An Image Retrieval Method Based on Orientation Selection Mechanism
A technology of image retrieval and direction selection, which is applied in digital data information retrieval, instruments, computing and other directions, and can solve the problem of not simulating the human brain mechanism.
Active Publication Date: 2022-08-09
GUANGXI NORMAL UNIV
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] Aiming at the problem that the traditional image retrieval technology does not simulate the mechanism of the human brain, the present invention provides an image retrieval method based on a direction selection mechanism, which can simulate the visual information processing mechanism to a certain extent, and combines visual effects such as color, edge direction, and grayscale. information, which can effectively improve the accuracy of image retrieval
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
[0040] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to specific examples.
[0041] The basic idea of the present invention is to use the pixel value differences of low-level visual features in the directions of 0°, 45°, 90° and 135° to determine the optimal direction felt by each pixel, and extract the optimal direction on this basis. The feature change relationship of visual information. Starting from the basic idea, an image retrieval method based on the direction selection mechanism proposed by the present invention, such as figure 1 As shown, it includes the following steps:
[0042] Step (1) first convert the input color image from RGB color space to HSV color space;
[0043] In the RGB color space, R represents the red component, G represents the green component, and B represents the blue component. In the HSV color space, H represe...
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 discloses an image retrieval method based on a direction selection mechanism. First, the input image is converted from the RGB color space to the HSV color space; secondly, the visual feature map is extracted in the HSV color space; then, the optimal direction selection is performed on the visual feature map. , obtain the optimal orientation map; finally, based on the visual feature map and the optimal orientation map, extract the local feature change relationship, and obtain the feature change histogram for similarity matching. While using traditional image retrieval technology, this method simulates the visual information processing mechanism of the human brain to a certain extent, and can effectively describe the color, texture and spatial relationship characteristics of images.
Description
technical field [0001] The invention relates to the technical field of image retrieval, in particular to an image retrieval method based on a direction selection mechanism. Background technique [0002] With the rapid upgrading of mobile devices such as mobile phones, more and more people are enjoying the joy of technology. At the same time, people use portable devices such as mobile phones and SLRs to take pictures and take pictures, and share the collected images to the Internet through various mobile phone applications or computer programs. In this way, the Internet has a large amount of image data, and it also increases the difficulty for people to search for the pictures they want. On the other hand, the big data of images has promoted the unprecedented development of technologies such as deep learning. As a popular technology to simulate the neural mechanism of the human brain, deep learning has achieved great success in the field of computer vision. Researchers hav...
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): G06F16/583
CPCG06F16/5838G06F16/5862G06F16/5854
Inventor 刘广海魏钊
Owner GUANGXI NORMAL UNIV