Title :
A novel content Based Scene Retrieval using multi-frame features
Author :
Tien Tan Ngo ; Dung Vo
Author_Institution :
Fac. of Electr. & Electron. Eng., Ho Chi Minh City Univ. of Technol., Ho Chi Minh City, Vietnam
Abstract :
This paper proposes a novel algorithm for Content Based Scene Retrieval (CBSR) using video features such as moment, histogram, Edge Histogram Descriptor (EHD)... This application is similar for Content Based Image Retrieval (CBIR) but instead of finding corresponding images in the database, it identifies the corresponding scene which contains the testing frame. The proposed algorithm can deal with scene with similar contents which has not been mentioned in other methods. The simulation results show that identification performance obtains the accuracy up to 99.42% for a 2:31 minute trailer.
Keywords :
content-based retrieval; feature extraction; image colour analysis; image retrieval; video signal processing; CBIR; CBSR; EHD; color histogram; content based image retrieval; content based scene retrieval; edge histogram descriptor; moment; multiframe features; scene identification detection; testing frame; video features; Accuracy; Databases; Feature extraction; Histograms; Image color analysis; Image edge detection; Testing; color histogram; content based image retrieval (CBIR); edge histogram descriptor (EHD); moment; scene identification detection;
Conference_Titel :
Advanced Technologies for Communications (ATC), 2014 International Conference on
Print_ISBN :
978-1-4799-6955-5
DOI :
10.1109/ATC.2014.7043365