Published papers about

Appearance Based Approaches to Recognition

by James L. Crowley and co-authors

Approach:

Appearance is the set of possible images of an object. The parameters of image formation define a manifold embedded in the space of possible images. As commonly defined, this space has one dimension per pixel. Attempts to represent and match images based on appearance manifolds in image space generally fail because of problems of image alignment, occlusions, or image segmentation. In these papers we show that appearance manifolds can be represented in a much lower dimensional space defined by a vector of receptive fields. We show that such an approach provides a computationally efficient means to recall and recognize objects under changes in viewpoint within cluttered scenes.
We define a family of receptive field functions based on Gaussian derivatives. We show how these receptive fields can be locally normalized in scale and orientation to provide robust image indexing. We project this family onto a color space to obtain a family of chromatic receptive fields. We develop a method to determine dense correspondence between views taken over a view-sphere to define a four dimensional view-variant appearance manifold. We show that this manifold can be used to robustly recall and recognize ordinary objects at arbitrary view angles and distance. The resulting algorithm has a very low computational complexity and can be scaled to large numbers of objects.

 

Journal Papers

  1. F. Pelisson, D. Hall, O. Riff, J. L. Crowley, "Brand Identification Using Gaussian Derivative Histograms, Machine Vision and Applications", To appear, 2004.
  2. J. L. Crowley and F. Pourraz, "Continuity properties of the appearance manifold for mobile robot position estimation", Image and Vision Computing, Vol 19, pp 741-752, September 2001.
  3. D. Hall, J. L. Crowley and V. Colin de Verdière, "View Invariant Object Recognition using Coloured Receptive Fields", Machine Graphics and Vision, Vol 9. pp 341-352, No. 2. June 2000.
  4. V. Colin de Verdière et J. L. Crowley, "Local Appearance Space for Recognition of Navigation Landmarks", Robotics and Autonomous Systems, Vol 31, Nos 1-2, pp 61-70, April 2000.
  5. B.Schiele and J. L. Crowley, "Recognition without Correspondence using Multidimensional Receptive Field Histograms", International Journal of Computer Vision, 36(1), pp 31-50, Jan. 2000
  6. J. L. Crowley, F. Wallner and B. Schiele, "Position Estimation Using Principal Components of Range Data", Robotics and Autonomous Systems, Vol 23, no 4, pp 267-276, 1998.
  7. B.Schiele and J. L. Crowley, "Transinformation of Object Recognition and its Application to Viewpoint Planning.", Robotics and Autonomous Systems, Vol 21, No 1, July 1997.

 

Conference Papers

  1. N. Gourier, D. Hall, J. L. Crowley, Facial Features Detection Robust to Pose, Illumination and Identity, International Conference on Systems Man and Cybernetics, The Hague, Oct 2004
  2. D. Hall and J. L. Crowley, "Detection de Visages par Charactéristiques Géneriques Calculées à Partir des Images de Luminance", (In French), RFIA, Reconnaissance des Formes et Intelligences Artificielle, Toulouse, Jan. 2004.
  3. D. Hall and J. L. Crowley, "Computation of generic features for object classification", Scale Space 03, 4th International Conference on Scale-Space theories in Computer Vision, 10-12 June 2003, Isle of Skye, Scotland, UK
  4. J. L. Crowley, O. Riff, "Fast Computation of Characteristic Scale using a Half Octave Pyramid", Scale Space 03, 4th International Conference on Scale-Space theories in Computer Vision, 10-12 June 2003, Isle of Skye, Scotland, UK
  5. D. Hall, F. Pelisson, O. Riff et J. L. Crowley, "Brand Identification Using Gaussian Derivative Histograms", International Conference on Vision Systems, ICVS-03, Graz, avril 2003.
  6. J. L. Crowley, O. Riff and J. Piater, "Fast Computation of Characteristic Scale using a Half Octave Pyramid", CogVis 2002, International Workshop on Cognitive Computing, Zurich, October 2002.
  7. J. L. Crowley, O. Riff and J. Piater, Fast Computation of Characteristic Scale using a Half Octave Pyramid, CogVis 2002, International Workshop on Cognitive Computing, Zurich, October 2002.
  8. K. Schwerdt, D. Hall, J. L. Crowley, "Visual Recognition of Emotional States", The Third International Conference on Multimodal Interfaces, ICMI-2000, Beijing China, 14-16 October 2000.
  9. D. Hall, J. L. Crowley, "Estimating the Pose of Phicons for Human Computer Interaction", The Third International Conference on Multimodal Interfaces, ICMI-2000, Beijing China, 14-16 October 2000.
  10. O. Chomat, V. Colin de Verdière, D. Hall and J. L. Crowley, "Local Scale Selection for Gaussian Based Description Techniques", 6th European Conference on Computer Vision, Springer Verlag, Dublin, pp 117-133, June 2000.
  11. O. Chomat, J. Martin, and J. L. Crowley, "A Probabilistic Sensor for the Perception and Recognition of Activities", 6th European Conference on Computer Vision, Springer Verlag, Dublin, pp 487-506, June 2000.
  12. D. Hall, V. Colin de Verdiere and J. L. Crowley, "Object Recognition using Coloured Receptive Field", 6th European Conference on Computer Vision, Springer Verlag, Dublin, pp 164-178, June 2000.
  13. O. Chomat and J. L. Crowley, "A Probabilistic Sensor for the Perception of Activities", 4th IEEE International Conference on Automatic Face and Gesture Recognition", Grenoble, France, March 2000.
  14. O. Chomat, V. Colin de Verdière and J. L. Crowley, " Recognizing Goldfish? or Local Scale Selection for Recognition Technique", Symposium on Intelligent Robotics Systems, SIRS-99, Coimbra, pp 197-206, July 1999
  15. E. Backman V. Colin de Verdière et J. L. Crowley, "Dense Stereo Matching using Local Appearance", Symposium on Intelligent Robotics Systems, SIRS-99, Coimbra, pp13-22, July 1999.
  16. F. Pourraz and J. L. Crowley, "Continuity Properties of the Appearance Manifold for Mobile Robot Position Estimation", IEEE Workshop on Visual Navigation, Fort Collins, June 1999.
  17. O. Chomat and J. L. Crowley, "Probabilistic Recognition of Activity using Local Appearance", IEEE Conference on Computer Vision and Pattern Recognition, CVPR 99, Fort Collins, June 1999.
  18. V. Colin de Verdière and J. L. Crowley, "Visual Recognition Using Local Appearance", ECCV '98, Frieburg, June, 1998.
  19. J. L. Crowley, F. Wallner and B. Schiele, "Position Estimation Using Principal Components of Range Data", 1998 IEEE Conference on Robotics and Automation, Leuven, May, 1998.
  20. V. Colin de Verdière et J. L. Crowley, "Reconnaissance d'Objets par Apparence Locale (In French)", RFIA '98, Clermont-Ferrand, January 1998.
  21. B. Schiele and J. L. Crowley, "Transinformation for Active Object Recognition", In ICCV'98, International Conference on Computer Vision, Bombay, India, January 1998
  22. J. L. Crowley, F. Wallner and B. Schiele, "Position Estimation Using Principal Components of Range Data", Intelligent Autonomous Robotics and Processes, Genoa, It, October 1997.
  23. J. Martin et J. L. Crowley, "An Appearance-Based Approach to Gesture-Recognition", 9th International Conference on Image Analysis and Processing, Florence, Italy, 17--19 September 1997
  24. S. D. Jones, C. Andresen and J. L. Crowley, "Appearance Based Processes for Visual Navigation", IROS '97, IEEE International Conference on Intelligent Robots and Systems, Grenoble, Sept. 1997.
  25. J. Coutaz, J. L. Crowley, F Berard and D. Salber, "EigenSpace Coding as a Means to Support Privacy in Computer Mediated Communication", Interact 97, Sydney, July 97.
  26. B.Schiele and J. L. Crowley, "The concept of Visual Classes for Object Classification.", Scandinavian Conference on Image Analysis, SCIA '97, Lapeenranta, June 1997.
  27. B. Schiele and J.L. Crowley, "Where to look next and What to look for", IROS '96, Osaka, Dec 1996.
  28. B. Schiele and J.L. Crowley, "Probabilistic Object Recognition using Mutidimensional Receptive Field Histograms", ICPR '96, Vienna, August 96.
  29. B. Schiele and J.L. Crowley,"Object Recognition using Multidimensional Receptive Field Histograms", ECCV-'96, European Conference on Computer Vision, Cambridge UK, April '96.
  30. J. L. Crowley and J. Martin,"Experimental Comparison of Correlation Techniques", IAS-4, International Conference on Intelligent Autonomous Systems, Karlsruhe, March 1995. (Best Paper Award IAS-4) (224 K bytes)