No abstract

ÑThe stable relationship between personality and EEG ensures the feasibility of personality inference from brain activities. In this paper, we recognize an individualÕs personality traits by analyzing brain waves when he or she watches emotional materials. Thirty-seven participants took part in this study and watched 7 standardized film clips that characterize real-life emotional experiences and target seven discrete emotions. Features extracted from EEG signals and subjective ratings enter the SVM classifier as inputs to predict five dimensions of personality traits. Our model achieves better classification performance for Extraversion (81.08%), Agreeableness (86.11%), and Conscientiousness (80.56%) when positive emotions are elicited than negative ones, higher classification accuracies for Neuroticism (78.38-81.08%) when negative emotions, except disgust, are evoked than positive emotions, and the highest classification accuracy for Openness (83.78%) when a disgusting film clip is presented. Additionally, the introduction of features from subjective ratings increases not only classification accuracy in all five personality traits (ranging from 0.43% for Conscientiousness to 6.3% for Neuroticism) but also the discriminative power of the classification accuracies between five personality traits in each category of emotion. These results demonstrate the advantage of personality inference from EEG signals over state-of-the-art explicit behavioral indicators in terms of classification accuracy.

Convolutional Neural Networks (CNN) have been applied to age-related research as the core framework. Although faces are composed of numerous facial attributes, most works with CNNs still consider a face as a typical object and do not pay enough attention to facial regions that carry age-specific feature for this particular task. In this paper, we propose a novel CNN architecture called Fusion Network (Fusion-Net) to tackle the age estimation problem. Apart from the whole face image, the FusionNet successively takes several age-specific facial patches as part of the input to emphasize the age-specific features. Through experiments, we show that the FusionNet significantly outperforms other state-of-the-art models on the MORPH II benchmark.

No abstract

Copies of full items can be used for personal research or study, educational, or not-for profit purposes without prior permission or charge. Provided that the authors, title and full bibliographic details are credited, a hyperlink and/or URL is given for the original metadata page and the content is not changed in any way. Publisher's statement:Citation: Xufeng Lin ; Xingjie Wei and Chang-Tsun Li "Two improved forensic methods of detecting contrast enhancement in digital images", Proc. SPIE 9028, Media Watermarking, Security, and Forensics 2014, 90280X (February 19, 2014) Copyright notice: © (2014) Copyright Society of Photo-Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. DOI abstract link: http://dx.doi.org/10.1117/12.2038644 A note on versions:The version presented here may differ from the published version or, version of record, if you wish to cite this item you are advised to consult the publisher's version. Please see the 'permanent WRAP url' above for details on accessing the published version and note that access may require a subscription. For more information, please contact the WRAP ABSTRACTContrast enhancements, such as histogram equalization or gamma correction, are widely used by malicious attackers to conceal the cut-and-paste trails in doctored images. Therefore, detecting the traces left by contrast enhancements can be an effective way of exposing cut-and-paste image forgery. In this work, two improved forensic methods of detecting contrast enhancement in digital images are put forward. More specifically, the first method uses a quadratic weighting function rather than a simple cut-off frequency to measure the histogram distortion introduced by contrast enhancements, meanwhile the averaged high-frequency energy measure of histogram is replaced by the ratio taken up by the high-frequency components in the histogram spectrum. While the second improvement is achieved by applying a linear-threshold strategy to get around the sensitivity of threshold selection. Compared with their original counterparts, these two methods both achieve better performance in terms of ROC curves and real-world cut-and-paste image forgeries. The effectiveness and improvement of the two proposed algorithms are experimentally validated on natural color images captured by commercial camera.