Paper
25 October 2013 On application of image analysis and natural language processing for music search
Grzegorz Gwardys
Author Affiliations +
Proceedings Volume 8903, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2013; 89030Z (2013) https://doi.org/10.1117/12.2035450
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2013, 2013, Wilga, Poland
Abstract
In this paper, I investigate a problem of finding most similar music tracks using, popular in Natural Language Processing, techniques like: TF-IDF and LDA. I de ned document as music track. Each music track is transformed to spectrogram, thanks that, I can use well known techniques to get words from images. I used SURF operation to detect characteristic points and novel approach for their description. The standard kmeans was used for clusterization. Clusterization is here identical with dictionary making, so after that I can transform spectrograms to text documents and perform TF-IDF and LDA. At the final, I can make a query in an obtained vector space. The research was done on 16 music tracks for training and 336 for testing, that are splitted in four categories: Hiphop, Jazz, Metal and Pop. Although used technique is completely unsupervised, results are satisfactory and encouraging to further research.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Grzegorz Gwardys "On application of image analysis and natural language processing for music search", Proc. SPIE 8903, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2013, 89030Z (25 October 2013); https://doi.org/10.1117/12.2035450
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Associative arrays

Image processing

Metals

Feature extraction

Image analysis

Image segmentation

Neodymium

RELATED CONTENT

Symbolic feature detection for image understanding
Proceedings of SPIE (March 07 2014)
Quantitative analysis of blood vessel geometry
Proceedings of SPIE (July 09 2001)
FLIPS: Friendly Lisp Image Processing System
Proceedings of SPIE (August 01 1991)
Author name recognition in degraded journal images
Proceedings of SPIE (January 16 2006)
Color image semantics for digital libraries
Proceedings of SPIE (June 17 2003)

Back to Top