Study of Viola Jones Face Detection on Color Image based on Skin Pigmentation Level
AbstractAutomatic face detection has been very complex and challenging research topic due to the complexity of faces’ characteristics that is not rigid object. There have been many works on proposing robust algorithm on image detection. Many researcher use Viola Jones algorithm as their initial point and benchmark. The Viola-Jones face detection itself is the most popular and recent applicable algorithm that has been developed since 2004 by Paul Jones from Microsoft R&D and its co-inventor, Michael J. Jones from Mitsubishi R&D. Many previous works present the study on the Viola Jones algorithm subject to frontal face with no consideration on the skin pigmentation level. This paper presents study on The Viola Jones performance on color image that consider skin pigmentation level. To indicate the skin pigmentation level, the L* element on CIELAB color space is used. The skin pigmentation level is clustered into dark skin, brown skin and fair skin. The simulation result show that the Viola Jones performance tends to decrease when the skin pigmentation getting high (dark skin). Some hypotheses test had been done to support the claim.
Copyright (c) 2015 Jurnal ELEMENTER
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
a. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
b. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
c. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
This work is licensed under a Creative Commons Attribution 4.0 International License.