The Painful Face - Pain Expression Recognition Using Active Appearance Models.
The Painful Face - Pain Expression Recognition Using Active Appearance Models.
复制标题
DOI：
10.1016/j.imavis.2009.05.007
复制
发表时间：
2009-10
影响因子：
4.7
通讯作者：
Solomon, Patricia E.
中科院分区：
文献类型：
--
作者：
Ashraf, Ahmed Bilal;Lucey, Simon;Cohn, Jeffrey F.;Chen, Tsuhan;Ambadar, Zara;Prkachin, Kenneth M.;Solomon, Patricia E.
关键词：
疼痛通常通过患者自我报告进行评估。然而，自我报告的疼痛难以解释，并且可能受损，或者在某些情况下（即，幼儿和重病患者）甚至不可能。为了避免这些问题，行为科学家已经确定了可靠和有效的面部疼痛指标。迄今为止，这些方法需要高技能的人类观察者进行手动测量。在本文中，我们探索了一种自动识别急性疼痛，而不需要人类观察员的方法。具体来说，我们的研究仅限于自动检测肩袖损伤成人患者的疼痛。该系统采用视频输入的病人，因为他们移动他们的影响和未受影响的肩膀。考虑了两种类型的地面实况。序列水平的地面真理由熟练的观察员Likert类型的评级组成。帧级的地面真相计算从存在/不存在和强度的面部动作以前与疼痛。主动外观模型（AAM）被用来解耦的形状和外观的数字化人脸图像。支持向量机（SVM）进行了比较，从AAM和不同粒度的地面真理的几个表示。我们探讨了两个问题有关的建设，设计和开发的自动疼痛检测系统。首先，在什么水平（即，序列级或帧级）是否应该标记数据集以获得令人满意的自动疼痛检测性能？第二，在这两个标签层次上，我们非刚性地记录面部有多重要？
Pain is typically assessed by patient self-report. Self-reported pain, however, is difficult to interpret and may be impaired or in some circumstances (i.e., young children and the severely ill) not even possible. To circumvent these problems behavioral scientists have identified reliable and valid facial indicators of pain. Hitherto, these methods have required manual measurement by highly skilled human observers. In this paper we explore an approach for automatically recognizing acute pain without the need for human observers. Specifically, our study was restricted to automatically detecting pain in adult patients with rotator cuff injuries. The system employed video input of the patients as they moved their affected and unaffected shoulder. Two types of ground truth were considered. Sequence-level ground truth consisted of Likert-type ratings by skilled observers. Frame-level ground truth was calculated from presence/absence and intensity of facial actions previously associated with pain. Active appearance models (AAM) were used to decouple shape and appearance in the digitized face images. Support vector machines (SVM) were compared for several representations from the AAM and of ground truth of varying granularity. We explored two questions pertinent to the construction, design and development of automatic pain detection systems. First, at what level (i.e., sequence- or frame-level) should datasets be labeled in order to obtain satisfactory automatic pain detection performance? Second, how important is it, at both levels of labeling, that we non-rigidly register the face?
登录
查看更多内容
影响因子：
7.4
作者：
PRKACHIN, KM
通讯作者：
PRKACHIN, KM
影响因子：
19.5
作者：
Matthews, Iain;Xiao, Jing;Baker, Simon
通讯作者：
Baker, Simon
影响因子：
7.4
作者：
PRKACHIN, KM;BERZINS, S;MERCER, SR
通讯作者：
MERCER, SR
影响因子：
7.4
作者：
Prkachin, Kenneth M.;Solomon, Patricia E.
通讯作者：
Solomon, Patricia E.
DOI：
10.1109/tsmcb.2004.825931
发表时间：
2004-06-01
影响因子：
--
作者：
Pantic, M;Rothkrantz, LJM
通讯作者：
Rothkrantz, LJM