Image local feature semantic distribution structure and sample distribution structure fusion-encoding method
A technology of local features and image samples, applied in computer parts, character and pattern recognition, instruments, etc., can solve the problem of inability to accurately represent image content information
Active Publication Date: 2016-07-06
XIAN UNIV OF TECH
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The purpose of the present invention is to provide an image local feature semantic distribution structure and sample distribution structure fusion coding method, which solves the problem that the existing coding method cannot accurately represent the image content information
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
[0079] In the ORL (Olivetti Research Laboratory, Olivetti Research Laboratory) face image database, randomly select 80% of the data for each type of data learning support vector product and 20% of the data for testing classification for the final encoding of the image. Such as figure 1 As shown, the horizontal axis is the final coded dimension of the image (20-100), and the vertical axis is the recognition accuracy. The methods in the figure are SIFT (scale-invariant feature transformation, ScaleInvarianceFeatureTransform), GS-SIFT (based on SIFT, consider image sample distribution structure encoding, GlobalStructure-ScaleInvarianceFeatureTransform), LS-SIFT (based on SIFT, consider image local feature semantic distribution structure Encoding, LocalStructure-ScaleInvarianceFeatureTransform), encoding method GLS-SIFT of the present invention (based on SIFT, considering image local feature semantic distribution structure and image sample distribution structure fusion encoding, G...
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 local feature semantic distribution structure and sample distribution structure fusion-encoding method comprising the following steps: acquiring the multi-scale dense SIFT local features of an image; acquiring the semantic center of the local features through K-mean clustering, and measuring the local feature semantic distribution structure with use of x<2> measure; measuring the image sample distribution structure with use of Hausdorff distance based on the local features of the image; measuring the image sample distribution structure based on bag-of-words model encoding; and fusing the structures to acquire low-dimensional tight local features through a matrix spectrum optimization solution method, acquiring the new semantic center of the local features through K-mean clustering, and quantitatively encoding the features of each image to acquire an image feature description with strong classification discrimination capability. The method takes into consideration both the local feature semantic center distribution structure and the image sample distribution structure, the two structures are unified under the same framework, and therefore, the tight local features of images and image structure information fusion-encoding with strong classification discrimination capability are obtained.
Description
technical field [0001] The invention belongs to the technical field of video surveillance image processing, and in particular relates to a fusion coding method of a semantic distribution structure and a sample distribution structure of local features of an image. Background technique [0002] In recent years, there have been more and more applications of intelligent monitoring systems based on content analysis. In order to intelligently analyze and identify targets, image description and cognition are important issues to be solved, because image local descriptions show structural diversity and each structure The complexity of describing the fusion makes it difficult to fully describe the essential structure of the image distribution considering a single structural constraint. In this case, the current method cannot carry out the fusion encoding of the semantic distribution structure of the image local features and the sample distribution structure, and thus cannot represent ...
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): G06K9/62G06K9/46
CPCG06V10/462G06F18/23213G06F18/253
Inventor 蔺广逢缪亚林陈万军陈亚军张二虎朱虹
Owner XIAN UNIV OF TECH