Open AccessStudy on Infringement Identification of Art Works Based on CNN Image Recognition Technology
Author(s) -
Yan Chen,
Rui Qu
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1802/3/032084
Subject(s) - convolutional neural network , computer science , artificial intelligence , similarity (geometry) , cosine similarity , objectivity (philosophy) , identification (biology) , image (mathematics) , process (computing) , pattern recognition (psychology) , computer vision , philosophy , botany , epistemology , biology , operating system
In view of the current situation where the criteria for judging the infringement of art works are still vague and the court discretionary process is highly subjective, this article introduces the working principle of convolutional neural network (CNN) which is based on image recognition technology, and uses CNN algorithm to extract and store the characteristics of related works, And use the method of cosine similarity criterion to compare and calculate the degree of similarity, to assist in judging the standard of substantial similarity, and to improve the objectivity of the criterion for identifying copyright infringement of artworks