Search

Fundus images have been widely used in the diagnosis of retinopathy and cardiovascular diseases. However, because of the movement of patients' eyes and limitation of medical equipments, the quality of fundus images may be low sometimes. In this paper, we propose vessel enhancement method for a low-contrast and blurred image based on multi-scale morphological top-hat transformation, and the combination of Gabor and matched filter. The underlying rationale of this proposed method is to make use different kinds of information to improve blood vessels on retinal fundus images with poor quality. Experiments show that vessels enhanced by our proposed method are much clearer than the ones using original multi-scale morphological top-hat transformation, Gabor filter or matched filter. The results confirm that the quality of vessel enhancement can be improved by combining these methods.

The limited resources, being located in the unattended environment, and the dynamic change of topology, these bring about big challenges for the communication security of wireless sensor networks. The security protocol framework-SPINS adopts multiple-key protocol, which can achieve the confidentiality, authentication, integrity and freshness during the data communication process, and have a relatively low communication cost. However after the sensor nodes being spread and deployed, if the shared master key between node and base station was divulged, the entire network security will be affected. This paper introduces the Schnorr identity authentication to improve SPINS, and give a security protocols for wireless sensor networks based on identity authentication. The analysis shows that the improved protocol can effectively prevent the security problem caused by divulging the shared master key. Meanwhile it is beneficial to find the adversary nodes in the network, and to guarantee the effective communication between nodes in the network.

Depth estimation from a sequence of images is a challenging problem in computer vision research. One of the well-known solutions is the depth from focus. However, the drawbacks of this method are the tradeoff between spatial resolution and robustness, and failure in textureless regions. In this paper, a novel approach of depth from focus with multiple images is proposed to improve the two shortcomings. By employing the mean shift segmentation before the step of building Markov random field, the result of segmentation serves as adaptive window for DFF. The edges of the recovered depth map are guaranteed to align with the edges of the original image. After the initial estimation of depth, the hierarchical Markov random field is generated to expand the area to extract depth information according to the structure of the scene. In this way, the experiments show that depth can extract from the textureless regions to some extent.

In order to improve the quality of PV grid-connected current, an exact transient analytic model was established based on time-sequence for full bridge inverter. A predictive control method MAC and an improved MAC method PIMAC based on this model were proposed in this paper. In these two methods, the frequency of switch was considered, so some problems had been resolved compared to other traditional methods. The simulation results confirm the correction and superiority of the control strategies proposed.

Depth estimation from a single image is a challenging problem in computer vision research. By analyzing the defocus cues produced by the depth of field of lens, the information of depth can be determined. We employ reverse heat equation, which is simple and effective, for this analysis. Because the depth map is required to be smooth in many applications, a mean shift segmentation and graph cut based method is proposed to infer the depth map of the scene. The confidence of depth estimation is incorporated into the energy function of graph cut to preserve details of the depth map. Experimental results show that the proposed method can produce a good depth map even from a single image.

The three dimensional Reynolds-averaged Navier-Stokes equations and the Spalart-Allmaras turbulent model are adopted to simulate numerically the flow field of the three dimensional flow-path of a ram-rotor with different inlet relative Mach numbers (Ma 0 = 2.1∼2.5) and two kinds of throat length-height ratio. It has been found that the flow fields are different with the changing of the throat length-height ratio. When the throat length-height ratio is 1, with the increasing of the inlet relative Mach number, the separation zone moves from near the top wall to the bottom wall; and it is contrary when the length-height ratio is 2. With Ma 0 increases, the incident angle and the reflection angle of shock wave decrease. The shock loss, the interaction of the shock wave and boundary layer, and the boundary layer separation are the main factors of the flow loss. The averaged flow angle at the exit with the throat length-height ratio 2 is larger than that with the throat length-height ratio 1. The Mach number, the total pressure and the pressure ratio at the exit increase and the adiabatic efficiency decreases with the increasing of Ma 0 . Under the same Ma 0 , the ram-rotor with the throat length-height ratio 2 has higher total pressure, the pressure ratio and the adiabatic efficiency.

A numerical simulation has been carried out to investigate the influences of pressure-side winglet on controlling tip clearance flow in an axial compressor cascade. Emphasis is put on the analysis of effectiveness of pressure-side winglet when the approaching flow is at different incidences (−5°, 0°, +3°). The simulation results show that with the increase of incidence, the region under the effect of pressure difference extends towards the blade leading edge, and the position of leakage vortex generation moves progressively upstream; Moreover, with pressure-side winglet, at all these incidences, the blade loading near the tip are increased, thus the strength of tip leakage flow is intensified, and the aerodynamic performance of the cascade is deteriorated.

Femtocell networks have great potential for mobile applications. However, interference due to the co-existence of macrocells and femtocells is a serious problem. In addition, dense femtocells introduce severe inter-system interference. In this paper, a graph theory based dynamic sub-band allocation technique is presented to avoid downlink interference. We model the cells and their mutual interference as graph elements, nodes and weighted edges, respectively. To maintain a tolerable interference level, the total bandwidth is divided into a number of sub-bands, and these are assigned to the femtocells using a graph coloring algorithm. The division is optimized to minimize the bandwidth used to meet user traffic requirements, and minimize the femto-to-macro interference. In addition, sub-bands are assigned to the femtocells to avoid inter-femto interference. An iterative spectrum management algorithm is also introduced.

RFID has been widely adopted in access control as an identity identification technology. This system can be combined with the face recognition technique to avoid the RFID is used by unauthorized people. However, this approach also suffers a drawback that someone may try to deceive the security system by presenting a photo of the real card owner. In this paper, we propose a method ensuring that such kind of spoof can be rejected. After a frontal face has been detected, the facial object will be tracked by optical flow algorithm until a profile is detected. Experimental results show that the proposed mechanism can improve the validity of the access control system effectively.

Driver's distraction in driving is one of the major causes of the traffic accidents. The abnormal behavior of the driver's head movement and the facial expressions were studied in detail in order to get the characteristics of the inattention status. With real-time monitoring on the driver's attention characteristics: the position and movement status information of eyes and mouth, the detection mechanisms is established to detect the scattered mental of drivers state and estimate the driver’s distracting degree. Based on the detection results of eyes and mouth region, BP neural network is used to evaluate the various model of the driver's inattention. The adoption of the D-S evidence theory is effective for the decision-level fusion of the multi-information of the driver's distraction status. The experimental results demonstrate that the reliability and accuracy of the scattered mental of drivers state detection is highly improved by using the BP neural network and D-S rule multi-information fusion.

Radio frequency identification (RFID) technology has been widely adopted in access control system. However, the people holding the RFID card passing through the access control may not be the authorized one. Therefore, an access control system combining RFID technology and face recognition based on neural network is presented in this work. The system recognizes the face of the person holding the RFID card and denies access if they do not match. We adopt a Radial Basis Function Neural Network (RBFNN) to learn the face of authorized card holders and save the parameters of RBFNN only. This could reduce storage when the number of card holders getting large. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) features are extracted to reduce the dimensions of face image data. The Localized Generalization Error Model (L-GEM) is adopted to train a RBFNN for better generalization capability. The face recognition system is first evaluated by benchmarking ORL face image database. The whole access control system is then tested in a real environment. Experimental results show that the proposed method has a good performance and could improve the security of RFID access control.

This paper mainly illustrates that electricity purchasers face the decision of electricity purchase and the issues of risk managements in the four trading markets under the framework of the electricity markets. The restrictions and non-restriction purchase/sale of two purchasing electricity models are set up by means of Variance measuring risk under the framework of the electricity market. Meanwhile, in the paper, it also proposes several feasible algorithms to minimize risks for the electricity purchaser by guaranteeing their return.

RFID identification has been widely adopted in access control. This kind of card or tag based approaches has a major drawback that anyone could get access with the card. In this work, we propose a neural network based face recognition system as the second access control to make sure the person granted access matches the ID on the RFID card. In this preliminary work, the face of accessing person is detected in video stream and we extract the Scale Invariant Feature Transform (SIFT) features from a face image. To enhance the generalization capability of the face recognition, we introduced the Localized Generalization Error Model (L-GEM) to train the Radial Basis Function Neural Network (RBFNN) for face recognition. Experimental results show that the proposed method could identify person that matches the RFID access card or not in a high probability.