Speckle degrades severely the quality of medical B-scan ultrasonic images, especiallyit blurs edges and details of images. An adaptive speckle suppression and edge enhancementmethod based on Nakagami distribution is p...Speckle degrades severely the quality of medical B-scan ultrasonic images, especiallyit blurs edges and details of images. An adaptive speckle suppression and edge enhancementmethod based on Nakagami distribution is presented. The statistics of log-compressed echo im-ages is derived for Nakagami distribution. An adaptive filter based on local statistical propertyof speckle is designed. The stick technique that utilizes sticks with different sizes and variousorientations is applied to locally approximate certain linear features of image. The local regionis a stick instead of a usual window, the orientation of sticks is decided by hypothesis test op-timizing method and the length of sticks is obtained by region growing technique. Performanceof the new method has been tested on the phantom and ultrasound images of pig muscle andechocardiographic. The results show that the technique effectively reduces the speckle noise whilepreserving and enhancing the tissue edge and resolvable details.展开更多
Existing blockwise empirical likelihood(BEL)method blocks the observations or their analogues,which is proven useful under some dependent data settings.In this paper,we introduce a new BEL(NBEL)method by blocking the ...Existing blockwise empirical likelihood(BEL)method blocks the observations or their analogues,which is proven useful under some dependent data settings.In this paper,we introduce a new BEL(NBEL)method by blocking the scoring functions under high dimensional cases.We study the construction of confidence regions for the parameters in spatial autoregressive models with spatial autoregressive disturbances(SARAR models)with high dimension of parameters by using the NBEL method.It is shown that the NBEL ratio statistics are asymptoticallyχ^(2)-type distributed,which are used to obtain the NBEL based confidence regions for the parameters in SARAR models.A simulation study is conducted to compare the performances of the NBEL and the usual EL methods.展开更多
文摘Speckle degrades severely the quality of medical B-scan ultrasonic images, especiallyit blurs edges and details of images. An adaptive speckle suppression and edge enhancementmethod based on Nakagami distribution is presented. The statistics of log-compressed echo im-ages is derived for Nakagami distribution. An adaptive filter based on local statistical propertyof speckle is designed. The stick technique that utilizes sticks with different sizes and variousorientations is applied to locally approximate certain linear features of image. The local regionis a stick instead of a usual window, the orientation of sticks is decided by hypothesis test op-timizing method and the length of sticks is obtained by region growing technique. Performanceof the new method has been tested on the phantom and ultrasound images of pig muscle andechocardiographic. The results show that the technique effectively reduces the speckle noise whilepreserving and enhancing the tissue edge and resolvable details.
基金Supported by the National Natural Science Foundation of China(12061017,12361055),and the Research Fund of Guangxi Key Lab of Multi-source Information Mining&Security(22-A-01-01)。
文摘Existing blockwise empirical likelihood(BEL)method blocks the observations or their analogues,which is proven useful under some dependent data settings.In this paper,we introduce a new BEL(NBEL)method by blocking the scoring functions under high dimensional cases.We study the construction of confidence regions for the parameters in spatial autoregressive models with spatial autoregressive disturbances(SARAR models)with high dimension of parameters by using the NBEL method.It is shown that the NBEL ratio statistics are asymptoticallyχ^(2)-type distributed,which are used to obtain the NBEL based confidence regions for the parameters in SARAR models.A simulation study is conducted to compare the performances of the NBEL and the usual EL methods.
