Using Nakagami MRF mode to deal with ultrasound data
碩士 === 銘傳大學 === 應用統計資訊學系碩士班 === 103 === Recent research on ultrasound image, in addition to the traditional ultrasound B-mode imaging, has been expanded to the Nakagami parameter images. To investigate the parameter estimates, Markov Random Field is a main focus of research on the selection of ultra...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2015
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/89913926892678476777 |
| Summary: | 碩士 === 銘傳大學 === 應用統計資訊學系碩士班 === 103 === Recent research on ultrasound image, in addition to the traditional ultrasound B-mode imaging, has been expanded to the Nakagami parameter images. To investigate the parameter estimates, Markov Random Field is a main focus of research on the selection of ultrasound image point. In this study, we used Nakagami-MRF model and the least absolute shrinkage and selection operator (LASSO) to estimate the parameter value m.
We use the simulated data of Rayleigh distribution in LASSO estimation to estimate the value of m. The procedure of estimation contains huge inverse matrix operations. We used two method (original matrix, partitioned matrix). The result of partitioned matrix method can solve the problem of inverse matrix operations and obtain the value of m which is close to the theoretical value of Rayleigh distribution.
|
|---|