Object recognition through a multi-mode fiber
- 327 Downloads
We present a method of recognizing an object through a multi-mode fiber. A number of speckle patterns transmitted through a multi-mode fiber are provided to a classifier based on machine learning. We experimentally demonstrated binary classification of face and non-face targets based on the method. The measurement process of the experimental setup was random and nonlinear because a multi-mode fiber is a typical strongly scattering medium and any reference light was not used in our setup. Comparisons between three supervised learning methods, support vector machine, adaptive boosting, and neural network, are also provided. All of those learning methods achieved high accuracy rates at about 90% for the classification. The approach presented here can realize a compact and smart optical sensor. It is practically useful for medical applications, such as endoscopy. Also our study indicated a promising utilization of artificial intelligence, which has rapidly progressed, for reducing optical and computational costs in optical sensing systems.
KeywordsObject recognition and classification Machine learning Multi-mode fiber Support vector machine Adaptive boosting Neural network
This work was supported by JSPS KAKENHI Grant Number 15K13381.
- 1.Narasimhan, S.G., Nayar, S.K.: Structured light methods for underwater imaging: light stripe scanning and photometric stereo. In: Proceedings of 2005 MTS/IEEE OCEANS, vol. 3, pp. 2610–2617 (2005)Google Scholar
- 2.Gu, J., Nayar, S., Grinspun, E., Belhumeur, P., Ramamoorthi, R.: Compressive structured light for recovering inhomogeneous participating media. In: Proc. 10th Eur. Conf. Comput. Vis. Part IV, pp. 845–858. Springer, Berlin, Heidelberg (2008)Google Scholar
- 27.Freund, Y., Schapire, R.E.: A short introduction to boosting. J. Jpn. Soc. Artif. Intell. 14, 771–780 (1999)Google Scholar
- 29.Hu, Y.H.: Handbook of Neural Network Signal Processing, 1st edn. CRC Press Inc, Boca Raton (2000)Google Scholar
- 30.Caltech computer vision database. http://www.vision.caltech.edu/archive.html. Accessed 1 Feb 2017