Abstract
Motivated by the aim of developing a vision-based system to assist the social interaction of blind persons, the performance of some face detectors are evaluated. The detectors are applied to manually annotated video sequences acquired by blind persons with a glass-mounted camera and a necklace-mounted one. The sequences are relevant to the specific application and demonstrate to be challenging for all the considered detectors. A further analysis is performed to reveal how the performance is affected by some features such as occlusion, rotations, size and position of the face within the frame.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
- 3.
- 4.
- 5.
We did not change the default parameters on purpose, for two reasons: first, some detectors have fixed parameters and second, the choice of default parameters made by the authors of the detector may reflect a compromise between various aspects of performance that we are not aware of.
References
Online: Be my eyes. http://www.bemyeyes.org
Jin, Y., Kim, J., Kim, B., Mallipeddi, R., Lee, M.: Smart cane: face recognition system for blind. In: Proceedings of 3rd International Conference on Human-Agent Interaction, HAI 2015, pp. 145–148. ACM, New York (2015)
Chaudhry, S., Chandra, R.: Design of a mobile face recognition system for visually impaired persons. CoRR abs/1502.00756 (2015)
Carrato, S., Fenu, G., Medvet, E., Mumolo, E., Pellegrino, F.A., Ramponi, G.: Towards more natural social interactions of visually impaired persons. In: Battiato, S., Blanc-Talon, J., Gallo, G., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2015. LNCS, vol. 9386, pp. 729–740. Springer, Cham (2015). doi:10.1007/978-3-319-25903-1_63
Zafeiriou, S., Zhang, C., Zhang, Z.: A survey on face detection in the wild: past, present and future. Comput. Vis. Image Underst. 138, 1–24 (2015)
Hsu, G.S., Chu, T.Y.: A framework for making face detection benchmark databases. IEEE Trans. Circuits Syst. Video Technol. 24(2), 230–241 (2014)
Carrato, S., Marsi, S., Medvet, E., Pellegrino, F.A., Ramponi, G., Vittori, M.: Computer vision for the blind: a dataset for experiments on face detection and recognition. In: Proceedings of 39th International Convention on Information and Communication Technology, Electronics and Microelectronics, pp. 1479–1484. Mipro Croatian Society, Opatija (2016)
Fazzi, E., Lanners, J., Danova, S., Ferrarri-Ginevra, O., Gheza, C., Luparia, A., Balottin, U., Lanzi, G.: Stereotyped behaviours in blind children. Brain Dev. 21(8), 522–528 (1999)
Bonetto, M., Carrato, S., Fenu, G., Medvet, E., Mumolo, E., Pellegrino, F.A., Ramponi, G.: Image processing issues in a social assistive system for the blind. In: 2015 9th International Symposium on Image and Signal Processing and Analysis (ISPA), pp. 216–221. IEEE (2015)
Frazor, R.A., Geisler, W.S.: Local luminance and contrast in natural images. Vis. Res. 46(10), 1585–1598 (2006)
Viola, P., Jones, M.J.: Robust real-time face detection. Int. J. Comput. Vis. 57(2), 137–154 (2004)
Liao, S., Jain, A.K., Li, S.Z.: A fast and accurate unconstrained face detector. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 211–223 (2016)
Markuš, N., Frljak, M., Pandžić, I.S., Ahlberg, J., Forchheimer, R.: Object detection with pixel intensity comparisons organized in decision trees (2013). arXiv preprint arXiv:1305.4537
Dundar, A., Jin, J., Martini, B., Culurciello, E.: Embedded streaming deep neural networks accelerator with applications. IEEE Trans. Neural Netw. Learn. Syst. (2016, to appear)
Kuhn, H.W.: The Hungarian method for the assignment problem. Nav. Res. Logist. Q. 2(1–2), 83–97 (1955)
Fenu, G., Jain, N., Medvet, E., Pellegrino, F.A., Pilutti Namer, M.: On the assessment of segmentation methods for images of mosaics. In: Proceedings of 10th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2015), pp. 130–137 (2015)
Acknowledgment
This work has been supported by the University of Trieste - Finanziamento di Ateneo per progetti di ricerca scientifica - FRA 2014, and by a private donation in memory of Angelo Soranzo (1939–2012).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
De Marco, M., Fenu, G., Medvet, E., Pellegrino, F.A. (2017). Computer Vision for the Blind: A Comparison of Face Detectors in a Relevant Scenario. In: Gaggi, O., Manzoni, P., Palazzi, C., Bujari, A., Marquez-Barja, J. (eds) Smart Objects and Technologies for Social Good. GOODTECHS 2016. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 195. Springer, Cham. https://doi.org/10.1007/978-3-319-61949-1_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-61949-1_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-61948-4
Online ISBN: 978-3-319-61949-1
eBook Packages: Computer ScienceComputer Science (R0)