Image Saliency Detection Method Based on Fuzzy Estimation Fusion
A detection method and remarkable technology, applied in the fields of computing, computer parts, character and pattern recognition, etc., to achieve the effect of strong robustness, good theoretical basis, and accurate results
Active Publication Date: 2019-04-26
WUHAN UNIV
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the currently popular bottom-up and top-down saliency detection method does not involve the use of the photographer's psychological characteristics to assist in saliency detection, and the photographer's shooting psychology is of great significance to the understanding of 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
[0032] The method proposed by the invention combines the bottom-up saliency detection method with the top-down saliency detection method, proposes a framework for simulating and quantifying the psychology of the photographer when shooting, and compares the results of the simulation and quantification It is used to guide the fusion of saliency information under different mechanisms, and comprehensively utilizes the low-level visual features and blur features of images for detection.
[0033] The present invention first calculates the low-level visual feature map of the image according to the input image data to be detected; secondly, simulates the psychological characteristics of the photographer when shooting to perform image fuzzy estimation, calculates the visual positioning point of the viewer, and obtains the corresponding visual density map as A high-level visual feature map of an image. Then use the image blur estimation results to quantify the photographer's intention p...
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 provides an image saliency detection method based on fuzzy estimation fusion, which includes a low-level visual feature acquisition stage and a fuzzy feature application stage. The image is detected by the feature detection algorithm, and the detected salient feature map is used as the low-level visual feature acquisition result of the image to be detected. In the application stage of the fuzziness feature, first input multiple sets of training image blocks, and train the sparse dictionary; then use fuzzy estimation to simulate the psychological characteristics of the photographer when shooting and quantify it, and use the quantification results to guide the image processing under different mechanisms. The fusion of saliency information obtains the final image saliency detection results to improve the saliency detection accuracy. The image saliency detection result obtained by the present invention is more in line with the human visual saliency detection mode. At the same time, it has better robustness and higher detection accuracy.
Description
technical field [0001] The invention relates to the field of image saliency detection, in particular to an image saliency detection method based on fuzzy estimation. Background technique [0002] In recent years, with the continuous development of digital technology, the size of photos has become larger and higher, the resolution has become higher and higher, and the information contained in photos has become more and more abundant. If you want to process all the information in the image in time, it is very important for computer image System is not a small challenge. Therefore, there is a need for a selection mechanism to assist in the selective processing of the information in the image, so as to reduce the burden on the image processing system. Human visual saliency can help the human visual system to distinguish areas containing important information in an image while reducing the interference of background areas. By applying the visual saliency model to the field of c...
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): G06K9/32G06K9/46
CPCG06V10/255G06V10/462
Inventor 陈震中丁晓颖
Owner WUHAN UNIV