Image compression method based on salient object detection model
A technology of object detection and image compression, which is applied in image communication, digital video signal modification, electrical components, etc. It can solve the problems that the transmission rate cannot meet the demand, it is difficult to achieve real-time processing, and the loss of detailed information, etc., to achieve variable resolution , high compression rate, to achieve the effect of image compression
Inactive Publication Date: 2018-07-06
FUZHOU UNIV
View PDF7 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] With the rapid development of science and technology, the obtained image resolution is getting higher and higher, and the current transmission rate cannot meet the demand, so it is necessary to compress the image
Image compression is an important research field of image processing. The existing compression methods either lose important details and cannot meet the needs of actual applications, or the compression rate is too low to meet the requirements of real-time processing.
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
[0055] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.
[0056] The purpose of the present invention is to solve the problems existing in the existing image compression methods, and to provide an image compression method based on salient object detection. The present invention can pass through the detected salient objects to compress the object area and the background differently. compression rate. Technical scheme of the present invention is as follows:
[0057] S1. Use the salient object detection model of the deconvolution attention residual module to obtain candidate detection boxes;
[0058] S2. Using a greedy non-maximum value suppression method to eliminate redundant detection frames from the candidate detection frames;
[0059] S3. Then compress the image by reducing the compression ratio according to the detected salient objects according to the confidence value.
[0060] Further, t...
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 invention provides an image compression method based on salient object detection. The method comprises the following steps: firstly, in a salient object detection model, using a deconvolution attention residual module to increase context information so as to improve the detection accuracy; secondly, using a greedy non-maximum suppression method to eliminate redundant detection frames from manysalient object candidate detection frames to find an optimal salient object position; and finally, using an image compression standard based on wavelet transform to compress salient regions and backgrounds with different compression ratios.
Description
technical field [0001] The invention belongs to the field of digital image processing, in particular to an image compression method based on a salient object detection model. Background technique [0002] With the rapid development of science and technology, the obtained image resolution is getting higher and higher, and the current transmission rate cannot meet the demand, so the image needs to be compressed. Image compression is an important research field of image processing. Existing compression methods either lose important details and cannot meet the needs of practical applications, or the compression rate is too low to meet the requirements of real-time processing. The visual attention mechanism is introduced into image compression, and different compression rates are used for the salient area and the background, so that not only can a high compression rate be achieved for the entire image, but also the high resolution of important areas can be maintained, and variabl...
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 Applications(China)
IPC IPC(8): H04N19/42H04N19/543
CPCH04N19/42H04N19/543
Inventor 余春艳徐小丹杨素琼陈立王秀
Owner FUZHOU UNIV