Instrumentation & Measurement Magazine 24-3 - 90

develop a highly reliable framework is to recognize objects
from multiple touches. As such, an unsupervised network is
first leveraged to reduce the dimensionality of features from
each imprint and then multiple imprints are concatenated to
be classified using kNN and SVM. Results confirm that, with
at least four touches on the object at visually salient locations,
the object can be perfectly recognized (Table 1).

[10]	L. Itti, C. Koch, and E. Niebur, " A model of saliency-based visual
attention for rapid scene analysis, " IEEE Trans. Pattern Anal. Mach.
Intell., vol. 20, no. 11, pp. 1254-1259, 1998.
[11]	G. Rouhafzay and A.-M. Cretu, " Perceptually improved 3D object
representation based on guided adaptive weighting of feature
channels of a visual-attention model, " 3D Res., vol. 9, no. 3, p. 29,
Sep. 2018.
[12]	R. L. Klatzky and S. J. Lederman, " Identifying objects from a

Conclusion

haptic glance, " Percept. Psychophys., vol. 57, no. 8, pp. 1111-1123,

Recent research makes use of biologically inspired computation and artificial intelligence as efficient means to solve
real-world problems. Drawing inspiration from visuo-tactile
collaboration in the human sensorial loop, this paper discusses possible approaches to exploit vision and touch sensing
modalities to accelerate and optimize the process of 3D object
representation and recognition for robotic manipulation.

References
[1]	 S. Kennett, M. Eimer, C. Spence, and J. Driver, " Tactile-visual
links in exogenous spatial attention under different postures:
convergent evidence from psychophysics and ERPs, " J. Cogn.
Neurosci., vol. 13, no. 4, pp. 462-478, May 2001.

Nov. 1995.
[13]	G. Rouhafzay and A.-M. Cretu, " Object recognition from haptic
glance at visually salient locations, " IEEE Trans. Instrum. Meas.,
vol. 69, no. 3, pp. 672-682, Mar. 2020.

Ghazal Rouhafzay (grouh050@uottawa.ca) is a Ph.D. degree
candidate at the School of Electrical Engineering and Computer Science, University of Ottawa, Canada and a Research
Assistant at the University of Québec in Outaouais, Canada. Her current research interest includes 3D sensing and
modeling, biologically inspired visual and tactile data integration, deep learning techniques for visual and tactile object
recognition.

[2]	 S. Lacey and K. Sathian, " Visuo-haptic multisensory object
recognition, categorization, and representation, " Front. Psychol.,
vol. 5, no. JUL, pp. 1-15, Jul. 2014.
[3]	 S. Foix, G. Alenya, and C. Torras, " Lock-in time-of-flight (ToF)
cameras: a survey, " IEEE Sens. J., vol. 11, no. 9, pp. 1917-1926, Sep.
2011.
[4]	 E. Trucco and A. Verri, Introductory Techniques for 3-D Computer
Vision. Upper Saddle River, NJ, USA: Prentice Hall, 1998.
[5]	 J. Geng, " Structured-light 3D surface imaging: a tutorial, " Adv.
Opt. Photonics, vol. 3, no. 2, p. 128, Jun. 2011.
[6]	 J. Davis, D. Neh, R. Ramamoorthi, and S. Rusinkiewicz,
" Spacetime stereo: a unifying framework for depth from

Ana-Maria Cretu (M'10-SM'17) obtained her M.Sc. and Ph.D.
degrees from the School of Electrical Engineering and Computer Science at University of Ottawa, Canada. She is currently
Associate Professor with the Department of Computer Science
and Engineering at the University of Québec in Outaouais,
Canada. Her research interests include computational intelligence, soft computing, biologically-inspired computational
models, tactile and vision sensing, and 3D object sensing, modeling and manipulation. She serves as Technical Committee
Member for several international conferences and as a reviewer for journals and transactions.

triangulation, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no.
2, pp. 296-302, Feb. 2005.
[7]	 H. Yousef, M. Boukallel, and K. Althoefer, " Tactile sensing for
dexterous in-hand manipulation in robotics-a review, " Sensors
Actuators A Phys., vol. 167, no. 2, pp. 171-187, Jun. 2011.
[8]	 P. Regtien and E. Dertien, Sensors for Mechatronics. Cambridge,
MA, USA: Elsevier, 2018.
[9]	 G. Rouhafzay and A.-M. Cretu, " A virtual tactile sensor with
adjustable precision and size for object recognition, " in Proc. IEEE
Int. Conf. Computational Intelligence and Virtual Environments for
Measurement Syst. and Applications (CIVEMSA), 2018.

90	

Pierre Payeur is a Professor at the School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa,
Canada. He is the Director of the Sensing and Machine Vision
for Automation and Robotic Intelligence Research Laboratory and a Founding Member of the Vision, Imaging, Video
and Autonomous Systems Research Laboratory. He holds a
Ph.D. degree in electrical engineering from University Laval,
Québec, Canada. His research interests include machine vision, tactile sensing, automation, robotics and computational
intelligence.

IEEE Instrumentation & Measurement Magazine	

May 2021
Instrumentation & Measurement Magazine 24-3

Table of Contents for the Digital Edition of Instrumentation & Measurement Magazine 24-3
