Basically, a 3D scanning system comprises high-resolution cameras, optics, and AI algorithms integration to provide multiple benefits to large manufacturing units. Indeed, unlike touch probing, 3D scanning is one of most relevant computer vision application which provides conceptual view of the inspected part. 3D scanners can validate whether the material is sufficient to proceed with machining or not. Alternatively, Camera calibration is an important process in scanning system setup which has direct impact on system performance particularly precision. In this work we attempt to conceptually design and test a fully automated and low-cost scanner for producing three-dimensional models with millimeter-scale resolution for object measurement and inspection. Hence, a stereovision system is set up where pair of cameras is mounted to acquire image pairs to perform a scan. Promising and potential result is achieved by demonstrated analytical and mapped output.

Pansharpening is achieved by inferring spatial details derived from a PANchromatic (PAN) image into its corresponding expanded multispectral (MS) bands. In this letter, we propose to apply an adaptive superpixel-based injection scheme that modulates the PAN details through an optimization procedure. Optimal injection coefficients can be locally estimated by using the shuffled complex evolution developed in the University of Arizona (SCE-UA) algorithm over multiple local segments (i.e., superpixels) resulting from the simple linear iterative clustering (SLIC) method. The performance of the proposed approach is assessed using degraded and real data sets acquired from WorldView-3 and WorldView-4 satellites. Experimental results show the suitability of the proposed adaptive injection scheme compared with other state-of-the-art pansharpening methods in terms of spatial and spectral qualities.

The objective of this paper is to extend the Maximum Adaptive Exponential Weighted Moving Average (Max-AEWMA) chart to the Max Double AEWMA (Max-DAEWMA) chart. The Max-DAEWMA statistic is based on the Max of the absolute values of the two DAEWMA statistics, one for controlling the variance and the other for the mean. The combined novel technique, is called particle filter (PF)-based Max-DAEWMA for detecting faults of wastewater treatment plants (WWTP). The statistical chart, Max-DAEWMA is applied to detect the fault in mean and/or drifts in WWTP systems where the state variables are estimated using PF technique. The results show the effectiveness of the Max-DAEWMA method over Max-DEWMA and EWMA charts.

In this paper, we develop an improved fault detection (FD) technique in order to enhance monitoring abilities of nonlinear chemical processes. Kernel principal component analysis (KPCA) is an effective data driven technique for monitoring nonlinear processes. However, it is well known that data collected from complex and multivariate processes are multiscale due to the variety of changes that could occur in process with different localization in time and frequency. Thus, to enhance process monitoring abilities, we propose to combine advantages of KPCA and multiscale representation using wavelets by constructing a multiscale KPCA model and a new detection chart named multiscale kernel generalized likelihood ratio test (MS-KGLRT) is derived for fault detection. The detection performance of the new chart is studied using the Tennessee Eastman process (TEP).

It is well known that Exponentially Weighted Moving Average (EWMA) chart is designed to be optimal and efficient to quickly detect small faults. However, the classical EWMA can not perform well in the case of simultaneously large and small faults. To address this limitation, we propose to use an adaptive or a variable parameters control chart. Therefore, in this paper, we propose a novel approach, called particle filter (PF)-based adaptive EWMA (AEWMA) chart, with time-varying smoothing parameter lambda, to detect the fault in Wastewater Treatment Plant (WWTP) process. So that, the PF is applied to compute the residuals, and the AEWMA chart is used to detect the faults. The validation of the developed PF-based AEWMA technique is done using a simulated benchmark COST WWTP BSM1 model. The proposed PF-based AEWMA approach showed better detection abilities when compared to the classical EWMA and Shewhart charts.

In this paper, we address the problem of spectral unmixing in urban hyperspectral images using a Maximum A Posteriori (MAP)-based Non-negative Matrix Factorization (NMF) approach. Considering a Linear-Quadratic (LQ) mixing model, we seek to decompose the spectrum observed in each pixel of the image into a set of pure material spectra, as well as their abundance fractions and the mixing coefficients associated with products of these pure material spectra. The main idea of the proposed method is to take into account the available prior information about the unknown parameters for a better estimation of them. To this end, we first derive a MAP-based cost function, then minimize it using a projected gradient algorithm by modifying a recently proposed NMF method adapted to LQ mixtures. Simulation results confirm the relevance of our approach.

In this paper, the potential use of P-band radar signal for the estimation of soil roughness parameters is analyzed. The Integral Equation Model (IEM) is used to study the sensitivity of backscattered P-band signal to soil surface parameters. A new roughness parameter referred to as Zp, combining the root mean square surface height and the correlation length, is proposed to describe the behavior of P-band radar signal as a function of soil roughness. The IEM model is validated using real data covering a large range of roughness values, derived from experimental airborne P-band SAR campaigns made over agricultural fields. Discrepancies between the measurements and simulations led to the analysis of the influence of low frequency roughness structures on backscattering simulations. The analysis of the behavior of P-band radar signal as a function of multi-scale soil roughness (micro topography and large roughness structures) reveals the complexity of using P-band data for the analysis of bare surface soil parameters.

Over the past decade, the field of automatic speaker recognition has been the subject of extensive research looking for an efficient determination of a person's identity. Despite the essential role played by acoustic characteristics in order to discriminate between speakers. The research of discriminative information about a person remains a major challenge. The main objective of this paper is to present a new approach employing additional information which is dialect detection with a novel parameterization of the speech to improve the task of speaker identification. The superiority of the proposed system has been demonstrated by different kernels function of Support Vector Machines (SVM) with speakers taken from TIMIT database.

Gaussian mixture models (GMM) have become the standard method used for speaker recognition systems. A recent discovery is that combining GMM approach with another classifier is an effective method for speaker classification. We consider the GMM supervector in the context of support vector machines (SVM). We construct a support vector machine tested with two kernel functions employing the GMM supervectors. The main idea of the study is to combine the discriminative classifier SVM and the traditional GMM pattern classification with a new dimensional cepstral feature vector extracted from the speech to achieve better classification rate. This idea has been analytically formulated and tested on speakers from TIMIT database. First we describe the SVM-GMM system then we briefly discuss how the new low dimensional feature vector can feed to identification rate. We show comparative results obtained with GMM, SVM, GMM-SVM based system and existing works. Thereafter, we show that the new hybrid system can outperform the standard GMM-SVM based system and give remarkable increases in speaker identification rates.

The study of the EEG inverse problem consists in active brain's source reconstruction. In this paper we review the localization error from this reconstruction using a new configuration of electrodes on the scalp. The suggested new configuration consists on studying each lobe separately. The objective is to minimize the localization error with a minimum number of electrodes. To validate this study, we use the Shrinking sLORETA-FOCUSS method as a solution of the inverse problem. The obtained results show very interesting values using a minimum number of electrodes placed on the scalp surface. In this paper we will embed the proposed approach on an FPGA platform using adaptation techniques. Due to different electrodes we used the dynamic partial reconfiguration technic. The different electrodes data are treated by IPs based on VHDL accelerators. The proposed architecture will be embedded on Xilinx Virtex 5 ML 507 platform.

The ultrasound imaging is a coherent imaging technique, the resulting images are characterized by a grainy appearance called speckle. In that case the ultrasound images are difficult to use automatically in clinical use, then treatments are required for this type of images. In fact, a pre-treatment phase is essential to filter the speckle and to improve the quality of ultrasound images which will then be segmented to extract the necessary forms that exist. This paper represents the importance of the pre-treatment for segmentation applied to cardiac echographic images. Speckle filtering is realized by means of the wavelet transform algorithm, and then we use Snakes algorithm to locate and extract cardiac structures.

In this paper, we propose a secure semi-fragile self-authentication watermarking technique based on embedding of perceptual hash derived from discrete wavelet transformation of jpeg2000 encoder. The original image is transformed on wavelet domain using JPEG2000 encoder. Then, we extract LL sub-band coefficients in order to perform perceptual hash. This hash will be embedded back into the same sub-band as a watermark using QIM approach. The experimental results show that the proposed scheme is capable to detect the authenticity of watermarked image while preserving the visual quality.

We consider how new technologies could be used, particularly in deafness healthcare. This concerns recent designs of hearing aid systems dedicated to restoring hearing, at least partially. In general, the apparatus could be in two basic forms: a conventional hearing aid dedicated to restore hearing loss that is not severs, and cochlear prostheses dedicated to restoring total or profound hearing loss. With the development of digital signal processing 'DSP' technologies, these prostheses are becoming more flexible in use and performance. Two complementary strategies for digital speech processing could be proposed for hearing-aid systems using a DSP-driven board. These two strategies were conceived around a temporal approach utilising a filter bank model and a spectral approach utilising a fast Fourier transform 'FFT'. Clinically, it is important to distinguish these two strategies especially during apparatus adjustments, to achieve patient comfort. Digital signal processing dedicated to hearing aid research was based on an adjustable FFT/filter-bank based algorithm. It could be adapted to speech amplification in a conventional hearing aid, or to electrical stimulation in cochlear prostheses. This algorithm, which should be used in flexible and fully programmable devices, would certainly improve hearing capacity since we have included additional possibilities in processing sounds.