In this paper, we propose an algorithm for recognition of objects from 2D images. The algorithm is neural network based. It uses Kohonen self-organised feature maps (SOFM) as a vector quantiser whose performance is compared to that of EM technique. A codebook is designed using SOFM and a simple labelling procedure is used to label the feature vectors, then the labelled training data set of di erent objects are recognised by the resilient propagation network. The algorithm is applied to 2D images of industrial objects.
|Number of pages||8|
|Journal||Pattern Recognition and Image Analysis|
|Publication status||Published - 1997|
- 2D images
- self organized feature maps
Lakany, H., Schukat-Talamazzini, E. G., Niemann, H., & Ghonaimy, M. A. R. (1997). Object recognition from 2D images using Kohonen self-organized feature maps. Pattern Recognition and Image Analysis, 7(3), 301-308.