Significant tag sorting-based image significant target detection method

A target detection, notable technology, applied in the direction of instruments, character and pattern recognition, computer components, etc.

Inactive Publication Date: 2016-11-16
BEIJING JIAOTONG UNIV +1
View PDF9 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Recently, the use of data-driven top-down methods has achieved good results in the field of image saliency extraction. Existing supervised algorithms regard the saliency

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
  • Significant tag sorting-based image significant target detection method
  • Significant tag sorting-based image significant target detection method
  • Significant tag sorting-based image significant target detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0082] The embodiment of the present invention provides a flowchart of a method for detecting salient objects in an image based on salient label sorting, as shown in figure 1 As shown, the method includes the following steps:

[0083] Step S110: establishing an image sample set from some existing datasets containing salient objects;

[0084] The above datasets include MSRA1000, ECSSD and ICOSEG.

[0085] Step S120: Divide each image in the image sample set into t image regions using SLIC (simple lineariterative clustering) segmentation method, where t is a natural number, preferably 150. And extract visual features and background contrast features for each image region, the above-mentioned visual features include color features and texture features. Each image in the image sample set is represented by the features of the image region.

[0086] The color feature of the image includes the average RGB of the pixels contained in each image area, LAB, HSV color value and the cor...

Embodiment 2

[0123] This embodiment provides an image salient object detection device based on salient label sorting, the specific structure of the device is as follows image 3 shown, including:

[0124] The image area feature acquisition module 31 is used to establish an image sample set, divide each image in the image sample set into a plurality of image areas using the SLIC segmentation method, and extract visual features and background contrast features for each image area;

[0125] The saliency label acquisition module 32 of the image region is used to extract the saliency target of each image in the image sample set by using the image saliency detection algorithm, and obtain the saliency label of each image region in each image;

[0126] The salient value acquisition module 33 of the image area is used to form a training set and a test set according to the visual features, background contrast features, and salient value labels of each image area, and use an algorithm based on the sa...

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

Embodiments of the invention provide a significant tag sorting-based image significant target detection method. The method mainly comprises the following steps of: segmenting each image in an image sample set into a plurality of image areas by using an SLIC segmentation method, and extracting visual features and background contrast features of each image area; forming a training set and a test set according to the visual features and background contrast features of each image area and significant value tags, and learning a significant value of each image area in each image by using a significant tag sorting-based algorithm; and carrying out significant image recovery on each image according to the significant value of each image area by utilizing a low-rank matrix recovery theory, and detecting a significant target in the image. According to the method provided by the invention, nuclear norms of matrixes are fully utilized to control the complexity of models, similarity of the visual features and semantic tags are combined, and the correlation between Laplacian regularization constraints on images is utilized, so that the problem that the significant tags are relatively large in space but quantity of training images is limited is effectively solved.

Description

technical field [0001] The invention relates to the technical field of article image processing, in particular to an image salient target detection method based on salient label ranking. Background technique [0002] In recent years, with the rapid development of Internet technology and multimedia information technology, multimedia information with images as carriers has gradually become an important means for people to transmit information and obtain information. However, compared with the explosive growth of image data, the computing resources that can be used to process multimedia information are very limited. Therefore, the saliency detection technology can combine the information selection ability of the human cognitive system to extract the content of interest from the complex image, rationally and effectively use the complex massive multimedia visual information resources, and occupy an important position in the field of image analysis and understanding. role. [00...

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): G06K9/20G06K9/62
CPCG06V10/225G06V2201/07G06F18/253G06F18/214
Inventor 郎丛妍李尊何伟明于兆鹏杜雪涛杜刚朱艳云
Owner BEIJING 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