Abstract
The paper describes improved face detection methods for grayscale and color images using the combined cascade of classifiers and skin color segmentation. The combined cascade with proposed face candidates’ verification method allows achieving one of the best detection rates on CMU test set and a high processing speed suitable for a video flow processing. It’s also shown that the mixture of color spaces is more efficient during the skin color segmentation than the application of one color space. A lot of experiments are made to choose rational parameters for the developed face detection system in order to improve the detection rate, false positives’ number and system’s speed.
Highlights
During the last decade the researches in the face detection (FD) area became more and more active
The reason is that there are a lot of applications of this task such as face recognition, videoconferences, content-based image retrieval, video surveillance, human-computer interface, face expressions’ analysis, visitors’ counting, access control where the detection is the first stage of any face processing [1]
The FD task is quite easy for the humans but becomes a serious problem while developing an automatic detection system
Summary
During the last decade the researches in the face detection (FD) area became more and more active. There is the range of applications where the existent FD methods are not suitable, for example, video surveillance systems and access control. In such systems to achieve the high detection rate with the lowest false positive detections it is necessary to use the complex monolithic classifiers. Their usage with the existing face search strategies lowers the performance of FD subsystem and makes impossible processing of the video stream. In order to configure the rational parameters of developed FD system we provide the experimental results of such researches in respect to the detection rate, number of false positive detections as well as the performance
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
