Ordinal measure (OM) feature-based image retrieval method and sorting measure feature-based image retrieval system
A technology of image retrieval and ranking measurement, applied in the field of content-based image and video retrieval, can solve the problem of matching speed drop and achieve the effect of improving speed
Active Publication Date: 2015-03-11
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF3 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
As the number of images in the image library increases, its matching speed will decrease significantly
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
[0037] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below through specific embodiments in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0038] figure 1A schematic flowchart of an image retrieval method based on ranking measure features according to an embodiment of the present invention is given. In a nutshell, this method replaces the ranking measure features of the image to be detected to obtain multiple rank measure features of the image, and selects the image whose rank measure feature is the same as any rank measure feature of the image to be detected from the image library as Search Results. This method converts the calculation of the similarity between two ranking measurement features into the comparison of mu...
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 ordinal measure (OM) feature-based image retrieval method. According to the method, upon the attribute value similarity and the position similarity of blocks, performing replacement on ordinal measure features of a to-be-detected image so as to obtain multiple ordinal measure features of the image, and an image of which the ordinal measure feature is identical with any ordinal measure feature of the to-be-detected image is retrieved from an image library. By adopting the method, without calculating the similarity among the ordinal measure features, the ordinal measure features are matched by a comparison method for fixed length strings, so that the speed of comparison and retrieval is increased; the ordinal measure feature-based image retrieval method is suitable for large-scale image retrieval; moreover, the replacement is performed on the ordinal measure features upon the attribute value similarity and the position similarity of the blocks, and as the distribution of attribute value sizes is considered by the replacement, the defect that only the attribute value sizes are considered without considering the difference among the attribute values by the original OM features is remedied.
Description
technical field [0001] The invention relates to a content-based image and video retrieval technology, in particular to an image retrieval method based on ranking measurement features. Background technique [0002] The rapid growth of visual information such as Internet images and videos has brought great challenges to the organization and management of information. There is an increasing demand for content analysis and detection of massive images and videos. Image and video copy detection, video indexing and video search engines And other technologies came into being. Currently, Ordinal Measure (OM) features are usually used in these technologies as feature descriptions for video / image content. The ranking measure feature reflects the relative density distribution of an image, and it uses the sorting relationship of the average gray value of the image sub-blocks as the index feature of the image. Usually, the sorting measure features can be extracted in the following way: ...
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): G06F17/30
CPCG06F16/5838
Inventor 靳国庆张冬明代锋张勇东李锦涛
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI