Saliency map fusion method and system

A fusion method and remarkable technology, applied in the field of computer vision, can solve the problems of multi-computation, inconvenient use, large workload, etc., to achieve the effect of high robustness, improved universality, and simple concept

Pending Publication Date: 2020-09-04
BEIJING UNION UNIVERSITY
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method uses the method of Choquet integration for saliency map fusion, the workload is relatively large, more calculations are required, and it is not very convenient to use.

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
  • Saliency map fusion method and system
  • Saliency map fusion method and system
  • Saliency map fusion method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] Execute step 100 to perform a training process and prepare a training set, which includes a training image set D, a corresponding benchmark binary label set G, M extraction methods, and saliency map extraction results A of the M extraction methods. Execute step 110, given a Figure 1A As shown in the test image X, calculate the chi-square distance between the test image X and the 256-dimensional color histogram of the training set image. Execute step 120, the K nearest neighbors obtained after retrieval Each neighbor image X k The corresponding standard binary value is marked as α k , Represents the detection results of M methods of neighboring images, 1≤k≤K, such as Figure 1B shown. Execute step 130, according to the above assumptions, the fusion problem is formalized as a ridge regression problem, and the objective function is as follows:

[0066]

[0067] The first item is the reconstruction error of the fusion result and the benchmark binary label, the s...

Embodiment 2

[0074] The application belongs to the technical field of computer vision and the field of image processing, and discloses a saliency map fusion method. The present invention observes that different extraction methods have different extraction performances, and even the same extraction method has different extraction effects on different images. The saliency map fusion method proposed by the invention takes into account the differences in the extraction effects of different extraction methods on different images, and the performance of fusion is greatly improved compared with the performance of a single method before fusion.

[0075] Due to individual image differences, each method cannot guarantee better extraction performance on each image than all other methods. To overcome this problem, this application proposes an image-dependent saliency map fusion model to make these methods complement each other and further improve the performance of the extraction results.

[0076] Si...

Embodiment 3

[0081] In the quantitative performance evaluation, the current popular performance evaluation indicators are used:

[0082] (1) Precision rate and recall rate curve (PR curve);

[0083] (2) Receiver operating characteristic curve (ROC Curve);

[0084] The method of the present invention is referred to as FBS for short, and the PR curve figure is as figure 2 As shown, by comparing with other 14 popular methods (HS, MR, DRFI, PCA, HM, GC, MC, DSR, SBF, BD, SMD, MCDL, LEGS, and RFCN), it can be seen that the PR curve of FBS is high for all other methods.

[0085] ROC curve such as Figure 2A As shown, by comparing with other 14 popular methods (HS, MR, DRFI, PCA, HM, GC, MC, DSR, SBF, BD, SMD, MCDL, LEGS and RFCN), we can see that the ROC curve of FBS is higher than all other methods.

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 saliency map fusion method and system. The method comprises the following steps: preparing a training set; and searching neighbors of a test image X in the training set, and fitting the saliency map of the test image X through the saliency map of the neighbor image to obtain a final saliency map. According to the saliency map fusion method and system provided by the invention, the difference of different image extraction effects of different extraction methods is considered, and the fusion performance is greatly improved compared with the performance of a single methodbefore fusion.

Description

technical field [0001] The invention relates to the fields of computer vision and image processing, in particular to a saliency map fusion method and system. Background technique [0002] Image saliency detection aims to find out the most important part of the image. It is an important preprocessing step in the field of computer vision to reduce computational complexity. It has a wide range of applications in image compression, target recognition, image segmentation and other fields. At the same time, it is a challenging problem in computer vision. Each of these methods has its own advantages and disadvantages. Even for the same saliency detection method, the detection effect for different pictures is also very different. Therefore, it is particularly important to obtain better saliency maps by combining the results of multiple saliency detection methods. There are some traditional saliency map fusion methods, most of which are simple summation or simple multiplication and ...

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): G06K9/46G06K9/62G06T5/50
CPCG06T5/50G06T2207/20221G06V10/462G06F18/214
Inventor 梁晔马楠李大伟孙晨昊徐俊张磊周航王楠
Owner BEIJING UNION UNIVERSITY
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