Colour-based object recognition

This thesis studies the use of colour information for object recognition. A new representation for objects with multiple colours-the colour adjacency graph (CAG)-is proposed. Each node of the CAG represents a single chromatic component of the image deened as a set of pixels forming a unimodal cluster in the chromatic scattergram. Edges encode information about adjacency of colour components and their reeectance ratio. The CAG is related to both the histogram and region adjacency graph representations. It is shown to be preserving and combining the best features of these two approaches while avoiding their drawbacks. The proposed approach is tested on a range of diicult object recognition and localisation problems involving complex imagery of non rigid 3D objects under varied viewing conditions with excellent results. Acknowledgements I would like to thank my supervisor Josef Kittler for his user-friendly guidance during the course of this work. \Very spatial thanks" go to Radek Ma r k. It would have been impossible to carry out all the experiments reported in this thesis without the software libraries he developed and programs he implemented. Lastly and most importantly I would like to thank my wife Romana for her support and understanding.

[1]  L. Maloney.  Evaluation of linear models of surface spectral reflectance with small numbers of parameters. , 1986, Journal of the Optical Society of America. A, Optics and image science.

[2]  Thomas O. Binford,et al.  Local shape from specularity , 1988, Comput. Vis. Graph. Image Process..

[3]  M. S. Drew,et al.  Diagonal Transforms Suuce for Color Constancy , 1993 .

[4]  John Princen.  Hough Transform Methods for Curve Detection and Parameter Estimation , 1990 .

[5]  Jiri Matas,et al.  Generation, Verification and Localization of Object Hypotheses based on Colour , 1993, BMVC.

[6]  Gianni Vernazza,et al.  Image Analysis and Processing , 1995 .

[7]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[8]  Y. Chien,et al.  Pattern classification and scene analysis , 1974 .

[9]  Maria Petrou,et al.  The Differentiating Filter Approach to Edge Detection , 1994 .

[10]  R. Marik,et al.  The Color Adjacency GraphRepresentation of Multi-Coloured , 1995 .

[11]  Steven A. Shafer,et al.  Using color to separate reflection components , 1985 .

[12]  Carl-Johan Westelius,et al.  Focus of attention and gaze control for robot vision , 1995 .

[13]  Jiri Matas,et al.  On representation and matching of multi-coloured objects , 1995, Proceedings of IEEE International Conference on Computer Vision.

[14]  Jiri Matas,et al.  Image interpretation: exploiting multiple cues , 1995 .

[15]  T. Kanade,et al.  USING A COLOR REFLECTION MODEL TO SEPARATE HIGHLIGHTS FROM OBJECT COLOR , 1987 .

[16]  C. H. Chen,et al.  Handbook of Pattern Recognition and Computer Vision , 1993 .

[17]  Jake K. Aggarwal,et al.  Color-based computer analysis of aerial photographs , 1979 .

[18]  Miroslaw Zbigniew. Bober.  General motion estimation and segmentation from image sequences , 1994 .

[19]  Geoffrey Henry Hutson.  Colour television theory : PAL-system principles and receiver circuitry , 1971 .

[20]  J. Kittler,et al.  Robust motion analysis , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[21]  N. Asada,et al.  Color image analysis by varying camera aperture , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

[22]  G. Borgefors.  Distance transformations in arbitrary dimensions , 1984 .

[23]  Dana H. Ballard,et al.  Parameter Nets , 1984, Artif. Intell..

[24]  Glenn Healey.  A parallel color algorithm for segmenting images of 3-D scenes , 1989, Sixth Multidimensional Signal Processing Workshop,.

[25]  Graham D. Finlayson,et al.  Color constancy and a changing illumination , 1994, Electronic Imaging.

[26]  Shree K. Nayar,et al.  Reflectance ratios: An extension of Land's retinex theory , 1994 .

[27]  Shree K. Nayar,et al.  Reflectance ratio: A photometric invariant for object recognition , 1993, 1993 (4th) International Conference on Computer Vision.

[28]  L. Maloney,et al.  Color constancy: a method for recovering surface spectral reflectance. , 1986, Journal of the Optical Society of America. A, Optics and image science.

[29]  John A. Richards,et al.  Remote Sensing Digital Image Analysis , 1986 .

[30]  Jiri Matas,et al.  Recognition of Cylindrical Objects Using Occluding Boundaries Obtained from Colour Based Segmentation , 1994, BMVC.

[31]  Demetri Terzopoulos,et al.  Animat vision: Active vision in artificial animals , 1995, Proceedings of IEEE International Conference on Computer Vision.

[32]  Robert C. Bolles,et al.  3DPO: A Three- Dimensional Part Orientation System , 1986, IJCAI.

[33]  Graham D. Finlayson,et al.  Color constancy in diagonal chromaticity space , 1995, Proceedings of IEEE International Conference on Computer Vision.

[34]  Glenn Healey,et al.  Using color for geometry-insensitive segmentation , 1989 .

[35]  Alireza Khotanzad,et al.  Image segmentation by a parallel, non-parametric histogram based clustering algorithm , 1990, Pattern Recognit..

[36]  James L. Crowley,et al.  Vision as Process , 1995 .

[37]  Josef Kittler,et al.  Optimal Edge Detectors for Ramp Edges , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[38]  Josef Kittler,et al.  Combining Evidence in Probabilistic Relaxation , 1989, Int. J. Pattern Recognit. Artif. Intell..

[39]  Yuichi Ohta,et al.  An approach to color constancy using multiple images , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[40]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[41]  Andrew Blake,et al.  Geometry From Specularities , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[42]  Josef Kittler,et al.  Probabilistic Relaxation as an Optimizer , 1995, BMVC.

[43]  S. Nayar,et al.  Computing Reeectance Ratios from an Image , 1993 .

[44]  Luc Cournoyer,et al.  The NRCC three-dimensional image data files , 1988 .

[45]  Jiri Matas,et al.  Control of Scene Interpretation , 1995 .

[46]  Michael J. Swain,et al.  Indexing via color histograms , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[47]  David A. Forsyth,et al.  A Novel Approach To Colour Constancy , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[48]  Josef Kittler,et al.  A locally sensitive method for cluster analysis , 1976, Pattern Recognit..

[49]  Jiri Matas,et al.  Spatial and Feature Space Clustering: Applications in Image Analysis , 1995, CAIP.

[50]  Keinosuke Fukunaga,et al.  A Graph-Theoretic Approach to Nonparametric Cluster Analysis , 1976, IEEE Transactions on Computers.

[51]  W. Christmas.  Structural matching in computer vision using probabilistic reasoning , 1995 .

[52]  Jiri Matas,et al.  Illumination Invariant Colour Recognition , 1994, BMVC.