Image retrieval method based on multi-feature fusion
A multi-feature fusion and image retrieval technology, which is applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as imperfect retrieval methods
Active Publication Date: 2018-11-16
上海得见计算机科技有限公司
View PDF11 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The present invention proposes an image retrieval method based on multi-feature fusion, which solves the problem of incomplete fusion of multiple image feature retrieval methods in the prior art
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
[0048] An image retrieval method based on multi-feature fusion, the specific steps are as follows:
[0049] (1) Obtain the target image I, and calculate the image features of the target image I
[0050] 1) Extract the color feature of the target image I, and store it in the color feature library of the image
[0051] ① Convert the target image I from the RGB color space to the HSV color space according to the standard conversion formula;
[0052] ②Convert the target image I converted to HSV color space according to the formula and Carry out the first step of quantization, quantize the hue H to 7 intervals, and quantize the brightness V and saturation S to 3 intervals respectively;
[0053] 3. according to formula L=9H+3S+V the RGB value of target image I is mapped in 63 kinds of color spaces of HSV by quantization;
[0054] The amount of information provided by the color of different positions in an image is different. Usually, the information of an image is mainly conce...
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 retrieval method based on multi-feature fusion. The image retrieval method comprises the following steps of acquiring a target image I, and calculating image features of the target image I; extracting color features of the target image I, and storing the color features in a color feature library of the image; extracting shape features of the target image I and storing the shape features in a shape feature library of the image; extracting texture features of the target image I, and storing the texture features in a texture feature library of the image; and calculating the similarity between the target image I and an image data set, thereby obtaining a final retrieval result. The method has the following beneficial effect that a user can obtain similar home scheme images according to retrieved images. According to the method, for the deficiency of an existing single feature and the combination of feature sets in the home industry, and in an actual home scene, the efficiency of single feature retrieval can be improved, and the problem that the coverage of the single feature is insufficient can be solved. The searching efficiency of home product images can be improved; the time of searching for home schemes by the user can be shortened; and the actual searching experience of the user can be improved.
Description
technical field [0001] The invention relates to the technical field of image retrieval, in particular to an image retrieval method based on multi-feature fusion. Background technique [0002] The content-based image retrieval method refers to the use of information such as visual features and spatial relationships of the image itself to establish a high-dimensional feature vector library of the image, perform matching according to the high-dimensional feature vector of the image, and return the user's image retrieval results. Compared with the text-based image retrieval method, the retrieval result of this method is more effective. [0003] According to the division of logical types, image features can be divided into three categories: color features, texture features and shape features. Among them, the color feature is one of the most widely used image features, which can provide color-based classification functions for image search; the texture feature focuses on describi...
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 IPC IPC(8): G06F17/30G06K9/46G06K9/62
CPCG06V10/56G06F18/253
Inventor 栾雄张闻强徐念龙杨莹
Owner 上海得见计算机科技有限公司