A Method for Generating Semantic Similarity Matrix of Image in Medical Field
A semantic similarity and image technology, applied in the direction of instruments, computing, character and pattern recognition, etc., can solve the problems of wasting limited storage space, reducing the efficiency and accuracy of medical image semantic retrieval, restricting the efficiency of knowledge use, etc., to reduce the occurrence of rate, the effect of improving accuracy
Active Publication Date: 2018-10-30
BENGBU MEDICAL COLLEGE
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although these different domain knowledge base systems are concentrated descriptions of knowledge in the same domain, they still inevitably contain a lot of image information with repeated semantics, resulting in a waste of limited storage space and seriously reducing the efficiency and efficiency of medical image semantic retrieval. Accuracy, which ultimately makes interoperability between knowledge entities in the field impossible, greatly restricting the efficiency of knowledge use
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
[0024] The design concept of the present invention is: using the Bayesian probability model to explicitly represent the semantic information hidden in the image in the form of a tagged word set. Semantic weights of image concepts are adjusted using attributes, and discrete attribute values are obtained by constructing binary conditional attribute decision tables. The method of distinguishable difference matrix is adopted to reduce the calculation scale of tagged words. The matrix calculation of multi-angle semantic distance is introduced to generate a semantic similarity matrix.
[0025] The system of this embodiment includes a domain image semantic information tagging module, a conditional decision entropy generating module, a tagged word reduction module, and a matrix calculation module. The present invention will be further described below in conjunction with the accompanying drawings.
[0026] see figure 1 , a method for generating a semantic similarity matrix of ima...
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 relates to a method for generating a semantic similarity matrix between images in the field. Taking the semantic distance between images in the medical field as the research object, a similarity matrix of medical images based on a rough semantic probability model is proposed through the similarity relationship mapping of multi-strategy matching. The extraction modeling method mainly includes four steps: semantic annotation based on Bayesian probability model, discretization of image features, reduction of semantic features, and domain similarity model calculation based on polymorphism theory. The present invention can effectively improve the accuracy of semantic information merging between images in the medical field, improve the quality of the knowledge base in the fusion medical clinical diagnosis field, and reduce the calculation scale required for large-scale mining of image semantic information.
Description
technical field [0001] The invention belongs to the technical field of medical semantic network and knowledge grid computing and retrieval, and in particular relates to a method for generating a semantic similarity matrix of images in the medical field. Background technique [0002] Due to its extensive application, knowledge in the medical field has been paid more and more attention by relevant scholars. Medical information resources are relatively isolated due to their complexity, dispersion, and heterogeneity, and it is difficult to meet the information needs of users, resulting in the diversity and conflict of image databases in the same field, making it impossible for knowledge bases in the field to interact. operate. [0003] With the rapid development of technologies such as network communication and cloud storage, the scale of information sources including various medical images has gradually expanded. How to obtain implicit and valuable information from massive da...
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): G06K9/62
CPCG06F18/24155
Inventor 王凯
Owner BENGBU MEDICAL COLLEGE