Nearest-neighbour classifiers in natural scene analysis

It is now well-established that k nearest-neighbour classi"ers o!er a quick and reliable method of data classi"cation. In this paper we extend the basic de"nition of the standard k nearest-neighbour algorithm to include the ability to resolve con#icts when the highest number of nearest neighbours are found for more than one training class (model-1). We also propose model-2 of nearest-neighbour algorithm that is based on "nding the nearest average distance rather than nearest maximum number of neighbours. These new models are explored using image understanding data. The models are evaluated on pattern recognition accuracy for correctly recognising image texture data of "ve natural classes: grass, trees, sky, river re#ecting sky and river re#ecting trees. On noise contaminated test data, the new nearest neighbour models show very promising results for further studies. We evaluate their performance with increasing values of neighbours (k) and discuss their future in scene analysis research. Crown Copyright 2001 Published by Elsevier Science Ltd. on behalf of Pattern Recognition Society. All rights reserved.

[1]  John F. Haddon,et al.  Spatio-temporal relaxation labelling applied to segmented infrared image sequences , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[2]  Edmond Mesrobian,et al.  Neural Networks for Computer Vision: A Framework for Specifications of a General Purpose Vision System , 1989, Photonics West - Lasers and Applications in Science and Engineering.

[3]  J.F. Haddon,et al.  Texture classification of segmented regions of FLIR images using neural networks , 1994, Proceedings of 1st International Conference on Image Processing.

[4]  Joe L. Mundy,et al.  The development of the Image Understanding Environment , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Azriel Rosenfeld,et al.  Image Analysis and Computer Vision: 1997 , 1998, Comput. Vis. Image Underst..

[6]  Heba Lakany,et al.  Object recognition from 2D images using Kohonen self-organized feature maps , 1997 .

[7]  John F. Haddon,et al.  Integrating Spatio-temporal Information in Image Sequence Analysis to Enforce Consistency of Interpretation , 1998, Digit. Signal Process..

[8]  John F. Haddon,et al.  Image Segmentation by Unifying Region and Boundary Information , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[10]  Sameer Singh.  A Single Nearest Neighbor Fuzzy Approach for Pattern Recognition , 1999, Int. J. Pattern Recognit. Artif. Intell..

[11]  Yves Kodratoff,et al.  Machine Learning for Object Recognition and Scene Analysis , 1994, Int. J. Pattern Recognit. Artif. Intell..

[12]  Michael Georgiopoulos,et al.  Image pattern algorithms using neural networks , 1990, Other Conferences.

[13]  Firooz A. Sadjadi.  Performance evaluation of a texture-based segmentation algorithm , 1991, Defense, Security, and Sensing.

[14]  Reiner Creutzburg,et al.  Recent Issues in Pattern Analysis and Recognition , 1989, Lecture Notes in Computer Science.

[15]  Robert L. Simpson.  Computer vision: an overview , 1991, IEEE Expert.

[16]  K. Yamamoto.  Future directions in computer vision and image understanding; ETL perspectives , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[17]  Silvana G. Dellepiane,et al.  A fuzzy approach to cue detection and region merging for image segmentation , 1989, Recent Issues in Pattern Analysis and Recognition.

[18]  Robert M. Haralick,et al.  18 Image texture survey , 1982, Classification, Pattern Recognition and Reduction of Dimensionality.

[19]  James F. Boyce,et al.  Co-occurrence matrices for image analysis , 1993 .

[20]  Markos Markou,et al.  NEAREST NEIGHBOUR STRATEGIES FOR IMAGE UNDERSTANDING , 1999 .

[21]  Neill W. Campbell,et al.  Interpreting image databases by region classification , 1997, Pattern Recognit..

[22]  Hui Liu,et al.  Adaptive image segmentation by quantization , 1992, Optics & Photonics.

[23]  Sameer Singh.  Effect of noise on generalisation in massively parallel fuzzy systems , 1998, Pattern Recognit..

[24]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[25]  R. Booth,et al.  A Neural Network Implementation For Real-Time Scene Analysis , 1988, Other Conferences.

[26]  Oscar Firschein.  Defense Applications of Image Understanding , 1995, IEEE Expert.