Prior art

The following prior art references are considered most relevant to US patent 6700999, based on the citations provided within the patent document and general knowledge of the field.

Patent Citation

• US6111517A: Continuous video monitoring using face recognition for access control
  • Publication/Filing Date: Filed December 30, 1996; Published August 29, 2000.
  • Brief Description: This patent describes a system for continuous video monitoring that uses face recognition for access control. It focuses on recognizing faces in video streams for security applications.
  • Potential Anticipation (35 U.S.C. § 102): This patent could potentially anticipate aspects of Claim 1, Claim 8, Claim 15, Claim 21, and Claim 27 related to the general concept of face tracking in video sequences, especially in the context of human-computer interaction or security systems. Specifically, it addresses continuous video monitoring and face recognition, which are applications where face tracking is a prerequisite.

Non-Patent Citations

• Chellappa et al., "Human and Machine Recognition of Faces: A Survey," Proceedings of the IEEE, vol. 83, no. 5, pp. 705-740, May 1995.

  • Publication Date: May 1995.
  • Brief Description: This paper provides a comprehensive survey of both human and machine face recognition techniques. It discusses critical issues, various techniques for segmentation/location of faces, feature extraction, and recognition, and explores different applications.
  • Potential Anticipation (35 U.S.C. § 102): This survey article broadly covers many foundational aspects of face recognition and tracking, including techniques for segmenting faces from cluttered scenes and extracting features. It could potentially anticipate the general concepts of "constructing a score map," "producing a mask," and "locating face candidate regions" as described in Claims 1, 6, 8, 13, 15, 21, 25, 27, and 32, by outlining the state of the art in face detection and segmentation prior to US6700999.

• Dorin Comaniciu et al., "Mean Shift analysis and applications," The Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp 1197-1203, 1999.

  • Publication Date: September 20, 1999.
  • Brief Description: This paper introduces the mean shift algorithm, a nonparametric estimator of density gradient, for discontinuity preserving filtering and image segmentation in the joint spatial-range domain of images. It discusses its application in image smoothing and segmentation and its utility in detecting modes of density.
  • Potential Anticipation (35 U.S.C. § 102): The mean shift algorithm described here is a fundamental technique for identifying dense regions in feature spaces, which is directly relevant to locating face candidate regions. It could potentially anticipate aspects of "constructing a score map" and "producing a mask" by delineating regions of high flesh-tone probability, as described in Claims 1, 4, 5, 6, 8, 11, 12, 13, 17, 18, 23, 24, 27, 30, 31, and 32. Its application to image segmentation directly relates to the segmentation operation in location subtask P330 of US6700999.

• Dorin Comaniciu et al., "Robust Analysis of Feature Spaces: Color Image Segmentation," IEEE, pp750-755, 1997.

  • Publication Date: 1997.
  • Brief Description: This work presents a general nonparametric technique, based on the mean shift algorithm, for recovering significant image features and performing color image segmentation. It emphasizes autonomous segmentation and robust feature space analysis.
  • Potential Anticipation (35 U.S.C. § 102): Similar to "Mean Shift analysis and applications," this paper's focus on robust color image segmentation using mean shift directly relates to the score map construction and segmentation steps in US6700999. It could anticipate the general process of using pixel values and color space analysis to identify and segment regions, as in Claims 1, 2, 4, 5, 6, 8, 9, 11, 12, 13, 16, 17, 18, 22, 23, 24, 27, 28, 30, 31, and 32.

• Gary R. Bradski, "Computer Vision Face Tracking for Use in a Perceptual User Interface," Intel Technology Journal, Q2 1998.

  • Publication Date: Q2 1998.
  • Brief Description: This article describes the Continuously Adaptive Mean Shift (CAMSHIFT) algorithm for real-time face and object tracking, particularly for use in perceptual user interfaces. It modifies the mean shift algorithm to adapt to dynamically changing color probability distributions in video frames and uses color histograms (e.g., hue channel in HSV color space) to track faces.
  • Potential Anticipation (35 U.S.C. § 102): This publication is highly relevant as it explicitly discusses real-time face tracking using color models (specifically HSV hue histograms) and the mean shift algorithm, which are core components of US6700999. It could anticipate Claim 1 (method of tracking, score map based on pixel values, mask production), Claim 2 (pixel values and flesh-tone probabilities), Claim 6 (temporal filtering conceptually, as tracking over time is implied), Claim 8 (apparatus for tracking, mapper for score map, segmenter for mask), Claim 9 (mapper produces score map based on pixel values/flesh-tone), and other claims detailing the color-based segmentation and tracking. The use of a "probability density image" and "initial histogram" in CAMSHIFT for color-based tracking directly correlates to the "score map" and "histogram that relates pixel values to flesh-tone probabilities" in US6700999.

• Martin Hunke et al., "Face Locating and Tracking for Human-Computer Interaction," IEEE, pp1277-1281, 1995.

  • Publication Date: 1995.
  • Brief Description: This paper proposes a connectionist face tracker that manipulates camera orientation and zoom to keep a person's face located in a stable image for human-computer interaction. It uses features like shape and color for locating faces and adapts to changing lighting conditions.
  • Potential Anticipation (35 U.S.C. § 102): This reference explicitly addresses face locating and tracking for human-computer interaction, including controlling camera position and zoom. This directly relates to Claim 21 (system with camera control) and Claim 25 (system with camera control and temporal filter, as temporal information is used in control decisions). The use of "color" as a feature for locating faces also potentially anticipates aspects of score map construction and mask production related to color analysis in Claims 1, 6, 8, 13, 15, 21, 25, 27, and 32.

• Raja Yogesh, et al., "Tracking and Segmenting people in varying lighting conditions using colour," Proceedings. Third IEEE International Conference on Automatic Face and Gesture Recognition, pp228-233, 1998.

  • Publication Date: 1998.
  • Brief Description: This paper focuses on tracking and segmenting people using color information, with an emphasis on varying lighting conditions. It likely discusses methods for robust color-based segmentation in different environments.
  • Potential Anticipation (35 U.S.C. § 102): This reference could anticipate elements of Claims 1, 2, 6, 8, 9, 13, 15, 16, 21, 22, 25, 28, and 32 by addressing the use of color for segmentation and tracking, especially under varying lighting conditions, which is a practical challenge also addressed by US6700999's flesh-tone probability and adaptive parameters.

• Samal and Iyengar, "Automatic recognition and analysis of human faces and facial expressions: A survey," Pattern Recognition, vol. 25, no. 1, pp. 65-77, Jan. 1992.

  • Publication Date: January 1992.
  • Brief Description: This is an early survey paper on the automatic recognition and analysis of human faces and facial expressions, reviewing various techniques available before 1990.
  • Potential Anticipation (35 U.S.C. § 102): As another foundational survey, this article provides context for the prior art in face recognition and analysis. It would cover the general ideas of face detection, feature extraction, and recognition, potentially anticipating the high-level goals and basic components of face tracking systems outlined in Claims 1, 6, 8, 13, 15, 21, 25, 27, and 32, by showing that the problems and general approaches were known in the art.