection contour lines are fine.

Description

technical field [0001] The invention belongs to the field of image processing and computer vision, and relates to a dual-channel output contour detection method based on an encoding and decoding structure, which is essentially a problem of binary classification of image pixels by using a convolutional neural network. Background technique [0002] Contour detection is the core task in the field of computer vision. Extracting the target contour in the image through the rich feature information of the digital image is the basis of advanced visual tasks such as target detection, semantic segmentation, and defect recognition. Accurately extracting image target contours is still a challenging task due to factors such as lighting, camera equipment precision, and target contour complexity. [0003] The traditional edge detection operator method is to detect the contour by looking for pixels with obvious brightness changes in the digital image. The contour detection method based on ...

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): G06K9/48G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V10/46G06N3/045G06F18/253Y02T10/40
Inventor 陈利王晓东蔡欣展刘艳艳
Owner NANKAI UNIV
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