Title :
Real Adaboost for content identification
Author :
Naini, Rohit ; Moulin, Philippe
Author_Institution :
ECE Dept., Univ. of Illinois, Urbana, IL, USA
Abstract :
This paper proposes a machine learning method based on Real Adaboost that jointly optimizes the content ID codes and the decoding metric. Significant performance gains over prior art are demonstrated for audio fingerprinting.
Keywords :
content-based retrieval; fingerprint identification; learning (artificial intelligence); Real Adaboost; audio fingerprinting; content ID codes; content identification; decoding metric; machine learning method; Algorithm design and analysis; Boosting; Databases; Decoding; Fingerprint recognition; Hidden Markov models; Measurement;
Conference_Titel :
Statistical Signal Processing Workshop (SSP), 2012 IEEE
Conference_Location :
Ann Arbor, MI
Print_ISBN :
978-1-4673-0182-4
Electronic_ISBN :
pending
DOI :
10.1109/SSP.2012.6319814
