Weighted Median (WM) filters have the robustness and edge preserving capability of the classical median filter and resemble linear FIR filters in certain properties. Furthermore, WM filters belong to the broad class of nonlinear filters called stack filters. This enables the use of the tools developed for the latter class in characterizing and analyzing the behavior and properties of WM filters, e.g. noise attenuation capability. The fact that WM filters are threshold functions allows the use of neural network training methods to obtain adaptive WM filters. In this tutorial paper we trace the development of the theory of WM filtering from its beginnings in the median filter to the recently developed theory of optimal weighted median filtering. Applications discussed include: idempotent weighted median filters for speech processing, adaptive weighted median and optimal weighted median filters for image and image sequence restoration, weighted medians as robust predictors in DPCM coding and Quincunx coding, and weighted median filters in scan rate conversion in normal TV and HDTV systems.
. Imaging of superparamagnetic iron oxide nanoparticles based on their non-linear response to alternating magnetic fields shows promise for imaging cells and vasculature in healthy and diseased tissue. Such imaging can be achieved through x-space reconstruction typically along a unidirectional Cartesian trajectory, which rapidly convolutes the particle distribution with a 'anisotropic blurring' point spread function (PSF), leading to images with anisotropic resolution.
Medical image reconstruction methods based on deep learning have recently demonstrated powerful performance in photoacoustic tomography (PAT) from limited-view and sparse data. However, because most of these methods must utilize conventional linear reconstruction methods to implement signal-to-image transformations, their performance is restricted. In this paper, we propose a novel deep learning reconstruction approach that integrates appropriate data pre-processing and training strategies. The Feature Projection Network (FPnet) presented herein is designed to learn this signal-to-image transformation through data-driven learning rather than through direct use of linear reconstruction. To further improve reconstruction results, our method integrates an image post-processing network (U-net). Experiments show that the proposed method can achieve high reconstruction quality from limited-view data with sparse measurements. When employing GPU acceleration, this method can achieve a reconstruction speed of 15 frames per second.
Sir:FigureThe craniofacial cleft is a rare congenital craniomaxillofacial anomaly caused by embryonic developmental abnormality. It exits in a multitude of patterns, varies in degree of severity, and involves multiple anatomical regions and organs in the face. Since the nineteenth century, many experts have been endeavoring to study the malformation and to design varying classification methods based on different aspects.1–3 Of the available classification methods in the literature, the most popular and clinically accepted one is the Tessier classification because of its many distinct merits.4 In particular, it can enable communication and discussion among physicians.5 In clinical practice, however, the Tessier classification indeed has some inconveniences. Actually, it only uses the numbers 0 to 14 to simply present the malformations, although the manifestations of craniofacial clefts are very complex. If a physician does not check the patient or review the case record, he or she cannot determine the actual condition of a patient from only the diagnosis provided by the Tessier classification. For example, if a patient is diagnosed as Tessier cleft no. 4, one cannot image the concrete conditions of the patient's soft tissues, bone, eyelids, lacrimal system, and so forth. Therefore, it is necessary to establish a classification method of craniofacial clefts that can provide a clear mental image of the patient's conditions and facilitate communication among physicians. For this reason, we have combined the idea of the Eight Diagrams of China and the Tessier classification into a spectacle frame diagram (Fig. 1).Fig. 1: A spectacle frame classification of the craniofacial clefts.In this spectacle frame diagram, the numbers 0 to 14 still have the same meaning as those of the Tessier classification on a one-to-one basis for soft-tissue craniofacial clefts. However, LS represents the lacrimal system deformities; N illustrates the nasal bone cleft or coloboma; and the three Ms symbolize the maxilla cleft or coloboma, each showing one-third part of the maxilla according to the different craniofacial clefts. Z represents the zygomatic bone and arch cleft or coloboma, and the three Fs show the frontal bone cleft or coloboma. Like M, each F shows a different one-third part of the frontal bone. U represents the upper eyelid cleft or coloboma and L is the lower eyelid cleft or coloboma. According to the clinical features and image examination of patients, one can blacken the corresponding areas of this spectacle frame diagram simply to represent the situation of soft-tissue cleft, maxilla, frontal bone, nasal bone, eyelids, lacrimal system, and other features. This method has been attempted for the purpose of describing symbolically the patient's representation in our practice (Fig. 2). The initial experience suggests that the advantages of our method include the following: (1) it is easily to display the true cleft in every patient, including untreated and treated patients, without any detail overlooked; (2) it is more favorable for description and communication among physicians; and (3) it can avoid the time-consuming review of the case history in every consultation.Fig. 2: (Above) A child with bilateral Tessier cleft no. 4 and Tessier cleft no. 2 on the left side with bilateral lower eyelid coloboma and lacrimal system deformity. (Below) The complex conditions of the patient can be represented by the spectacle frame diagram. The condition of the patient can be shown simply by the corresponding black areas.It must be emphasized that this spectacle frame diagram is not a new one but is only a modification of the Tessier classification as a supplement to a certain extent. In our experience, this simple symbolic diagram is able to describe rare craniofacial clefts in detail and is better than the other classifications for communication and for the medical record. It may be helpful for clinical physicians in the diagnosis and treatment of craniofacial clefts. Xiao-Jun Tang, M.D. Lai Gui, M.D. Zhi-Yong Zhang, M.D. Lin Yin, M.D. Department of Maxillofacial Surgery, Plastic Surgery Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, People's Republic of China Philippe Pellerin, M.D. Service de Chirurgie Plastique et Reconstructrice, Centre des Brûlés Hôpital Roger Salengro, Lille, France DISCLOSURE The authors have no financial interest to declare in relation to the content of this article. No external funds were received. PATIENT CONSENT Parents or guardians provided written consent for use of the patient's image.
For characteristics that power supplys in coal mine underground has multi input voltage grades and are susceptible to disturbed when big equipments are starting or stopping,the paper put forward a design scheme of adaptive wide-voltage power supply with explosion-proof and intrinsic safety.The power supply uses intelligent phase shift voltage regulating technology and wide-voltage switching power supply technology,and adopts single-chip microcomputer to realize automatic identification of high and low voltage section,automatic switch,intelligent phase shift voltage regulating of 85-825 V wide input voltage,and uses PWM to convert fluctuant voltage to a stable DC voltage.The experiment results show that the scheme solves problems of multi voltage grades and wide-voltage fluctuation of mine-used power supply.
This article makes a cognitive semantic analysis on the catchwords such as Shanzhai from the view of cognitive linguistics.The author finds that metaphorical and metonymic thinking plays an important role in the production of the new meaning of a word.It also is the main cognitive mechanism to create catchwords.
As a concise representation of stack filters, multistage weighted-order statistic (MWOS) filters are introduced, which correspond to multistage threshold logic gates or multilayer perceptrons in the binary domain. Two adaptive algorithms are derived for finding optimal MWOS filters under the mean absolute error criterion and the mean square error criterion, respectively. Experimental results from image enhancement are provided to compare the performance of adaptive MWOS filters and adaptive stack filters.< >
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)