Abstract
This article presents a novel approach of edged and edgeless object-shape recognition and 3D reconstruction from gradient-based analysis of tactile images. We recognize an object’s shape by visualizing a surface topology in our mind while grasping the object in our palm and also taking help from our past experience of exploring similar kind of objects. The proposed hybrid recognition strategy works in similar way in two stages. In the first stage, conventional object-shape recognition using linear support vector machine classifier is performed where regional descriptors features have been extracted from the tactile image. A 3D shape reconstruction is also performed depending upon the edged or edgeless objects classified from the tactile images. In the second stage, the hybrid recognition scheme utilizes the feature set comprising both the previously obtained regional descriptors features and some gradient-related information from the reconstructed object-shape image for the final recognition in corresponding four classes of objects viz. planar, one-edged object, two-edged object and cylindrical objects. The hybrid strategy achieves 97.62 % classification accuracy, while the conventional recognition scheme reaches only to 92.60 %. Moreover, the proposed algorithm has been proved to be less noise prone and more statistically robust.
Similar content being viewed by others
References
Alpaydin E (2004) Linear discrimination. Introduction to machine learning, 1st edn. MIT Press, Cambridge, pp 197–228
Argall BD, Billard AG (2010) A survey of tactile human-robot interactions. Rob Auton Syst 58(10):1159–1176
Bierbaum A, Gubarev I, Dillmann R (2008) Robust shape recovery for sparse contact location and normal data from haptic exploration. In: IEEE/RSJ international conference on intelligent robots and systems (IROS 2008). IEEE, Nice, pp 3200–3205
Chia-Ping C, Chu-Song C, Yi-Ping H (2009) Pixel-based correspondence, and shape reconstruction for moving objects. In: Proceedings IEEE 12th international conference on computer vision workshops (ICCV workshops). IEEE, Kyoto, pp 1962–1969
Dahiya RS, Metta G, Valle M, Sandini G (2010) Tactile sensing: from humans to humanoids. IEEE Trans Rob 26:1–20
Dietterich TG (1998) Approximate statistical test for comparing supervised classification learning algorithms. J Neural Comput 10(7):1895–1924
Duda RO, Hart PE, Stork DG (2012) Unsupervised learning and clustering. In: Pattern classification. Wiley, New York, pp 517–600
Gonzalez RC, Woods RE, Eddins SL (2012) Digital image processing using MATLAB, 4th edn. Tata McGraw Hill, LLC, USA, pp 551–614
Graupe D (2007) Principles of artificial neural networks, 2nd edn. Advanced series on circuits and systems, vol 6. World Scientific, Denver, MA
Ballesteros S, Heller MA (2008) Haptic object identification. In: Grunwald M (ed) Human haptic perception. Basics and Applications. Birkhauser Basel, Birkhauser Verlag AG, pp 207–222
Hayward V, Astley OR, Cruz-Hernandez M, Grant D, Robles-De-La-Torre G (2004) Haptic interfaces and devices. J Sens Rev 24:16–29
Heidemann G, Schopfer M (2004) Dynamic tactile sensing for object identification. In: Proceedings of IEEE international conference on robotics and automation (ICRA ‘04), vol 1. IEEE, New Orleans, LA, pp 813–818
Jain AK, Murty MN, Flynn PJ (1999) Data clustering: a review. ACM Comput Surv, N. Y., U. S. A. 31(3):264–323
Khasnobish A, Jati A, Singh G, Bhattacharyya S, Konar A, Tibarewala DN, Kim E, Nagar AK (2012) Object-shape recognition from tactile images using a feed-forward neural network. In: Proceedings IEEE international joint conference on neural networks (IJCNN 2012). IEEE, Brisbane, QLD, pp 1–8
Meier M, Schopfer M, Haschke R, Ritter H (2011) A probabilistic approach to tactile shape reconstruction. IEEE Trans Rob 27:630–635
Mitchell T (1997) Instance based learning. In: Machine learning. McGraw Hill, New York, pp 239–258
Murphy OJ (1990) Nearest neighbor pattern classification perceptrons. In: Proceedings of the IEEE, vol 78. IEEE, pp 1595–1598
Nakamoto H, Fukui W, Kobayashi F, Kojima F, Imamura N, Shirasawa H (2009) Shape classification based on tactile information by universal robot hand. In: 35th annual conference of IEEE on industrial electronics (IECON ‘09). IEEE, Porto, pp 2360–2365
Okamura AM, Turner ML, Cutkosky MR (1997) Haptic exploration of objects with rolling and sliding. In: Proceedings of the IEEE international conference on robotics and automation, vol 3. IEEE, Albuquerque, NM, pp 2485–2490
Pezzementi Z, Plaku E, Reyda C, Hager GD (2011) Tactile-object recognition from appearance information. IEEE Trans Rob 27:473–487
Romano JM, Hsiao K, Niemeyer G, Chitta S, Kuchenbecker KJ (2011) Human-inspired robotic grasp control with tactile sensing. IEEE Trans Rob 27:1067–1079
Shimoga KB, Goldenberg AA (1996) Soft robotic fingertips part II: modeling and impedance regulation. Int J Rob Res 15(4):335–350
Sigiuchi H, Watanabe S, Hasegawa Y, Nornoto M (2000) A control system for multi-fingered robotic hand with distributed touch sensor. In: 26th annual conference industrial electronics society, IECON 2000, vol 1. IEEE, Nagoya, pp 434–439
Simpkins A (2013) Robotic tactile sensing: technologies and system (Dahiya RS, Valle M 2013) [on the shelf]. IEEE Robot Autom Mag 20(2):107–107
Takamuku S, Fukuda A, Hosoda K (2008) Repetitive grasping with anthromorphic skin-covered hand enables robust haptic recognition. In: International conference on intelligent robots and systems (IROS 2008). IEEE, Nice, pp 3212–3217
Talasaz A, Patel RV (2013) Integration of force reflection with tactile sensing for minimally invasive robotics-assisted tumor localization. IEEE Trans Haptics 6:217–228
Ting Z, Hong L, Li J, Shaowei F, Jing Y (2013) Development of a flexible 3-D tactile sensor system for anthropomorphic artificial hand. IEEE Sens J 13:510–518
Visell Y (2009) Tactile sensory substitution: models for enaction in HCI. J Interact Comput 21:38–53
Webb AR, Copsey KD (2011) Nonlinear discriminant analysis—kernel and projection methods. In: Statistical pattern recognition, 3rd edn. Wiley, New York, pp 274–321
Yamada Y, Ishiguro A, Uchikawa Y (1993) A method of 3D object reconstruction by fusing vision with touch using internal models with global and local deformations. In: Proceedings international conference on robotics and automation, vol 2. IEEE, Atlanta, GA, pp 782–787
Acknowledgments
This study has been supported by University Grants Commission (UGC), India, University with Potential for Excellence—Phase II (UPE II) in Cognitive Science, Jadavpur University and Council of Scientific and Industrial Research (CSIR), India.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Khasnobish, A., Singh, G., Jati, A. et al. Object-shape recognition and 3D reconstruction from tactile sensor images. Med Biol Eng Comput 52, 353–362 (2014). https://doi.org/10.1007/s11517-014-1142-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-014-1142-1