Depth study based method for detecting salient regions in natural image

A technology of deep learning and detection method, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of poor detection effect in significant areas, and achieve high discrimination, robustness, and high detection accuracy

Active Publication Date: 2014-05-21
NORTHWESTERN POLYTECHNICAL UNIV
View PDF2 Cites 52 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem of poor salient area detection in natural images by existing methods, the present invention proposes a bottom-up deep learning-based natural image

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
  • Depth study based method for detecting salient regions in natural image
  • Depth study based method for detecting salient regions in natural image
  • Depth study based method for detecting salient regions in natural image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0044] The hardware environment used for implementation is: Intel Pentium2.93GHz CPU computer, 4.0GB memory, and the running software environment is: Matlab R2011b and Windows7. We use the MIT and Toronto databases published on the Internet to conduct our experiments. The MIT database contains 1003 natural images, and the Toronto database contains 120 images. We have realized the method that the present invention proposes with Matlab software.

[0045] The present invention is specifically implemented as follows:

[0046] Step 1 extracts the visual features of the image data:

[0047] The present invention uses cross-validation to select 903 images each time (the last time is 900 images) for training, and uses the remaining images for testing. First, extract 37-dimensional features from each picture in the training set. The following describes the extraction m...

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 relates to a depth study method for detecting salient regions in a natural image. During a training phase, a certain number of pictures are selected from a natural image database, basic features of the images are extracted to form a training sample, subsequently, the extracted features are studied by using a depth study model so as to obtain enhanced advanced features which are more abstractive and more distinguishable, and finally, a classifier is trained by using studied features. During a testing phase, as to any test image, firstly, the base features are extracted, secondly, the enhanced advanced features are extracted by using the trained depth model, finally, salience is predicted by using the classifier, and a predicted value of each pixel point serves as a salient value of the point. In such a way, a salient image of the whole image can be obtained, and the higher the salient value is, the more salient the image is.

Description

technical field [0001] The invention relates to a method for detecting salient regions in natural images based on deep learning, which can be applied to the salient detection of multiple regions in natural images under complex backgrounds. Background technique [0002] Salient region detection of natural images has always been a research hotspot in the field of image processing and computer vision. So far, there have been a large number of research structures and research groups engaged in research in this area, and very good results have been achieved. [0003] According to the division of visual information processing, the visual attention process can be divided into two parts, namely bottom-up (bottom-up) and top-down (top-down) visual attention. The bottom-up visual attention model constructs the attention process by directly calculating the visual saliency of low-level features, which has the characteristics of fast speed, no conscious control, and forward propagation. ...

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): G06K9/66
Inventor 韩军伟闻时锋张鼎文郭雷
Owner NORTHWESTERN POLYTECHNICAL 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