Global-local optimization model based on multistage convolution neural network and significant detection algorithm

A convolutional neural network and local optimization technology, applied in computing, computer components, character and pattern recognition, etc., can solve problems such as dependence on computing speed, limited running speed, and speed of segmentation algorithms

Active Publication Date: 2016-06-22
XI AN JIAOTONG UNIV
View PDF3 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The effect and operation speed of this method depend greatly on the segmentation algorithm. On the one hand, the boundary division of salient objects depends entire

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
  • Global-local optimization model based on multistage convolution neural network and significant detection algorithm
  • Global-local optimization model based on multistage convolution neural network and significant detection algorithm
  • Global-local optimization model based on multistage convolution neural network and significant detection algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention provides a saliency detection algorithm based on a multi-level convolutional neural network. The global-local optimization model (GE-RM) based on the convolutional neural network is composed of a global estimation model (GEM) and a local optimization model ( RfM) composition;

[0035] The global estimation model has two output paths, the initialization branch path and the main path.

[0036] The initialization branch path of the global estimation model consists of a cascade of parts A and B, and part A consists of seven convolutional layers and three pooling layers. The preferred connection order is:

[0037] conv1-pool1-conv2-conv3-conv4-pool2-conv5-conv6-pool3-conv7,

[0038] Among them, conv1 is the input;

[0039] Part B consists of two cascaded fully connected layers (FC), of which the fully connected layer at the end is used as the output layer; preferably, the output layer has 4096 output units, which can form a 64x64 saliency map.

[004...

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 significant detection algorithm based on a multistage convolution neural network. The algorithm comprises the following steps of using a global estimation model of a large receptive field to carry out global significance estimation; during a global estimation model training process, using a full connection layer as an output layer to train and initialize parts of convolution layer parameters; using a plurality of alternative convolution layers and liter sampling layers to replace the full connection layer and training and acquiring an optimal global significance estimation graph; using a local convolution neural network with a small receptive field and a large output picture size to fuse global and local information to acquire a high quality significance graph. Through processing of the local convolution neural network, an original image is served as input of the model. A final output result possesses a same size with an original input image and is clear. By using the significant detection algorithm based on the multistage convolution neural network, compared to a traditional method, high accuracy is possessed; a significant object can be accurately found and simultaneously a contour is clear.

Description

【Technical field】 [0001] The invention relates to a method for visual saliency detection in natural images based on a deep convolutional neural network, which is applied to the detection of salient target areas under complex backgrounds. 【Background technique】 [0002] Human vision can quickly find salient objects in the surrounding environment, ignore some information that is not of interest to humans, and focus on important parts of visual images, which can avoid the brain from processing complicated and useless information. Visual saliency detection is to simulate the rapid human perception of environmental behavior. [0003] With the popularization of various digital devices and the rapid development of the Internet, there are more and more pictures and video data. Similar to human vision, computers can extract saliency information in pictures through saliency detection of images or videos, and quickly locate areas in images that need to be processed. Through visual sa...

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
IPC IPC(8): G06K9/62
CPCG06F18/24
Inventor 王飞汪子钦姜沛林
Owner XI AN JIAOTONG 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