Description
Signal processing and machine learning techinques are two powerful frameworks
for analyzing signals and developing efficient processing and classification algorithms
for bimoedical and industrial applications.
The research acitivity of MAS group is focused on signal analysis and processing methods for ultrasonic diagnosis systems. In the last decades, ultrasound diagnosis methods are receiving increasing attention in modern medical and non destructive test (NDT) procedures, thanks to their cheapness, high portability and non-ionizing radiation.
Computer aids for cancer diagnosis, biomedical image restoration methods, advanced time-frequency analysis techinques for NDT of material, and state of the art signal processing implementation techonolgies (DSP, FPGA, GPU computing) are the main research focus.
Current Projects
Ultrasound Image Segmentation and Classification
Information Technology has hugely affected medical imaging,
making possible the realization of complex vision systems, like ultrasonography. So far the interpretation of bioimages has always been
exclusive responsibility of physicians, but recently computerized schemes have been proposed to highlight from images some important
aspects of biological tissues invisible to human eye. >> More Info
Time-Frequency Analysis of NDT signals
In the last years time frequency transformation techniques have acquired
a leading role in signal processing. However, such transformations have
some restrictive properties which make them not suitable in some
applications. In particular, the possibility of generalizing and
adaptively varying the time frequency plane tiling is a major demand. >> More Info
Signal and Image Restoration
One of the major limitation on US image quality is reduced resolution due to both the effect of limited effective aperture size and noise.
Moreover, since the US transducer pulse introduces an unwanted spectral shaping of the backscattered echo signal, deconvolution is used to
eliminate this effect and to obtain the pure tissue response. >> More Info
|