This paper presents an image segmentation method that outlines fractured bones in an X-ray image of a patient's arm within cast materials, and displays the alignment between the fractured bones. The cast material ...
详细信息
This paper presents an image segmentation method that outlines fractured bones in an X-ray image of a patient's arm within cast materials, and displays the alignment between the fractured bones. The cast material overlaying on the fractured bones creates extra noises to the X-ray image and provides challenges to the segmentation method. Our segmentation method aims on outlining the objects from a low contrast and high noise ratio of the X-ray images. A geodesic active contour model with global constraints is applied to this segmentation task. A prior shape is collected and embedded into the active contour model as a global constraint. A maximum-likelihood function is derived and used as a feedback system for each evolving process to a decision making procedure. Mutual Information is employed to measure the difference or the likelihood between the prior shape and the evolving curve. Experimental results show that the method produces the outlines of the fractured bones on the low contrast X-ray images robustly and accurately. The computation of our segmentation method is fast and efficient
Motion estimation plays an important role for the coding performance achieved in current video coding schemes. However, the computational burden of motion estimation algorithms is often high, especially if the tempora...
详细信息
In this letter, an efficient recursive least squares (RLS) algorithm using infinite impulse response (IIR) filter for acoustic echo cancellation (AEC) is proposed. The RLS adaptive filter is naturally extended from th...
详细信息
In this letter, an efficient recursive least squares (RLS) algorithm using infinite impulse response (IIR) filter for acoustic echo cancellation (AEC) is proposed. The RLS adaptive filter is naturally extended from the finite impulse response (FIR) structure to the IIR structure. One of the main advantages of an IIR RLS filter is that a long-delay echo can be synthesized by a relatively small number of filter coefficients leading to lesser computational complexity. In addition it is more suitable for modeling physical systems, due to its pole-zero structure, over their FIR counterparts. To investigate the tracking performance and the stability of the proposed IIR RLS filter in a practical implementation, real data for far end speech signal and its echo were used in car environment. The proposed algorithm is shown to have global convergence. To demonstrate the effectiveness of the proposed IIR RLS filter, it is compared to the usual FIR RLS filter. The good performance of the proposed IIR RLS algorithm for AEC have been verified via computer simulations
This paper presents an integrated neuro-fuzzy (NF) scheme and a rule-based-fuzzy (RBF) scheme applications to Moving Picture Expert Group (MPEG) video transmission in Bluetooth. In a Bluetooth network, transmission ra...
详细信息
This paper presents an integrated neuro-fuzzy (NF) scheme and a rule-based-fuzzy (RBF) scheme applications to Moving Picture Expert Group (MPEG) video transmission in Bluetooth. In a Bluetooth network, transmission rate is unpredictable due to interferences by other wireless devices or general Bluetooth channel noises. MPEG variable bit rate (VBR) video transmission is also unreliable and presents long delay and excessive data loss, due to variations in bit rate. It is therefore almost impossible to transmit MPEG VBR video over a Bluetooth channel, without data loss, excessive time delay or image quality degradation. In this work, a traffic-shaping buffer is introduced before the host controller interface (HCI) of the Bluetooth protocol stack. An integrated NF scheme reduces the burstiness of the traffic-shaper output rate to enable the MPEG VBR video to comply with the generic cell rate algorithm contract before entering the Bluetooth channel. The computer simulation results show that the application of the proposed scheme reduces excessive time delay and data loss at the HCI, as compared with a conventional video transmission in Bluetooth
In this paper, a new image denoising method based on wavelet analysis and support vector machine regression (SVR) is presented. The feasibility of image denoising via support vector regression is discussed and is demo...
详细信息
ISBN:
(纸本)9783540743767
In this paper, a new image denoising method based on wavelet analysis and support vector machine regression (SVR) is presented. The feasibility of image denoising via support vector regression is discussed and is demonstrated by an illustrative example which denoise a, 1-dimension signal with Gauss KBF SVM. The wavelet theory is discussed and applied to construct the wavelet kernel, then the wavelet support vector machine (WSVM) is proposed. The result of experiment shows that the denoising method based on WSVM can reduce noise well, the comparison between the method proposed in this paper and other ones is also given which proves this method is better than Gaussian KBF SVM and other traditional methods.
The current work address two types of Tikhonov Regularization to extracta template evoked potential (EP) signal from a small number of noisy records. Under the same goal, the Subspace Regularization Technique (SRT) wa...
详细信息
ISBN:
(纸本)9789531841160
The current work address two types of Tikhonov Regularization to extracta template evoked potential (EP) signal from a small number of noisy records. Under the same goal, the Subspace Regularization Technique (SRT) was experienced in literature without comparison regarding as the standard form Tikhonov Regularization technique (STRT). Both methods are tested in experimental studies and simulations. The signal-to-Noise Ratio (SNR) improvement is used as error criteria. The superiority of SRT have not been observed in results. In addition, the STRT is found to be less computational complex. The STRT method is optimum for smooth solutions whereas the SRT allows sharp variations in the solutions. Thus, we propose the use of the STRT instead of the SRM for template auditory EP estimation.
The objective of this paper is to present a detailed description of using DSP board and imageprocessing techniques to construct an automated vehicle counting system. Such a system has many potential applications, suc...
详细信息
ISBN:
(纸本)9781424412655
The objective of this paper is to present a detailed description of using DSP board and imageprocessing techniques to construct an automated vehicle counting system. Such a system has many potential applications, such as traffic signal control and district traffic abduction. We use TI TMS320DM642 DSP as the computational unit to avoid heavy investment in industrial control computer while obtaining improved computational power and optimized system structure. The overall software is comprised of two parts: embedded DSP software and host PC software. The embedded DSP software acquires the video image from stationary cameras, detects and counts moving vehicles, and transmits the processing results and real-time images after compression to PC software through network. The host PC software works as a graphic user interface through which the end user can configure the DSP board parameters and access the video processing results. The vehicle detection and counting algorithm is carefully devised to keep robust and efficient in traffic scenes for longtime span and with changeful illumination. Experimental results show that the proposed system performs well in actual traffic scenes, and the processing speed and accuracy of the system can meet the requirement of practical applications.
Semantic video adaptation takes into account the relevance of the different fragments of the video content in order to create a tailored video stream based on the user's preferences. As a shot can be considered as...
详细信息
Semantic video adaptation takes into account the relevance of the different fragments of the video content in order to create a tailored video stream based on the user's preferences. As a shot can be considered as the smallest semantic unit in a video sequence, metadata can be added to each shot using MPEG-7 descriptions. Based on these metadata and the user's preferences, the original bitstream can be adapted in order to obtain the desired fragments. MPEG-21 DIA offers a tool, gBS schema, for exposing the high-level structure of a binary resource as an XML description. In this paper, shot information is inserted in these descriptions to create a link between metadata and semantic video adaptation. Furthermore, this paper proposes to keep the structure of these descriptions format-agnostic. As a result, only one generic transformation style sheet has to be implemented to support shot-based video adaptation of sequences compliant with different video specifications. Special attention is paid to sequences coded with the H.264/AVC standard as this specification contains several interesting features important for shot-based video adaptation
A novel approach to on-line classification based on fuzzy rules with an open/evolving structure is introduced in this paper. This classifier can start `from scratch', learning and adapting to the new data samples ...
详细信息
A novel approach to on-line classification based on fuzzy rules with an open/evolving structure is introduced in this paper. This classifier can start `from scratch', learning and adapting to the new data samples or from an initial rule-based classifier that can be updated based on the new information contained in the new samples. It is suitable for real-time applications such as classification streaming data, robotic applications, e.g., target and landmark recognition, real-time machine health monitoring and prognostics, fault detection and diagnostics, etc. Each prototype is a data sample that represents the focal point of a fuzzy rule per class and is selected based on the data density by an incremental and evolving procedure. This approach is transparent, linguistically interpretable, and applicable to both fully unsupervised and partially supervised learning. It has been validated by two well known benchmark problems and by real-life data in a parallel paper. The contributions of this paper are: i) introduction of the concept of evolving (open structure) classification (eClass) of streaming data; ii) experiments with well known benchmark classification problems (Iris and wine reproduction data sets)
This paper proposes a new approach for the design of hardware architecture for the computation of 2D-DWT for an 8 x 8 image. The key feature of this design is to directly apply 2D-DWT on alternate pixels of an image, ...
详细信息
ISBN:
(纸本)9780769530727
This paper proposes a new approach for the design of hardware architecture for the computation of 2D-DWT for an 8 x 8 image. The key feature of this design is to directly apply 2D-DWT on alternate pixels of an image, called as the Non-Separable method, and implement it on an FPGA. The resulting design was implemented using only 6 adders and 10 multipliers, thus optimizing the number of multipliers and adders required for the computation of 2D-DWT. Thus our approach provides a cost effective solution as compared to the conventional 2D non-separable methods without compromising on speed performance. The design is implemented on Xilinx Virtex II Pro FPGA development kit and synthesized using Xilinx XST (VHDL/Verilog) synthesis tool.
暂无评论