Open AccessVideo Classification Based On the Improved K-Means Clustering Algorithm
Author(s) -
Taile Peng,
Zhen Zhang,
Ke Shen,
Tao Jiang
Publication year - 2020
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.179
H-Index - 26
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/440/3/032060
Subject(s) - cluster analysis , computer science , artificial intelligence , pattern recognition (psychology) , classifier (uml) , segmentation , canopy clustering algorithm , k means clustering , correlation clustering
To solve the problem of low accuracy of video classification, this paper proposes an improved k-Means algorithm, which is used as a classifier to realize video classification. Firstly, video segmentation is carried out to extract the visual features of the video and form a group of visual features. The traditional k-Means clustering algorithm is improved to form initial clustering points with labeled video samples, optimize the objective function, and further optimize the clustering results of the video. Several experiments show that the proposed classification algorithm has high classification accuracy.