Date of Graduation
Bachelor of Science
Computer Science and Computer Engineering
Committee Member/Second Reader
Committee Member/Third Reader
This paper seeks to establish the validity and potential benefits of using existing computer vision techniques on audio samples rather than traditional images in order to consistently and accurately identify a song of origin from a short audio clip of potentially noisy sound. To do this, the audio sample is first converted to a spectrogram image, which is used to generate SURF features. These features are compared against a database of features, which have been previously generated in a similar fashion, in order to find the best match. This algorithm has been implemented in a system that can run as a server, processing “query” clips as they come in and returning to the end user a specific song which matches the input query audio.
Hollis, Mason, "Music Feature Matching Using Computer Vision Algorithms" (2017). Computer Science and Computer Engineering Undergraduate Honors Theses. 47.