This paper presents the development of a portable system with the aim of allowing blind people to detect and recognize Euro banknotes. The developed device is based on a Raspberry Pi electronic instrument and a Raspberry Pi camera, Pi NoIR (No Infrared filter) dotted with additional infrared light, which is embedded into a pair of sunglasses that permit blind and visually impaired people to independently handle Euro banknotes, especially when receiving their cash back when shopping. The banknote detection is based on the modified Viola and Jones algorithms, while the banknote value recognition relies on the Speed Up Robust Features (SURF) technique. The accuracies of banknote detection and banknote value recognition are 84% and 97.5%, respectively.

This work describes the development of a face detection and recognition application developed into Raspberry Pi and Android. The application connects with the Raspberry Pi by Bluetooth protocols. The object detection is based on boosted cascade while the face recognition is based on Eigenfaces. The developed system may be especially useful for visually impaired users since it can contribute to facilitate their autonomous behavior during their everyday life. The developed device shows great potential for extrapolation to other areas as education of visually impaired users.

Since Computed Tomography (CT) is one of the most widely used medical imaging tests, it is essential to work on methods that reduce the radiation the patient is exposed to. Although there are several possible approaches to achieve this, we focus on reducing the exposure time through sparse sampling. With this approach, efficient algebraic methods are needed to be able to generate the images in real time, and since their computational cost is high, using high-performance computing is essential. In this paper we present a GPU (Graphics Processing Unit) software for solving the CT image reconstruction problem using the QR factorization performed with out-of-core (OOC) techniques. This implementation is optimized to reduce the data transfer times between disk, CPU, and GPU, as well as to overlap input/output operations and computations. The experimental study shows that a block cache stored on main page-locked memory is more efficient than using a cache on GPU memory or mirroring it in both GPU and CPU memory. Compared to a CPU version, this implementation is up to 6.5 times faster, providing an improved image quality when compared to other reconstruction methods. The software developed is an optimized version of the QR factorization for GPU that allows the algebraic reconstruction of CT images with high quality and resolution, with a performance that can be compared with state-of-the-art methods used in clinical practice. This approach allows reducing the exposure time of the patient and thus the radiation dose.

In CT (computerized tomography) imaging reconstruction, the acquired sinograms are usually noisy, so artifacts will appear on the resulting images. Thus, it is necessary to find the adequate filters to combine with reconstruction methods that eliminate the greater amount of noise possible without altering in excess the information that the image contains. The present work is focused on the evaluation of several filtering techniques applied in the elimination of artifacts present in CT sinograms. In particular, we analyze the elimination of Gaussian and Speckle noise. The chosen filtering techniques have been studied using four functions designed to measure the quality of the filtered image and compare it with a reference image. In this way, we determine the ideal parameters to carry out the filtering process on the sinograms, prior to the process of reconstruction of the images. Moreover, we study their application on reconstructed noisy images when using noisy sinograms and finally we select the best filter to combine with an iterative reconstruction method in order to test if it improves the quality of the images. With this, we can determine the feasibility of using the selected filtering method for our CT reconstructions with projections reduction, concluding that the bilateral filter is the filter that behaves best with our images. We will test it when combined with our iterative reconstruction method, which consists on the Least Squares QR method in combination with a regularization technique and an acceleration step, showing how integrating this filter with our reconstruction method improves the quality of the CT images.

Background and objective: As Computed Tomography scans are an essential medical test, many techniques have been proposed to reconstruct high-quality images using a smaller amount of radiation. One approach is to employ algebraic factorization methods to reconstruct the images, using fewer views than the traditional analytical methods. However, their main drawback is the high computational cost and hence the time needed to obtain the images, which is critical in the daily clinical practice. For this reason, faster methods for solving this problem are required. Methods: In this paper, we propose a new reconstruction method based on the QR factorization that is very efficient on affordable equipment (standard multicore processors and standard Solid-State Drives) by using Out-Of-Core techniques. Results: Combining both affordable hardware and the new software proposed in our work, the images can be reconstructed very quickly and with high quality. We analyze the reconstructions using real Computed Tomography images selected from a dataset, comparing the QR method to the LSQR and FBP. We measure the quality of the images using the metrics Peak Signal-To-Noise Ratio and Structural Similarity Index, obtaining very high values. We also compare the efficiency of using spinning disks versus Solid-State Drives, showing how the latter performs the Input/Output operations in a significantly lower amount of time. Conclusions: The results indicate that our proposed me thod and software are valid to efficiently solve large-scale systems and can be applied to the Computed Tomography reconstruction problem to obtain high-quality images. (C) 2020 The Authors. Published by Elsevier B.V.