Object Identification with Uncertain Information using Fuzzy Classification

Object identification in unknown environment when uncertain information is presented is a challenging research area. A sensory fusion technique where the image and distance information are fused to produce better results is discussed in this paper. Two types of low cost sensors used for collect the image and distance information. Distance information is filtered through fuzzy filtering to reduce the noise while the two dimensional fast Fourier transform was taken for image information in certain grid points. This information clustered through unsupervised learning technique such as fuzzy C-means clustering and extract cluster centers. Then the training data set is constructed accordingly. This information is used to train a back propagation type neural network. After training the neural network it was tested with the testing data. The results show successful accuracy and performance when using this unsupervised generic input vector construction method

[1]  Lakhmi C. Jain,et al.  A concurrent fuzzy-neural network approach for decision support systems , 2003, The 12th IEEE International Conference on Fuzzy Systems, 2003. FUZZ '03..

[2]  E. L. Walker.  Combining geometric invariants with fuzzy clustering for object recognition , 1999, 18th International Conference of the North American Fuzzy Information Processing Society - NAFIPS (Cat. No.99TH8397).

[3]  Ray G. Gosine,et al.  Application of a fuzzy classification technique in computer grading of fish products , 1998, IEEE Trans. Fuzzy Syst..

[4]  Wei-Chung Lin,et al.  A Neural Network Approach to CSG-Based 3-D Object Recognition , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  K.R. Venugopal,et al.  Generic Feature Extraction for Classification using Fuzzy C - Means Clustering , 2005, 2005 3rd International Conference on Intelligent Sensing and Information Processing.

[6]  Vallipuram Muthukkumarasamy,et al.  A Texture Feature Extraction Technique Using 2 D – DFT and Hamming Distance , 2001 .

[7]  Vallipuram Muthukkumarasamy,et al.  A texture extraction technique using 2D-DFT and Hamming distance , 2003, Proceedings Fifth International Conference on Computational Intelligence and Multimedia Applications. ICCIMA 2003.