Deep neural networks (DNNs) are used to classify and reconstruct the input images from the intensity of the speckle patterns that result after the inputs are propagated through multimode fiber (MMF). We were able to demonstrate this result for fibers up to 1 km long by training the DNNs with a database of 16,000 handwritten digits. Better recognition accuracy was obtained when the DNNs were trained to first reconstruct the input and then classify based on the recovered image. We observed remarkable robustness against environmental instabilities and tolerance to deviations of the input pattern from the patterns with which the DNN was originally trained.
1 August 2013 in International Journal of Heat and Fluid Flow
Deep neural networks have been used to map multi-modal, multi-photon microscopy measurements of a label-free tissue sample to its corresponding histologically stained brightfield microscope colour image. It is shown that the extra structural and functional contrasts provided by using two source modes, namely two-photon excitation microscopy and fluorescence lifetime imaging, result in a more faithful reconstruction of the target haematoxylin and eosin stained mode. This modal mapping procedure can aid histopathologists, since it provides access to unobserved imaging modalities, and translates the high-dimensional numerical data generated by multi-modal, multi-photon microscopy into traditionally accepted visual forms. Furthermore, by combining the strengths of traditional chemical staining and modern multi-photon microscopy techniques, modal mapping enables label-free, non-invasive studies of in vivo tissue samples or intravital microscopic imaging inside living animals. The results show that modal co-registration and the inclusion of spatial variations increase the visual accuracy of the mapped results.
1 July 2016 in International Journal of Heat and Mass Transfer
A non-intrusive method is presented for measuring different fluidic properties in a microfluidic chip by optically monitoring the flow of droplets. A neural network is used to extract the desired information from the images of the droplets. We demonstrate the method in two applications: measurement of the concentration of each component of a water/alcohol mixture, and measurement of the flow rate of the same mixture. A large number of droplet images are recorded and used to train deep neural networks (DNN) to predict the flow rate or the concentration. It is shown that this method can be used to quantify the concentrations of each component with a 0.5% accuracy and the flow rate with a resolution of 0.05 ml/h. The proposed method can in principle be used to measure other properties of the fluid such as surface tension and viscosity.