Emotion recognition in the wild via convolutional neural networks and mapped binary patterns

Gil Levi, Tal Hassner

פרסום מחקרי: פרק בספר / בדוח / בכנספרסום בספר כנסביקורת עמיתים

תקציר

We present a novel method for classifying emotions from static facial images. Our approach leverages on the recent success of Convolutional Neural Networks (CNN) on face recognition problems. Unlike the settings often assumed there, far less labeled data is typically available for training emotion classification systems. Our method is therefore designed with the goal of simplifying the problem domain by removing confounding factors from the input images, with an emphasis on image illumination variations. This, in an effort to reduce the amount of data required to effectively train deep CNN models. To this end, we propose novel transformations of image intensities to 3D spaces, designed to be invariant to monotonic photometric transformations. These are applied to CASIA Webface images which are then used to train an ensemble of multiple architecture CNNs on multiple representations. Each model is then fine-tuned with limited emotion labeled training data to obtain final classification models. Our method was tested on the Emotion Recognition in the Wild Challenge (EmotiW 2015), Static Facial Expression Recognition sub-challenge (SFEW) and shown to provide a substantial, 15.36% improvement over baseline results (40% gain in performance).

שפה מקוריתאנגלית
כותר פרסום המארחICMI 2015 - Proceedings of the 2015 ACM International Conference on Multimodal Interaction
מוציא לאורAssociation for Computing Machinery, Inc
עמודים503-510
מספר עמודים8
מסת"ב (אלקטרוני)9781450339124
מזהי עצם דיגיטלי (DOIs)
סטטוס פרסוםפורסם - 9 נוב׳ 2015
אירועACM International Conference on Multimodal Interaction, ICMI 2015 - Seattle, ארצות הברית
משך הזמן: 9 נוב׳ 201513 נוב׳ 2015

סדרות פרסומים

שםICMI 2015 - Proceedings of the 2015 ACM International Conference on Multimodal Interaction

כנס

כנסACM International Conference on Multimodal Interaction, ICMI 2015
מדינה/אזורארצות הברית
עירSeattle
תקופה9/11/1513/11/15

הערה ביבליוגרפית

Publisher Copyright:
© 2015 ACM.

טביעת אצבע

להלן מוצגים תחומי המחקר של הפרסום 'Emotion recognition in the wild via convolutional neural networks and mapped binary patterns'. יחד הם יוצרים טביעת אצבע ייחודית.

פורמט ציטוט ביבליוגרפי