• Publications
  • Influence
Eigenfaces for Recognition
A near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals, and that is easy to implement using a neural network architecture. Expand
Face recognition using eigenfaces
  • M. Turk, A. Pentland
  • Computer Science
  • Proceedings. IEEE Computer Society Conference on…
  • 3 June 1991
An approach to the detection and identification of human faces is presented, and a working, near-real-time face recognition system which tracks a subject's head and then recognizes the person byExpand
Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking
This work presents a carefully designed dataset of video sequences of planar textures with ground truth, which includes various geometric changes, lighting conditions, and levels of motion blur, and presents a comprehensive quantitative evaluation of detector-descriptor-based visual camera tracking based on this testbed. Expand
Fast 2D Hand Tracking with Flocks of Features and Multi-Cue Integration
  • M. Kölsch, M. Turk
  • Computer Science
  • Conference on Computer Vision and Pattern…
  • 27 June 2004
This paper introduces "Flocks of Features," a fast tracking method for non-rigid and highly articulated objects such as hands. It combines KLT features and a learned foreground color distribution toExpand
A novel subspace method called Fisher non-negative matrix factorization (FNMF) for face recognition is proposed, which results in the novel FNMF algorithm and is shown to achieve better performance than LNMF. Expand
Robust hand detection
  • M. Kölsch, M. Turk
  • Computer Science
  • Sixth IEEE International Conference on Automatic…
  • 17 May 2004
This paper presents a frequency analysis-based method for instantaneous estimation of class separability, without the need for any training, and builds detectors for the most promising candidates, their receiver operating characteristics confirming the estimates. Expand
Eigenfaces for Face Recognition
Multimodal interaction: A review
  • M. Turk
  • Computer Science
  • Pattern Recognit. Lett.
  • 15 January 2014
The question of early vs. late integration and inspiration in recent evidence in biological sensory integration are reviewed, as well as challenges that lie ahead for research in multimodal human-computer interaction. Expand
Effective representation using ICA for face recognition robust to local distortion and partial occlusion
This work proposes an effective part-based local representation method named locally salient ICA (LS-ICA) method for face recognition that is robust to local distortion and partial occlusion and compares it with other part- based representations such as LNMF (localized nonnegative matrix factorization) and LFA (local feature analysis). Expand
Manifold Based Analysis of Facial Expression
Preliminary experimental results show that the probabilistic facial expression model on manifold significantly improves facial deformation tracking and expression recognition. Expand