How to use manual labelers in evaluation of lip analysis systems?
2009 (English)In: Visual speech recognition: Lip segmentation and mapping / [ed] Shilin W & Alan Liew, USA: IGI Global , 2009, 239-259 p.Chapter in book (Other academic)
The purpose of this chapter is not to describe any lip analysis algorithms but rather to discuss some of the issues involved in evaluating and calibrating labeled lip features from human operators. In the chapter we question the common practice in the field: using manual lip labels directly as the ground truth for the evaluation of lip analysis algorithms. Our empirical results using an Expectation-Maximization procedure show that subjective noise in manual labelers can be quite significant in terms of quantifying both human and algorithm extraction performance. To train and evaluate a lip analysis system one can measure the performance of human operators and infer the “ground truth” from the manual labelers, simultaneously.
Place, publisher, year, edition, pages
USA: IGI Global , 2009. 239-259 p.
Lip Analysis, Expectation Maximization Algorithm, Performance Evaluation
Physical Sciences Engineering and Technology
Research subject Signal Processing; Computerized Image Analysis; Computing Science
IdentifiersURN: urn:nbn:se:umu:diva-20300ISBN: 978-160566186-5OAI: oai:DiVA.org:umu-20300DiVA: diva2:208420