Machine Learning Based Shape Classification Using Tactile Sensor Array
Contact shape recognition is an important functionality of any tactile sensory system as it can be used to classify the object in contact with the tactile sensor. In this work we propose and implement an affine transformation invariant 2D contact shape classification system. A tactile sensor array gives the contact pressure data which is fed to an image enhancement system which sends the binary contact image to the global, region and contour based feature selection block. The five element feature vectors is used as input to a voting based classifier which implements a C4.5 algorithm and a naïve Bayes classifier and combine the results to get an improved classifier. The system is designed and tested offline in a Pressure Profile system based tactile array using both cross validation and separate dataset. Results indicate that combining simple classifiers increases the accuracy of the system while being computationally efficient.
KeywordsTactile Machine learning contact-shape classification voting classifier
Unable to display preview. Download preview PDF.
- 2.Liu, H., Song, X., Nanayakkara, T., Seneviratne, L., Althoefer, K.: A computationally fast algorithm for local contact shape and pose classification using a tactile array sensor. In: Proceedings of International Conference on Robotics and Automation (ICRA), pp. 1410–1415 (2012)Google Scholar
- 3.Liu, H., Greco, J., Song, X., Bimbo, J., Seneviratne, L., Althoefer, K.: Tactile image based contact shape recognition using neural network. In: Multisensor Fusion and Integration for Intelligent Systems (MFI), pp. 138–143 (2012)Google Scholar
- 4.Bhattacharjee, T., Rehg, J., Kemp, C.: Haptic classification and recognition of objects using a tactile sensing forearm. In: Intelligent Robots and Systems (IROS), pp. 4090–4097 (2012)Google Scholar
- 5.Pezzementi, Z., Plaku, E., Reyda, C., Hager, G.: Tactile-object recognition from appearance information. Robotics 27, 473–487 (2011)Google Scholar
- 6.Ibrayev, R., Jia, Y.: Tactile recognition of algebraic shapes using differential invariants. Robotics and Automation 2, 1548–1553 (2004)Google Scholar
- 7.Aoyagi, S., Tanaka, T., Minami, M.: Recognition of Contact State of Four Layers Arrayed Type Tactile Sensor by using Neural Network. In: Information Acquisition, pp. 393–397 (2006)Google Scholar
- 8.Dahiya, R., Metta, G., Valle, M., Sandini, G.: Tactile sensing—from humans to humanoids. Robotics 26, 1–20 (2010)Google Scholar
- 11.Gonzalez, R., Woods, R., Eddins, S.: Digital image processing using MATLAB, 2nd edn. Gatesmark Publishing, Knoxville (2009)Google Scholar
- 12.Peura, M., Iivarinen, J.: Efficiency of simple shape descriptors. In: Aspects of Visual Form, pp. 443–451 (1997)Google Scholar
- 14.Quinlan, J.: C4. 5: Programs for Machine Learning 1 (1993)Google Scholar
- 15.Good, I.: Probability and the Weighing of Evidence, London (1950)Google Scholar