Alfredo Paolillo

A DSP-based FFT-analyzer for the fault diagnosis of rotating machine based on vibration analysis

A DSP-based measurement system dedicated to the vibration analysis on rotating machines was designed and realized. Vibration signals are on-line acquired and processed to obtain a continuous monitoring of the machine status. In case of fault, the system is capable of isolating the fault with a high reliability. The paper describes in detail the approach followed to built up fault and unfault models together with the chosen hardware and software solutions. A number of tests carried out on small-size three-phase asynchronous motors highlights high promptness in detecting faults, low false alarm rate, and very good diagnostic performance.

An automatic measurement system for the evaluation of carotid intima-media thickness

This paper presents an automatic system for the measurement of carotid intima-media thickness (IMT) that is based on the digital processing of ultrasound images. The measurement technique is described in detail, highlighting the advantages compared to other methods and, reporting some experimental results. Finally, an analytical approach is used to estimate the intrinsic accuracy of the system.

Estimation of signal parameters in the frequency domain in the presence of harmonic interference: a comparative analysis

In this paper, a novel method for the estimation of the parameters of the spectral components of a signal, also in the case of harmonic interference, is characterized and compared to other methods proposed in literature. The comparison criteria include the evaluation of residual errors and uncertainties on estimated parameters for different multicomponent signals.

An improved procedure for the automatic detection of dermoscopic structures in digital ELM images of skin lesions

Early detection of melanoma is a very critical issue in todaypsilas dermatologic practice. Different diagnostic methods have been proposed which define multiple criteria for the evaluation of the malignancy of a lesion. The paper is devoted to the detection of an important dermatologic structure: the atypical pigmented network. A proposal is described for the application of decision-tree classification techniques to the results of specific image processing algorithms for the estimation of chromatic and structural parameters.

A Comparison Between Stereo-Vision Techniques for the Reconstruction of 3-D Coordinates of Objects

This paper deals with the problems in setting up stereo-vision systems for contactless measurement of dimensional parameters in industrial environments. Two implicit calibration algorithms for the reconstruction of three-dimensional (3-D) real-world coordinates of objects from pairs of two-dimensional image coordinates have been implemented and compared. The former is based on a direct linear transformation, while the latter on an Artificial Neural Network (ANN). The results of the comparison made on artificial and real objects are finally reported in terms of statistical analysis of the reconstruction error

Towards an automatic diagnosis system for skin lesions: Estimation of blue-whitish veil and regression structures

This paper deals with ELM image processing for automatic analysis of pigmented skin lesions which represents one of the greatest challenges of dermatologic practice today. The “ELM 7 point checklist” defines a set of seven features, based on colour and texture parameters, which describe the malignancy of a lesion. It has been revealed as faster and with the same accuracy than the traditional ABCD criteria in the diagnosis of melanoma. A preliminary approach to the automated diagnosis of melanocytic skin lesions, based on ELM 7 point checklist is proposed. In particular, the image processing algorithms and classification techniques involved in the automatic detection of the occurrence of two criteria (Blue-whitish Veil and Regression structures) are introduced and the experimental results are reported.

A software tool for the diagnosis of melanomas

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. It has been presented as faster and with the same accuracy than the traditional ABCD criteria in the diagnosis of melanoma. In this paper a new system for automated diagnosis of melanocytic skin lesions, based on ELM 7 point checklist, is introduced.

Face Based Recognition Algorithms: A First Step Toward a Metrological Characterization

Face-based recognition systems have been increasingly used in many different applications in todays society, starting from surveillance and access control to the authentication for banking activities. Therefore, in the last few years an increasing interest in the performance characterization and improvement of such systems can be found in the scientific community. Most of the methodologies for testing the performance of such systems are based on the evaluation of recognition reliability indexes that are generally related to the probability of a false positive and/or of a false negative.

Uncertainty evaluation in face recognition algorithms

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.

Face-based recognition techniques: proposals for the metrological characterization of global and feature-based approaches

Security systems based on face recognition through video surveillance systems deserve great interest. Their use is important in several areas including airport security, identification of individuals and access control to critical areas. These systems are based either on the measurement of details of a human face or on a global approach whereby faces are considered as a whole. The recognition is then performed by comparing the measured parameters with reference values stored in a database. The result of this comparison is not deterministic because measurement results are affected by uncertainty due to random variations and/or to systematic effects. In these circumstances the recognition of a face is subject to the risk of a faulty decision. Therefore, a proper metrological characterization is needed to improve the performance of such systems. Suitable methods are proposed for a quantitative metrological characterization of face measurement systems, on which recognition procedures are based. The proposed methods are applied to three different algorithms based either on linear discrimination, on eigenface analysis, or on feature detection.