Multiscale Object Recognition under Affine Transformation

スポンサーリンク

概要

• 論文の詳細を見る

• A method to recognize planar objects undergoing affine transformation is proposed in this paper. The method is based upon wavelet multiscale features and Hopfield neural networks. The feature vector consists of the multiscale wavelet transformed extremal evolution. The evolution contains the information of the contour primitives in a multiscale manner, which can be used to discriminate dominant points, hence a good initial state of the Hopfield network can be obtained. Such good initiation enables the network to converge more efficiently. A wavelet normalization scheme was applied to make our method scale invariant and to reduce the distortion resulting from normalizing the object contours. The Hopfield neural network was employed as a global processing mechanism for feature matching and made our method suitable to recognize planar objects whose shape distortion arising from an affine transformation. The Hopfield network was improved to guarantee unique and more stable matching results. A new matching evaluation scheme, which is computationally efficient, was proposed to evaluate the goodness of matching. Two sets of images, noiseless and noisy industrial tools, undergoing affine transformation were used to test the performance of the proposed method. Experimental results showed that our method is not only effective and robust under affine transformation but also can limit the effect of noises.

• 社団法人電子情報通信学会の論文
• 1999-11-25

著者

• Lin W‐h

  National Cheng Kung Univ. Twn

• Lee J‐s

  Department Of Electrical Engineering And Computer Science

• Chen C‐h

  Department Of Management Information Systems Central Taiwan University Of Sciences And Technology

• Sun Y‐n

  National Cheng‐ Kung Univ. Twn

• Sun Yung-nien

  The Computer Science And Information Engineering National Cheng-kung University

• CHEN Chin-Hsing

  Department of Management Information Systems, Central Taiwan University of Sciences and Technology

• LIN Wen-Huei

  Department of Electrical Engineering, National Cheng Kung University

• LEE Jiann-Shu

  Computer Science and Information Engineering, Da Yeh University

• SUN Yung-Nien

  Institute of Information Engineering, National Cheng Kung University

• Lin Wen-huei

  Department Of Electrical Engineering National Cheng Kung University

• Chen Chin-hsing

  Department Of Electrical Engineering National Cheng Kung University

関連論文

• Boundary Based Parametric Polygon Morphing
• Self-Organizing Neural Networks by Construction and Pruning(Biocybernetics, Neurocomputing)
• n-Dimensional Cauchy Neighbor Generation for the Fast Simulated Annealing(Algorithm Theory)
• Improving Fairness in DiffServ Networks Using Adaptive Aggregate Markers(Networks)
• Call Admission and Efficient Allocation for Delay Guarantees
• Local Allocation of End-to-End Delay Requirement
• Multiscale Object Recognition under Affine Transformation
• Classified Vector Quantization for Image Compression Using Direction Classification
• A Genetic Grey-Based Neural Networks with Wavelet Transform for Search of Optimal Codebook
• An Edge-Preserving Image Coding System with Vector Quantization
• A New Operational Approach for Solving Fractional Calculus and Fractional Differential Equations Numerically(Discrete Mathematics and Its Applications)

もっと見る 閉じる

スポンサーリンク