Solutions for the quality control of metallic surfaces are proposed. Specifically, we study a deflectometric apparatus based on coaxial structured light and the related algorithmic procedure, which is able to detect the faulty surface of a sample captured by a video sequence. First, by considering the metallic surface a dynamic scene illuminated under different light conditions, we develop the descriptor residuals of linear evolution of light (RLEL) that extracts the defectiveness information starting from the movement of the object without explicitly considering the physical characteristics of the light structure. Then, leveraging on RLEL, we present a hybrid learning (HL) technique capable of overcoming the data-driven approach used in classic deep learning (DL). By exploiting a multisteps training process, we combine the model-based descriptor RLEL and a classical data-driven convolutional neural network (CNN) to obtain an unconventional gray-box CNN, which exceeds the performance of popular DL solutions such as 3-D-inception and 3-D-residual DL networks. Remarkably, HL also shows its validity in comparing the performance of the same network structures trained not in a hybrid way, namely without the injection of the model-based information given by RLEL.
In this paper, an effective and novel automatic learning solution for the quality control of metallic objects surfaces is proposed, which can be seamlessly integrated into the industrial process. Such a system requires a coaxial illuminator to capture the object view with a single camera while lighting it with structured light: in this way, the object surface can be viewed in time as a dynamic scene under different illumination conditions. By relying on a linear model to describe the expected evolution of the light over the object of interest, the Residuals of Linear Evolution of Light (RLEL) algorithm is derived with the specific aim of identifying and characterizing anomalies and defects through the residuals of a least square approach. Then, a novel learning strategy is developed that exploits the model-based RLEL descriptor and thus promotes itself as an alternative strategy to the black box approach of Convolutional Neural Networks (CNNs). By combining both the data-driven and the model-based learning approaches to perform the inspection task, an Hybrid Learning (HL) procedure is defined: in a first phase, the HL exploits an Encoder-Decoder network to incorporate the model-based description while, in a second phase, it uses only the pre-trained encoder to drive the learning process of a 3D-CNN. In doing so, the proposed procedure reaches interesting results that exceed also the performance of state-of-the-art 3D-Inception and 3D-Residual networks.
With this work we report on the design, development and testing of near UV LED-based systems for oxygen gas sensing. The design and developed system is an optoelectronic setup based on 405 nm LEDs which excites and measures the photoluminescence emitted from a porphyrin based luminophor. By means of an accurate optical and optoelectronic setup, the system is able to operate without the need of avalanche photodiodes, thus resulting in a compact and low energy structure. The optical setup is specifically designed to maximize both the LED light exciting the luminophor and converted light acquired from the sensor.
Nowadays, the adaptive optics (AO) system is of fundamental importance to reduce the effect of atmospheric
turbulence on the images formed on large ground telescopes. In this paper the AO system takes advantage
of the knowledge of the current turbulence characteristics, that are estimated by data, to properly control the
deformable mirrors. The turbulence model considered in this paper is based on two assumptions: considering
the turbulence as formed by a discrete set of layers moving over the telescope lens, and each layer is modeled as
a Markov-Random-Field. The proposed Markov-Random-Field approach is exploited for estimating the layers'
characteristics. Then, a linear predictor of the turbulent phase, based on the computed information on the
turbulence layers, is constructed. Since scalability and low computational complexity of the control algorithms
are important requirements for real AO systems, the computational complexity properties of the proposed model
are investigated. Interestingly, the proposed model shows a good scalability and an almost linear computational
complexity thanks to its block diagonal structure. Performances of the proposed method are investigated by means of some simulations.