Salient image extraction method and device
A salient and image technology, applied in the field of image processing, can solve the problems of time-consuming, slow extraction of salient images, low efficiency of extraction of salient images, etc., and achieve the effect of improving extraction efficiency.
Active Publication Date: 2021-10-26
BEIHANG UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In the above process, it takes a lot of time to segment the original image, and it takes a lot of time to process each superpixel block or image block, which makes the process of extracting salient images in the original image relatively difficult. Slow, resulting in low efficiency in extracting salient images
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
[0056] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0057] figure 1 It is a schematic diagram of the application scene of the salient image extraction method provided by the embodiment of the present invention. See figure 1 , the prediction model includes a viewpoint information extraction module, a semantic information extraction module and a detection module. When it is necessary to extra...
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
Embodiments of the present invention provide a salient image extraction method and device. The method includes: performing first convolution processing, first pooling processing, and normalization processing on the original image through a prediction model to obtain the viewpoint information of the original image, and the viewpoint The information is used to indicate the area of the salient object in the original image; the second convolution processing and the second pooling processing are performed on the original image through the prediction model to obtain the semantic description information of the original image, and the semantic description information is used to describe the original image. Content; the viewpoint information and semantic description information are detected and processed by the prediction model, and the salient image of the original image is obtained. Used to improve the efficiency of extracting salient images.
Description
technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and in particular, to a salient image extraction method and device. Background technique [0002] The original image usually includes a foreground image and a background image. The foreground image is usually a salient image in the original image. In practical applications, it is necessary to extract salient images from the original image in many application scenarios. [0003] At present, when it is necessary to extract a salient image in the original image, the original image is first segmented according to the RGB value of each pixel in the original image and the position of each pixel to obtain multiple superpixel blocks or image blocks, and then the preset The network model performs feature extraction on each superpixel block or image block, obtains the convolutional neural network features of the superpixel block or image block, and obtains a saliency map base...
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): G06K9/46G06V10/764
CPCG06V10/464G06V10/56G06T2207/20081G06T2207/20084G06T7/143G06T7/11G06T7/194G06T2207/10024G06T2207/20076G06V40/193G06V10/454G06V10/462G06V10/82G06V10/764G06T3/4007G06T2207/20104G06V40/18G06F18/24143
Inventor 陈小武郑安林李甲赵沁平陆峰
Owner BEIHANG UNIV