G. Betta - Academia.edu (original) (raw)
Papers by G. Betta
IEEE Transactions on Instrumentation and Measurement, 2000
This paper presents the current state-of-the-art of residual generation techniques adopted in ins... more This paper presents the current state-of-the-art of residual generation techniques adopted in instrument fault detection and isolation. Both traditional and innovative methods are described with their advantages and their limits. The improvement of analytical redundancy technique performances for better dealing with high-dynamics systems and/or with online applications is pointed out as the most interesting need to focus the research efforts.
Eddy currents induced in passive structures are of paramount importance for the functioning of a ... more Eddy currents induced in passive structures are of paramount importance for the functioning of a tokamak. First of all, they are the key ingredient in slowing down plasma instabilities from Alfvén to electromagnetic time scales [1], allowing active magnetic control and hence the actual possibility of having a long-lasting discharge. Moreover, during a disruption, large eddy currents are induced in the vessel and other conducting structures, giving rise to significant electromagnetic forces that may be even challenging for the integrity of the device [2]. It is hence very important to have a reliable indication of such eddy currents; this is usually done in an indirect way, by measuring the magnetic field in proximity of the vessel and using suitable modelling assumptions to retrieve the value of current density [3]. In this paper we present the design and experimental validation of a probe directly measuring eddy currents flowing in a conductor. The proposed probe is a dipole-like s...
... p., fazzari al, ferrari e., ferrero a., freschi pietro, galbiati f., giovannelli g., mancuso ... more ... p., fazzari al, ferrari e., ferrero a., freschi pietro, galbiati f., giovannelli g., mancuso d., mannino s., marchesi r., martello s., miceli c., mirandola r., palumbo m., pennisi c., periti e., petri d., pinto mr, prinzi p., quadrani f., rudan m., salvatore m., santoro a., spoto m., stefano e., tagliavini ...
Quality Measurement: The Indispensable Bridge between Theory and Reality (No Measurements? No Science! Joint Conference - 1996: IEEE Instrumentation and Measurement Technology Conference and IMEKO Technical Committee 7. Conference Proceedings
An advanced scheme for Instrument Fault Detection and Isolation is proposed. It is mainly based o... more An advanced scheme for Instrument Fault Detection and Isolation is proposed. It is mainly based on Artificial Neural Networks (ANNs), organized in layers and handled by knowledge-based analytical redundancy relationships. ANN design and training is performed by genetic algorithms which allow ANN architecture and parameters to be easily optimized. The diagnostic performance of the proposed scheme is evaluated with reference
International Journal of Applied Electromagnetics and Mechanics
The paper proposes the use of a suitable multi-frequency approach applied to a novel instrument f... more The paper proposes the use of a suitable multi-frequency approach applied to a novel instrument for eddy current non-destructive testing on conductive materials. The instrument is composed by a smart eddy current probe, based on a Giant Magneto Resistance sensor, and by a suitable processing unit. Key features of the proposed instrument are the capability of detecting, locating, and characterizing thin defects such as superficial and sub-superficial cracks. The proposed multi-frequency solution, together with a suitable data processing, allow both the sensitivity in the defect detection to be increased and the ability to evaluate the defect characteristics in terms of shape and dimension to be improved.
2015 XVIII AISEM Annual Conference, 2015
In this paper a suitable methodology for the improvement of the reliability of results in classif... more In this paper a suitable methodology for the improvement of the reliability of results in classification systems based on 3D images is proposed. More in detail, it is based on the knowledge of the uncertainty of the features constituting the 3D image (obtained processing a pair of two 2D stereoscopic images) and on a suitable statistical approach providing a confidence level to the classification result. These pieces of information are then managed in order to improve the classification performance in terms of correct classification and missed classification percentages. The experimental results, obtained applying the methodology on an Active Appearance Models algorithm, a popular method for face recognition based on 3D features, show that, compared with a traditional approach (which generally does not take into account the uncertainty on 3D features), the proposed methodology allows to significantly improve the classification performance even in scenarios characterized by a high uncertainty.
2015 IEEE Metrology for Aerospace (MetroAeroSpace), 2015
Fast reconstruction of defects geometry is one of the main goal of Eddy Current Non-destructive t... more Fast reconstruction of defects geometry is one of the main goal of Eddy Current Non-destructive testing. The information about the type of defects, their shapes, orientations and geometrical characteristics is of great importance in evaluating the impact of defects on structures' integrity and operation safety. From one point of view, the knowledge of the defect shape could give important information about the manufacturing, the use or the cause that have stressed the specimen and generated the defect, and from the other point of view the reconstruction of geometrical parameters of defect could be made easier if the shape of the defect is known. Although many inverse procedures have been developed for Eddy Current Testing, usually high-computational time and resources are requested, hampering the application of 3D reconstruction methods in on-line or in-situ inspections. In this paper a fast 2D defect profile reconstruction technique is presented based on image processing. The main idea of the proposed method is that images obtained from the maps of magnetic field on specimen with flaws, express a trend attributable to a class of known functions. In particular, the shape of the obtained image depends on both the type of defect that the type of measurement probe adopted. Then using a suitable reference image related to the response of the probe as a digital filter to process the acquired image through deconvolution or correlation operations, the shape of the flaw that has generated the image can be retrieved.
2015 XVIII AISEM Annual Conference, 2015
Localization is becoming a very important and challenging task of Wireless Sensor Networks (WSN),... more Localization is becoming a very important and challenging task of Wireless Sensor Networks (WSN), especially in low cost and low data-rate networks that employ a large number of nodes. Since the data collected may have no meaning if the sensor positions are unknown, it becomes of fundamental importance to be able to locate each node of the network with respect to an absolute or relative coordinate system. Various algorithms that propose strategies to determine the nodes position of a network are present in literature. They are divided into range-based and range-free algorithms. Some of the range-based algorithms estimate distance from Received Signal Strength Indicator (RSSI) measurements between the unknown node and the reference nodes. Estimators of this method appreciate the fact that it does not require additional hardware, because indicators of RSSI are generally built-in in radio chipsets now on market. It can be considered a valid solution for localization both in terms of economic cost and in terms of energy consumption. However, this solution presents high uncertainty due to the high variability that influences the RSSI measurements and to the different choices that characterize the implemented RSSI measurement methods. The authors, inspired by previous works present in literature, are aimed in exploring the influence of the most relevant causes of RSSI variability, as the multipath, and their effect on the RSSI values for WSNs. In this context they propose a simple measurement method based on the frequency diversity able to mitigate these effects.
Proceedings of 1995 IEEE Instrumentation and Measurement Technology Conference - IMTC '95, 1995
The paper proposes a digital level transducer based on an optical fiber from which the cladding w... more The paper proposes a digital level transducer based on an optical fiber from which the cladding was removed in n zones at a fixed distance one from each other. A theoretical analysis of the propagation in such a modified fiber was carried out, highlighting the good potentiality of the proposed sensor. A 1 m full scale, 25 mm resolution prototype was then designed, using the results of a numerical simulation, and realized, optimizing both the sensitive element and the conditioning hardware. The static and dynamic characterization tests carried out show high repeatability, good accuracy, and acceptable dynamic performance
2005 IEEE Instrumentationand Measurement Technology Conference Proceedings, 2005
Early detection of melanoma is one of the greatest challenges of dermatologic practice today. A n... more Early detection of melanoma is one of the greatest challenges of dermatologic practice today. A new diagnostic method, the "ELM 7 point checklist", defines a set of seven features, based on colour and texture parameters, which describe the malignancy of a lesion. This paper describes image processing algorithms which estimate chromatic and shape parameters involved in the detection of the
Lecture Notes in Electrical Engineering, 2015
Time synchronization in low-cost wireless sensor networks based on synchronization algorithm is a... more Time synchronization in low-cost wireless sensor networks based on synchronization algorithm is a today relevant issue as for the networks costs, energy consumption and indoor uses aspects. Among the other those based on the one way messaging and, in particular, on the adoption of regressive algorithms are widely used in many application contexts. This paper proposes a preliminary performance analysis aimed at highlighting the sensitivity of the regression-based algorithms versus some influence factor typical of the low cost applications, such as the finite resolution of the timing clock, the presence of clock drift, clock jitter and wander, the presence of real latencies of the radio devices, the presence of real latencies of the microcontroller device. The aim is to weight the influence of each one of these influence factors on the overall synchronization performance. The analysis is carried out a suitable and controlled experimental environment.
Lecture Notes in Electrical Engineering, 2013
The paper illustrates an automatic procedure for calibration and adjustment of Giant Magneto Resi... more The paper illustrates an automatic procedure for calibration and adjustment of Giant Magneto Resistance (GMR) sensors capable to quantify and reduce some of their measurement problems, as non-linearity, hysteresis and temperature dependence, in order to allow their use also as magnetometers for magnetic field amplitude measurement. The procedure, based on a hardware/software solution, shows a good measurement performance without introducing a relevant complexity in the whole measurement procedure.
2013 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 2013
The paper proposes a hand held eddy current based measurement instrument for the detection of thi... more The paper proposes a hand held eddy current based measurement instrument for the detection of thin defect on conductive planar specimens. The measurement instrument adopts a Giant Magneto Resistance based probe to detect the eddy current reaction field from the specimen and a suitable positioning system to measure the sensor position in the specimen plane. Two main novelties are proposed respect to previous realizations by the same authors: the improvement of the probe through the use of a bi-axial magnetic field sensor and the implementation of a suitable multi-frequency excitation strategy; the realization of a new processing section, based on an optimized SVM regressor, for the reliable estimation of the position and the geometrical characteristics of the thin defect. Results obtained on both simulated environments and real specimens showed the goodness of the proposal and the ability in the geometrical characterization of the thin defect.
IEEE International Workshop on Medical Measurement and Applications, 2006. MeMea 2006., 2006
Early detection of melanoma is one of the greatest challenges of dermatologic practice today. A n... more Early detection of melanoma is one of the greatest challenges of dermatologic practice today. A new diagnostic method, the "ELM 7 point checklist", defines a set of seven features, based on color and texture parameters, which describe the malignancy of a lesion. This paper describes image processing algorithms developed for the detection of the occurrence of "Atypical Pigment Network" and "Atypical Vascular Pattern" that are two important criteria of the "7-point checklist" method.
Measurement, 1994
ABSTRACT
Proceedings of the 20th IEEE Instrumentation Technology Conference (Cat. No.03CH37412), 2003
The evaluation of the uncertainties involved in the measurement of conducted emissions by adjusta... more The evaluation of the uncertainties involved in the measurement of conducted emissions by adjustable speed drive was dealt with. Besides the measurement uncertainty due to the all components of the measurement chain, the uncertainty contribution due to nonrepeatability and the additional one that may arise from configuration set-up and working conditions were investigated. Following the test arrangements suggested by EMC
Proceedings of the IEEE International Symposium on Industrial Electronics ISIE-02, 2002
In this paper, an accurate experimental investigation of several pulse width modulated techniques... more In this paper, an accurate experimental investigation of several pulse width modulated techniques for power converters feeding induction motors is described, with the aim of performing their comparison in terms of EMC performances. For this purpose, a test desk based on a voltage source inverter feeding a low power induction motor has been assembled in an semi-anechoic chamber. Besides, a single board digital modulator, which executes all the PWM strategies under consideration, has been manufactured. By means of a suitable measurement set-up, all the dominant emission sources and signals in the converter have been identified for each modulation technique and compared.
Lecture Notes in Electrical Engineering, 2015
The paper proposes a new approach to classification and recognition problems which takes into acc... more The paper proposes a new approach to classification and recognition problems which takes into account the measurement uncertainty affecting input data for improving the overall reliability of such kind of processes. The proposed method is based on an effective probabilistic approach for the evaluation of the confidence level of system outputs and the suitable use of such information for improving the performance in terms of correct decision.
2011 IEEE International Instrumentation and Measurement Technology Conference, 2011
ABSTRACT The paper proposes a method that takes into account the measurement uncertainty in patte... more ABSTRACT The paper proposes a method that takes into account the measurement uncertainty in pattern recognition procedures, where, generally, an input is classified searching the most similar, by means of some quantitative parameters, in a database of reference to the comparing the unknown . The result of the comparison between the measured values and the reference ones is not deterministic because of the uncertainty on both the value sets. As a consequence, the decision (recognition of subject) has a risk level, thus it might be wrong. The proposed approach is focused to give a quantitative assessment of the measurement uncertainty and consequently the risk level in decision-making. The case study refers to the face recognition with the Linear Discriminant Analysis (LDA) approach. The recognition is performed by comparing the values obtained with LDA algorithm on observed images and those obtained applying the same LDA to stored reference images.
IEEE Transactions on Instrumentation and Measurement, 2000
This paper presents the current state-of-the-art of residual generation techniques adopted in ins... more This paper presents the current state-of-the-art of residual generation techniques adopted in instrument fault detection and isolation. Both traditional and innovative methods are described with their advantages and their limits. The improvement of analytical redundancy technique performances for better dealing with high-dynamics systems and/or with online applications is pointed out as the most interesting need to focus the research efforts.
Eddy currents induced in passive structures are of paramount importance for the functioning of a ... more Eddy currents induced in passive structures are of paramount importance for the functioning of a tokamak. First of all, they are the key ingredient in slowing down plasma instabilities from Alfvén to electromagnetic time scales [1], allowing active magnetic control and hence the actual possibility of having a long-lasting discharge. Moreover, during a disruption, large eddy currents are induced in the vessel and other conducting structures, giving rise to significant electromagnetic forces that may be even challenging for the integrity of the device [2]. It is hence very important to have a reliable indication of such eddy currents; this is usually done in an indirect way, by measuring the magnetic field in proximity of the vessel and using suitable modelling assumptions to retrieve the value of current density [3]. In this paper we present the design and experimental validation of a probe directly measuring eddy currents flowing in a conductor. The proposed probe is a dipole-like s...
... p., fazzari al, ferrari e., ferrero a., freschi pietro, galbiati f., giovannelli g., mancuso ... more ... p., fazzari al, ferrari e., ferrero a., freschi pietro, galbiati f., giovannelli g., mancuso d., mannino s., marchesi r., martello s., miceli c., mirandola r., palumbo m., pennisi c., periti e., petri d., pinto mr, prinzi p., quadrani f., rudan m., salvatore m., santoro a., spoto m., stefano e., tagliavini ...
Quality Measurement: The Indispensable Bridge between Theory and Reality (No Measurements? No Science! Joint Conference - 1996: IEEE Instrumentation and Measurement Technology Conference and IMEKO Technical Committee 7. Conference Proceedings
An advanced scheme for Instrument Fault Detection and Isolation is proposed. It is mainly based o... more An advanced scheme for Instrument Fault Detection and Isolation is proposed. It is mainly based on Artificial Neural Networks (ANNs), organized in layers and handled by knowledge-based analytical redundancy relationships. ANN design and training is performed by genetic algorithms which allow ANN architecture and parameters to be easily optimized. The diagnostic performance of the proposed scheme is evaluated with reference
International Journal of Applied Electromagnetics and Mechanics
The paper proposes the use of a suitable multi-frequency approach applied to a novel instrument f... more The paper proposes the use of a suitable multi-frequency approach applied to a novel instrument for eddy current non-destructive testing on conductive materials. The instrument is composed by a smart eddy current probe, based on a Giant Magneto Resistance sensor, and by a suitable processing unit. Key features of the proposed instrument are the capability of detecting, locating, and characterizing thin defects such as superficial and sub-superficial cracks. The proposed multi-frequency solution, together with a suitable data processing, allow both the sensitivity in the defect detection to be increased and the ability to evaluate the defect characteristics in terms of shape and dimension to be improved.
2015 XVIII AISEM Annual Conference, 2015
In this paper a suitable methodology for the improvement of the reliability of results in classif... more In this paper a suitable methodology for the improvement of the reliability of results in classification systems based on 3D images is proposed. More in detail, it is based on the knowledge of the uncertainty of the features constituting the 3D image (obtained processing a pair of two 2D stereoscopic images) and on a suitable statistical approach providing a confidence level to the classification result. These pieces of information are then managed in order to improve the classification performance in terms of correct classification and missed classification percentages. The experimental results, obtained applying the methodology on an Active Appearance Models algorithm, a popular method for face recognition based on 3D features, show that, compared with a traditional approach (which generally does not take into account the uncertainty on 3D features), the proposed methodology allows to significantly improve the classification performance even in scenarios characterized by a high uncertainty.
2015 IEEE Metrology for Aerospace (MetroAeroSpace), 2015
Fast reconstruction of defects geometry is one of the main goal of Eddy Current Non-destructive t... more Fast reconstruction of defects geometry is one of the main goal of Eddy Current Non-destructive testing. The information about the type of defects, their shapes, orientations and geometrical characteristics is of great importance in evaluating the impact of defects on structures' integrity and operation safety. From one point of view, the knowledge of the defect shape could give important information about the manufacturing, the use or the cause that have stressed the specimen and generated the defect, and from the other point of view the reconstruction of geometrical parameters of defect could be made easier if the shape of the defect is known. Although many inverse procedures have been developed for Eddy Current Testing, usually high-computational time and resources are requested, hampering the application of 3D reconstruction methods in on-line or in-situ inspections. In this paper a fast 2D defect profile reconstruction technique is presented based on image processing. The main idea of the proposed method is that images obtained from the maps of magnetic field on specimen with flaws, express a trend attributable to a class of known functions. In particular, the shape of the obtained image depends on both the type of defect that the type of measurement probe adopted. Then using a suitable reference image related to the response of the probe as a digital filter to process the acquired image through deconvolution or correlation operations, the shape of the flaw that has generated the image can be retrieved.
2015 XVIII AISEM Annual Conference, 2015
Localization is becoming a very important and challenging task of Wireless Sensor Networks (WSN),... more Localization is becoming a very important and challenging task of Wireless Sensor Networks (WSN), especially in low cost and low data-rate networks that employ a large number of nodes. Since the data collected may have no meaning if the sensor positions are unknown, it becomes of fundamental importance to be able to locate each node of the network with respect to an absolute or relative coordinate system. Various algorithms that propose strategies to determine the nodes position of a network are present in literature. They are divided into range-based and range-free algorithms. Some of the range-based algorithms estimate distance from Received Signal Strength Indicator (RSSI) measurements between the unknown node and the reference nodes. Estimators of this method appreciate the fact that it does not require additional hardware, because indicators of RSSI are generally built-in in radio chipsets now on market. It can be considered a valid solution for localization both in terms of economic cost and in terms of energy consumption. However, this solution presents high uncertainty due to the high variability that influences the RSSI measurements and to the different choices that characterize the implemented RSSI measurement methods. The authors, inspired by previous works present in literature, are aimed in exploring the influence of the most relevant causes of RSSI variability, as the multipath, and their effect on the RSSI values for WSNs. In this context they propose a simple measurement method based on the frequency diversity able to mitigate these effects.
Proceedings of 1995 IEEE Instrumentation and Measurement Technology Conference - IMTC '95, 1995
The paper proposes a digital level transducer based on an optical fiber from which the cladding w... more The paper proposes a digital level transducer based on an optical fiber from which the cladding was removed in n zones at a fixed distance one from each other. A theoretical analysis of the propagation in such a modified fiber was carried out, highlighting the good potentiality of the proposed sensor. A 1 m full scale, 25 mm resolution prototype was then designed, using the results of a numerical simulation, and realized, optimizing both the sensitive element and the conditioning hardware. The static and dynamic characterization tests carried out show high repeatability, good accuracy, and acceptable dynamic performance
2005 IEEE Instrumentationand Measurement Technology Conference Proceedings, 2005
Early detection of melanoma is one of the greatest challenges of dermatologic practice today. A n... more Early detection of melanoma is one of the greatest challenges of dermatologic practice today. A new diagnostic method, the "ELM 7 point checklist", defines a set of seven features, based on colour and texture parameters, which describe the malignancy of a lesion. This paper describes image processing algorithms which estimate chromatic and shape parameters involved in the detection of the
Lecture Notes in Electrical Engineering, 2015
Time synchronization in low-cost wireless sensor networks based on synchronization algorithm is a... more Time synchronization in low-cost wireless sensor networks based on synchronization algorithm is a today relevant issue as for the networks costs, energy consumption and indoor uses aspects. Among the other those based on the one way messaging and, in particular, on the adoption of regressive algorithms are widely used in many application contexts. This paper proposes a preliminary performance analysis aimed at highlighting the sensitivity of the regression-based algorithms versus some influence factor typical of the low cost applications, such as the finite resolution of the timing clock, the presence of clock drift, clock jitter and wander, the presence of real latencies of the radio devices, the presence of real latencies of the microcontroller device. The aim is to weight the influence of each one of these influence factors on the overall synchronization performance. The analysis is carried out a suitable and controlled experimental environment.
Lecture Notes in Electrical Engineering, 2013
The paper illustrates an automatic procedure for calibration and adjustment of Giant Magneto Resi... more The paper illustrates an automatic procedure for calibration and adjustment of Giant Magneto Resistance (GMR) sensors capable to quantify and reduce some of their measurement problems, as non-linearity, hysteresis and temperature dependence, in order to allow their use also as magnetometers for magnetic field amplitude measurement. The procedure, based on a hardware/software solution, shows a good measurement performance without introducing a relevant complexity in the whole measurement procedure.
2013 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 2013
The paper proposes a hand held eddy current based measurement instrument for the detection of thi... more The paper proposes a hand held eddy current based measurement instrument for the detection of thin defect on conductive planar specimens. The measurement instrument adopts a Giant Magneto Resistance based probe to detect the eddy current reaction field from the specimen and a suitable positioning system to measure the sensor position in the specimen plane. Two main novelties are proposed respect to previous realizations by the same authors: the improvement of the probe through the use of a bi-axial magnetic field sensor and the implementation of a suitable multi-frequency excitation strategy; the realization of a new processing section, based on an optimized SVM regressor, for the reliable estimation of the position and the geometrical characteristics of the thin defect. Results obtained on both simulated environments and real specimens showed the goodness of the proposal and the ability in the geometrical characterization of the thin defect.
IEEE International Workshop on Medical Measurement and Applications, 2006. MeMea 2006., 2006
Early detection of melanoma is one of the greatest challenges of dermatologic practice today. A n... more Early detection of melanoma is one of the greatest challenges of dermatologic practice today. A new diagnostic method, the "ELM 7 point checklist", defines a set of seven features, based on color and texture parameters, which describe the malignancy of a lesion. This paper describes image processing algorithms developed for the detection of the occurrence of "Atypical Pigment Network" and "Atypical Vascular Pattern" that are two important criteria of the "7-point checklist" method.
Measurement, 1994
ABSTRACT
Proceedings of the 20th IEEE Instrumentation Technology Conference (Cat. No.03CH37412), 2003
The evaluation of the uncertainties involved in the measurement of conducted emissions by adjusta... more The evaluation of the uncertainties involved in the measurement of conducted emissions by adjustable speed drive was dealt with. Besides the measurement uncertainty due to the all components of the measurement chain, the uncertainty contribution due to nonrepeatability and the additional one that may arise from configuration set-up and working conditions were investigated. Following the test arrangements suggested by EMC
Proceedings of the IEEE International Symposium on Industrial Electronics ISIE-02, 2002
In this paper, an accurate experimental investigation of several pulse width modulated techniques... more In this paper, an accurate experimental investigation of several pulse width modulated techniques for power converters feeding induction motors is described, with the aim of performing their comparison in terms of EMC performances. For this purpose, a test desk based on a voltage source inverter feeding a low power induction motor has been assembled in an semi-anechoic chamber. Besides, a single board digital modulator, which executes all the PWM strategies under consideration, has been manufactured. By means of a suitable measurement set-up, all the dominant emission sources and signals in the converter have been identified for each modulation technique and compared.
Lecture Notes in Electrical Engineering, 2015
The paper proposes a new approach to classification and recognition problems which takes into acc... more The paper proposes a new approach to classification and recognition problems which takes into account the measurement uncertainty affecting input data for improving the overall reliability of such kind of processes. The proposed method is based on an effective probabilistic approach for the evaluation of the confidence level of system outputs and the suitable use of such information for improving the performance in terms of correct decision.
2011 IEEE International Instrumentation and Measurement Technology Conference, 2011
ABSTRACT The paper proposes a method that takes into account the measurement uncertainty in patte... more ABSTRACT The paper proposes a method that takes into account the measurement uncertainty in pattern recognition procedures, where, generally, an input is classified searching the most similar, by means of some quantitative parameters, in a database of reference to the comparing the unknown . The result of the comparison between the measured values and the reference ones is not deterministic because of the uncertainty on both the value sets. As a consequence, the decision (recognition of subject) has a risk level, thus it might be wrong. The proposed approach is focused to give a quantitative assessment of the measurement uncertainty and consequently the risk level in decision-making. The case study refers to the face recognition with the Linear Discriminant Analysis (LDA) approach. The recognition is performed by comparing the values obtained with LDA algorithm on observed images and those obtained applying the same LDA to stored reference images.