Acta Optica Sinica, Volume. 19, Issue 8, 1074(1999)
A Neural Network-Based Approach for Invariant Recognition of 2-D Objects
A neural network-based approach is proposed for invariant recognition of two-dimensional objects. The industrial tools to be recognized have one degree of freedom, the dynamic range of their shapes leads the feature vector not uniquely defined even for a single object. The Fourier descriptors of objects boundary are taken as the features being invariant to translation, rotation and scale changes. A multilayer feedforward neural net with two hidden layer classifiers is utilized. The experimental studies involving four sorts of mechanical tools are carried out. The performance is compared to a nearest neighbor rule. It is shown that the approach is robust to not only noisy but also varying feature vector, and the neural network can recognize some untrained objects.
Get Citation
Copy Citation Text
[in Chinese], [in Chinese], [in Chinese]. A Neural Network-Based Approach for Invariant Recognition of 2-D Objects[J]. Acta Optica Sinica, 1999, 19(8): 1074