SGER: Analyzing Facial Expression in Three Dimensional Space

-拟议的研究将在完整的3D空间中进行面部表情表征、检测、跟踪和分类的试点研究。为了证明3D表情识别的概念，本研究将研究3D面部特征如何以及哪些特征可以使基于3D的表情识别比基于2D的识别更好。对3D面部表情的分析将有助于检查自发表情固有的精细结构变化和精确的时间过程。虽然3D建模技术已被广泛应用于3D人脸识别和3D人脸动画，但关于3D人脸表情识别的研究几乎没有报道。尚未进行此类研究的一个主要原因是不存在3D表情数据库。作为概念验证，将构建一个最先进的3D动态面部表情数据库来测试算法并向研究界公开，以促进该领域的研究。该项目旨在实现在识别广泛的面部表情方面的高准确率，最终目标是在细节水平上增加对面部行为和面部表情3D结构的总体理解。因此，这一探索性研究将导致建立一个人性化的自发面部表情识别系统，这对下一代人机交互、安全、人类情感识别、生物医学、执法和心理学研究至关重要。该项目将促进通过自动3D面部表情识别实现下一代人机交互的研究。它将有助于增加对人类视觉系统认知过程的科学理解和建模。由此产生的系统和3D面部表情数据库将在安全、执法、生物医学、行为科学、娱乐和教育方面的应用中具有价值。3D人脸表情数据库将向整个研究社区开放。作为一所学术机构，纽约州立大学宾厄姆顿分校拥有大量多样化的学生和教职员工。这将有助于为数据库扫描许多不同种族背景的人。这项研究的结果可以整合到纽约州立大学宾厄姆顿分校与图像处理、计算机视觉和计算机图形学相关的研究生和本科生课程中。

------The proposed study will conduct a pilot research on facial expression representation, detection, tracking and classification in a complete 3D space. To prove the concept of 3D face expression recognition, the study will investigate the issue on how and what 3D facial features could make the 3D-based expression recognition better than 2D-based recognition. The analysis of 3D facial expressions will facilitate the examination of both the fine structural changes inherent in and the precise time course of spontaneous expressions. Although 3D modeling techniques have been extensively used for 3D face recognition and 3D face animation, barely any research on 3D facial expression recognition has been reported. A primary reason why such research has not yet been undertaken is that no 3D expression database exists. As a proof-of-concept, a state-of-the-art 3D dynamic facial expression database will be constructed to test the algorithms and make it public to the research community to foster the research in the field. The project aims to achieve a high rate of accuracy in identifying a wide range of facial expressions, with the ultimate goal of increasing the general understanding of facial behavior and 3D structure of facial expressions on a detailed level. As a result, this exploratory research will lead to building a humanized system for recognizing spontaneous facial expression, which is crucial to the next generation of human computer interaction, security, human affect recognition, biomedicine, law-enforcement and psychology research.This project will facilitate research on the next generation of human-computer interaction through automatic 3D facial expression recognition. It will help increase the scientific understanding and modeling of cognitive processes of the human visual system. The resulting system and the 3D facial expression database will be valuable for applications in security, law-enforcement, biomedicine, behavior science, entertainment and education. The 3D face expression database will be made available to the entire research community. As an academic institution, SUNY Binghamton has a large and diverse student and staff population. This will facilitate scanning many people of diverse ethnic backgrounds for the database. The results of this research can be integrated into graduate and undergraduate courses at SUNY Binghamton related to image processing, computer vision, and computer graphics.