Conference Paper

Face Detection using Discrete Gabor Jets and Color Information.

Conference: SIGMAP 2008 - Proceedings of the International Conference on Signal Processing and Multimedia Applications, Porto, Portugal, July 26-29, 2008, SIGMAP is part of ICETE - The International Joint Conference on e-Business and Telecommunications
Source: DBLP

ABSTRACT Face detection allows to recognize and detect human faces and provides information about their location in a given image. Many applications such as biometrics, face recognition, and video surveillance employ face detection as one of their main modules. Therefore, improvement in the performance of existing face detection systems and new achievements in this field of research are of significant importance. In this paper a hierarchical classification approach for face detection is presented. In the first step, discrete Gabor jets (DGJ) are used for extracting features related to the brightness information of images and a preliminary classification is made. Afterwards, a skin detection algorithm, based on modeling of colored image patches, is employed as a post- processing of the results of DGJ- based classification. It is shown that the use of color efficiently reduces the number of false positives while maintaining a high true positive rate. Finally, a comparison is made with the OpenCV implementation of the Viola and Jones face detector and it is concluded that higher correct classification rates can be attained using the proposed face detector.

  • [Show abstract] [Hide abstract]
    ABSTRACT: In this study, we improve the modified gradient method for face localization. In the modified gradient method (MGM) an approach similar to Roberts operator was used for detecting edges in face images. The Sobel edge detector is proposed for detecting edges of a face and generating the gradients for the face detection. Preliminary experimental results show that our proposed method can detect the face more accurately than that of the modified gradient method.
    IEEE SoutheastCon 2010 (SoutheastCon), Proceedings of the; 04/2010
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The National Library of Medicine (NLM) has developed People Locator TM (PL), a Web-based system for family reunification in cases of a natural or man-made disaster. PL accepts photos and brief text meta-data (name, age, etc.) of missing or found persons. Searchers may query PL with text information, but text data is often incomplete or inconsistent. Adding an image-based search capability, i.e., matching faces in query photos to those already stored in the system, would significantly benefit the user experience. We report on our face matching R&D that aims to provide robust face localization and matching on digital photos of variable quality. In this article, we review relevant research and present our approach to robust near-duplicate image detection as well as face matching. We describe the integration of our face matching system with PL, report on its performance, and compare it to other publicly available face recognition systems. In contrast to these systems that have many good quality well-illuminated sample images for each person, our algorithms are hampered by the lack of training examples for individual faces, as those are unlikely in a disaster setting.
    IEEE International Conference on Healthcare Informatics, Philadelphia, PA; 09/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: With recent advances in machine vision, automatic detection of human expressions in video is becoming important especially because human labeling of videos is both tedious and error prone. In this paper, we present an approach for detecting facial expressions based on the Facial Action Coding System (FACS) in spontaneous videos. We present an automated system for detecting asymmetric eye open (AU41) and eye closed (AU43) actions. We use Gabor Jets to select distinctive features from the image and compare between three different classifiers-Bayesian networks, Dynamic Bayesian networks and Support Vector Machines-for classification. Experimental evaluation on a large corpus of spontaneous videos yielded an average accuracy of 98% for eye closed (AU43), and 92.75% for eye open (AU41).
    Image Processing (ICIP), 2009 16th IEEE International Conference on; 12/2009