Object Recognition Using Reflex Fuzzy Min-Max Neural Network with Floating Neurons
This paper proposes an object recognition system that is invariant to rotation, translation and scale and can be trained under partial supervision. The system is divided into two sections namely, feature extraction and recognition sections. Feature extraction section uses proposed rotation, translation and scale invariant features. Recognition section consists of a novel Reflex Fuzzy Min-Max Neural Network (RFMN) architecture with “Floating Neurons”. RFMN is capable to learn mixture of labeled and unlabeled data which enables training under partial supervision. Learning under partial supervision is of high importance for the practical implementation of pattern recognition systems, as it may not be always feasible to get a fully labeled dataset for training or cost to label all samples is not affordable. The proposed system is tested on shape data-base available online, Marathi and Bengali digits. Results are compared with “General Fuzzy Min-Max Neural Network” proposed by Gabrys and Bargiela.
KeywordsActivation Function Object Recognition Unlabeled Data Pattern Recognition System Class Node
Unable to display preview. Download preview PDF.
- 8.Torres-Mendez, L.A., Ruiz-Suarez, J.C., Sucar, L.E., Gomez, G.: Translation, rotation and scale-invariant object recognition. IEEE Trans. on Systems, Man and Cybernetics 30(1), 5–130 (2000)Google Scholar
- 9.Nandedkar, A.V., Biswas, P.K.: A Fuzzy min-max neural network classifier with compensatory neuron architecture. In: 17th Int. Cnf. on Pattern Recognition (ICPR 2004), Cambridge UK, August 2004, pp. 553–556 (2004)Google Scholar
- 11.Baitsell, G.A.: Human Biology, 2nd edn. Mc-Graw Hill Book co. inc., New York (1950)Google Scholar
- 13.Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 2nd edn. Pearson Education Pvt. Ltd., Delhi (2002)Google Scholar
- 14.Sebastian, T., Klein, P., Kimia, B.: Recognition of shapes by editing shock graphs. In: 18th Int. Conf. on Computer Vision (ICCV 2001), vol. 1, pp. 755–762 (2001), http://www.lems.brown.edu/vision/researchAreas/SIID/