A method and device for saliency detection based on extensive learning system
A technology of learning system and detection method, applied in the fields of instrument, calculation, character and pattern recognition, etc., can solve problems such as poor effect, and achieve the effect of fast training
Active Publication Date: 2021-05-18
SHANGHAI NORMAL UNIVERSITY
View PDF10 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] However, when the existing saliency algorithm performs saliency detection, due to fewer features considered, the final effect is often poor.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0048] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is carried out on the premise of the technical solution of the present invention, and detailed implementation and specific operation process are given, but the protection scope of the present invention is not limited to the following embodiments.
[0049] A saliency detection method based on a breadth learning system, which is implemented by a computer system in the form of a computer program. The computer system is a saliency detection device, including a memory, a processor, and a memory stored in the memory and executed by the processor. program, such as figure 1 As shown, the processor implements the following steps when executing the program:
[0050] Step S1: Divide the image into multiple superpixels, extract the color, position, texture, prior and contrast information of each superpixel, and obtain the feature vector of...
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
Login to View More Abstract
The present invention relates to a saliency detection method and device based on a breadth learning system, wherein the method includes: step S1: dividing an image into multiple superpixels, and extracting the color, position, texture, prior and contrast of each superpixel information, and obtain the eigenvectors of each superpixel; step S2: process the image based on the obtained eigenvectors of each superpixel, and obtain an initial saliency map; step S3: establish a conditional random field model for the initial saliency map, and use the width-based The learned regression calculates the kernel matrix in the conditional random field, and uses the obtained optimal solution as the optimized saliency map; step S4: use the obtained optimized saliency map for visual tracking, image classification, image segmentation, and target recognition, Image video compression, image retrieval or image redirection. Compared with the prior art, the present invention combines color features, spatial features, texture features, prior features and contrast features in the feature extraction stage to improve the detection effect.
Description
technical field [0001] The invention relates to a saliency detection technology, in particular to a saliency detection method and device based on a breadth learning system. Background technique [0002] In recent years, saliency detection has become one of the hot topics in the field of computer vision, attracting the interest of a large number of scholars. Many excellent algorithms have emerged in this field, but it is still difficult to develop a simple and practical saliency model. At present, saliency detection has been widely used in visual tracking, image classification and image segmentation, object recognition, image video compression, image retrieval, image redirection and other related fields. [0003] According to different detection models and functions, saliency detection algorithms can be divided into visual attention detection and salient object detection. Among them, visual attention detection is to estimate the change trajectory of the gaze point when the ...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/46G06K9/62
CPCG06V10/462G06F18/2411G06F18/214
Inventor 林晓李想王志杰黄继风郑晓妹盛斌
Owner SHANGHAI NORMAL UNIVERSITY