共查询到20条相似文献，搜索用时 296 毫秒
1.
D.J.J. Farnell F.N. Hatfield M. Reakes D. Parry 《Journal of The Franklin Institute》2008,345(7):748-765
We employed multiscale line operators (MSLO) in order to segment blood vessels in digital fundus images. Separately, a median filter technique was used in order to provide results that were compared to those of the MSLO. The green channel of the colour image was used, and both sets of results were further enhanced by subsequently employing a simple “randomly seeded” region-growing algorithm. We applied this approach to two sets of retinal images, namely, the ARIA (www.eyecharity.com/aria_online/) and STARE (www.ces.clemson.edu/∼ahoover/stare/) retinal image archives. The ARIA dataset contained colour fundus images from healthy subjects, diabetic subjects, and age-related macular degeneration (AMD) subjects. Similarly, the STARE dataset contained images from both “normal” (i.e., healthy) and “abnormal” (i.e., diseased) eyes. Manual segmentations of the blood-vessel structure for all images in the ARIA and STARE datasets were obtained by a retinal image interpretation expert. These images were then taken to be our gold standards. Receiver-operator characteristic (ROC) curves were determined and the areas under the ROC curve (AZ) were obtained. A large increase in efficiency for our MSLO algorithm was observed for the entire datasets (ARIA AZ=0.899; STARE AZ=0.953) compared to basic thresholding alone (ARIA AZ=0.608; STARE AZ=0.753). Interestingly, the simple median filter algorithm followed by region growing also performed well (ARIA AZ=0.888; STARE AZ=0.947). Our results compared favourably to those results of previous segmentation procedures for the STARE dataset. As expected, the best results were found for the healthy control group for ARIA and for the normal subjects for STARE. 相似文献
2.
常用的基于均方根误差（RMSE）图像保真度准则不能准确地放映一些灰度图像主要敏感细节。本文提出了利用灰度直方图的相似度作为评价重建图像质量的准则。利用JPEG方法对图像进行压缩，并采用直方图相交匹配函数求得图像灰度级的匹配程度。实验结果表明，直方图相交匹配函数是一种有效的图像压缩评测准则。 相似文献
3.
《Information processing & management》2005,41(2):177-194
In this paper, we propose a re-ranking algorithm using post-retrieval clustering for content-based image retrieval (CBIR). In conventional CBIR systems, it is often observed that images visually dissimilar to a query image are ranked high in retrieval results. To remedy this problem, we utilize the similarity relationship of the retrieved results via post-retrieval clustering. In the first step of our method, images are retrieved using visual features such as color histogram. Next, the retrieved images are analyzed using hierarchical agglomerative clustering methods (HACM) and the rank of the results is adjusted according to the distance of a cluster from a query. In addition, we analyze the effects of clustering methods, query-cluster similarity functions, and weighting factors in the proposed method. We conducted a number of experiments using several clustering methods and cluster parameters. Experimental results show that the proposed method achieves an improvement of retrieval effectiveness of over 10% on average in the average normalized modified retrieval rank (ANMRR) measure. 相似文献
4.
5.
6.
This paper investigates the problem of finite-time outer-synchronization for discrete-time complex networks with Markov jump topology in the presence of communication delays and possible information losses and its application to image encryption. A hybrid control, which is subject to both stochastic jumps and deterministic switches, is proposed to realize finite-time and stochastic outer-synchronization for the concerned networks. By utilizing a stochastic Lyapunov functional combined with the average dwell-time method, sufficient conditions are found such that the synchronization error dynamical system is stochastically stable in finite-time. Two numerical examples are presented to illustrate the effectiveness of the proposed method. Finally, the complex network consists of four coupled Lorenz systems are utilized to generate chaotic sequences and a new chaotic image cryptosystem is constructed to transmit encrypted images based on the synchronized drive-response complex networks. Experiments are conducted by using numerical simulation, and the security is analyzed in terms of key space, key sensitivity, histogram distributions, correlation coefficients, information entropy and differential attack measures. The experimental results show that the proposed chaotic image cryptosystem has the advantages of high security against some classical attacks. 相似文献
7.
提出了一种基于角点特征Harris和对比度调制的图像拼接算法,以提高室外复杂场景的图像拼接质量。利用Harris算法提取基准图像（带匹配图像）和后续图像的特征点。确定特征的位置、尺度与方向,利用最近临法完成两幅特征点的匹配,确定重合区域,利用基于对比度调制方法完成对图像的拼接。实验结果表明,该方法对亮度差异较大的图像拼接具有良好的效果,适于室外复杂环境的图像拼接。 相似文献
8.
利用双树复小波变换并结合人眼视网膜的颜色特性,提出一种基于融合的彩色图像水印方案。利用复小波变换的平移不变性和多方向性来增强水印受攻击时的鲁棒性。通过试验调整水印能量在蓝、绿、红3种颜色信道里的比例来提高水印的不可见性。结果表明该水印方案在压缩、增加噪声、中值和平均滤波攻击下具有较高的鲁棒性。 相似文献
9.
针对传统图像预处理中图像信息损失的问题,提出基于小波变换的图像去噪和增强的算法。实验证明基于小波变换的图像预处理方法能在去噪和增强的同时,保留了图像在时间和空间域的信息,为视频录播后续的目标检测与跟踪提供了高质量图像,提高了录播系统的跟踪准确性。 相似文献
10.
11.
直方图均衡处理是一种重要的图像增强方法。本文在介绍直方图均衡处理方法原理的基础上分析了直方图均衡处理方法的优缺点。 相似文献
12.
描述了一种基于GDI＋的医学图像分析系统的设计原理,实现了眼底图像的缩放、移动、分析、保存与图像增强。系统采用双缓冲技术解决绘图过程中屏幕的闪烁问题,基于颜色矩阵以及GDI＋与GDI混合编程的方法,完成了二维医学图像的处理与分析。最后针对医疗诊断报告单的要求,完成了基于word的文档自动生成与保存。测试表明,该系统运行稳定,效果良好。 相似文献
13.
基于城市热岛效应的城市降温通道规划研究——以广州市为例 总被引：2，自引：1，他引：1
城市热岛效应是城市化形成的特殊城市气候特征之一,热岛效应对城市规划布局、经济发展及人群健康等许多方面的影响日益突出.本文应用Landsat-5 TM图像的TM6波段(空间分辨率为120m),利用单窗算法反演了行星亮度温度,结合GIS和CAD技术分析了广州市的“热岛效应”空间格局和特征,规划了城市降温通道.得出以下结论:①广州市城市热岛特征显著、空间分异明显.在中心城区内分布有大面积的热岛,中心片区城中村热岛效应强烈,城市绿地和水面“冷源”效应明显;②规划了广州市市区范围内的降温通道,形成了以珠江沿线为主轴、点线面相结合的网格状降温通道格局;③充分利用丰富的绿地、水域以及降温通道的作用降低热岛强度. 相似文献
14.
Unwanted sedimentation and attachment of a number of cells onto the bottom channel often occur on relatively large-scale inlets of conventional microfluidic channels as a result of gravity and fluid shear. Phenomena such as sedimentation have become recognized problems that can be overcome by performing microfluidic experiments properly, such as by calculating a meaningful output efficiency with respect to real input. Here, we present a dual-inlet design method for reducing cell loss at the inlet of channels by adding a new “ upstream inlet ” to a single main inlet design. The simple addition of an upstream inlet can create a vertically layered sheath flow prior to the main inlet for cell loading. The bottom layer flow plays a critical role in preventing the cells from attaching to the bottom of the channel entrance, resulting in a low possibility of cell sedimentation at the main channel entrance. To provide proof-of-concept validation, we applied our design to a microfabricated flow cytometer system (μFCS) and compared the cell counting efficiency of the proposed μFCS with that of the previous single-inlet μFCS and conventional FCS. We used human white blood cells and fluorescent microspheres to quantitatively evaluate the rate of cell sedimentation in the main inlet and to measure fluorescence sensitivity at the detection zone of the flow cytometer microchip. Generating a sheath flow as the bottom layer was meaningfully used to reduce the depth of field as well as the relative deviation of targets in the z-direction (compared to the x-y flow plane), leading to an increased counting sensitivity of fluorescent detection signals. Counting results using fluorescent microspheres showed both a 40% reduction in the rate of sedimentation and a 2-fold higher sensitivity in comparison with the single-inlet μFCS. The results of CD4+ T-cell counting also showed that the proposed design results in a 25% decrease in the rate of cell sedimentation and a 28% increase in sensitivity when compared to the single-inlet μFCS. This method is simple and easy to use in design, yet requires no additional time or cost in fabrication. Furthermore, we expect that this approach could potentially be helpful for calculating exact cell loading and counting efficiency for a small input number of cells, such as primary cells and rare cells, in microfluidic channel applications. 相似文献
15.
提出一种对基于扩频信息隐藏图像进行隐写分析的方法.应用马尔科夫链模型,根据图像的相邻像素点之间的相关性,结合阈值判别方法和改进的模式识别方法,判断一幅图像中是否存在隐写信息.在Corel图像库上的实验表明,本方法降低了虚警率,且正检率的性能优于已有方法. 相似文献
16.
Emad S. Hassan 《Journal of The Franklin Institute》2019,356(3):1640-1657
The multi-taper spectrum (MTS) estimator enjoys a relatively low computational complexity and high estimation accuracy making it an attractive method for spectrum sensing in cognitive radio (CR) networks. However, it is difficult to guarantee both detection and false alarm probabilities when its design is based on fixed threshold, especially when the noise power fluctuates due to channel conditions. In this paper, a new adaptive threshold method to guarantee both detection and false alarm probabilities for MTS based spectrum sensing is proposed. By means of estimating noise power and signal power, the decision of adaptive threshold is able to adapt the noise fluctuation and achieve efficient trade-off between detection and false alarm probabilities. A closed form expression for the adaptive threshold is derived for both additive white Gaussian noise (AWGN) channel and multipath fading channel. Several metrics are employed to compare the performance of the proposed adaptive threshold method with that of the fixed threshold methods such as: error decision probability, detection probability, false alarm probability and throughput. The obtained results show that the proposed method achieves better spectrum efficiency and high throughput in comparison with the conventional fixed and adaptive threshold methods presented in the literature. 相似文献
17.
一种基于活动围道的纹理图像分割方法 总被引：1，自引：0，他引：1
本文将Gabor滤波器和各向异性扩散方程相结合，提出了一种基于活动围道的无监督纹理图像分割算法。采用基于总变分流的扩散函数，各向异性扩散方程可以有效地在保留纹理图像大尺度边界信息的同时对图像纹理区域进行平滑，获得比原始图像更易分割的简化图像。但是平滑过程中纹理信息的丧失，限制了该方法的通用性和有效性。为了在利用各向异性扩散方法的同时有效地提取和利用纹理信息，我们利用Gabor滤波器提取一组表征纹理方向性和尺度性的特征图像，同时将原始图像作为表征纹理灰度信息的一个特征通道考虑。再利用矢量形式的各向异性扩散方程对特征图像进行边界保持的各向异性平滑。我们将基于区域灰度统计参数估计的活动围道分割方法扩展到矢量空间，来对平滑后的纹理特征量进行分割。实验证明利用该纹理分割算法可以获得较好的效果。 相似文献
18.
绿色税收视角下产业结构变迁对中国碳排放的影响 总被引：1，自引：0，他引：1
从绿色税收视角探讨产业结构与碳排放的关系,有利于制定控制碳排放的财税政策,助力绿色发展转型。本文首先测算出2003—2016年中国30个省（市、区）的CO2排放量,在扩展STRIPAT模型基础上,运用静态面板模型和面板门槛模型,对绿色税收下产业结构变迁的碳排放效应进行实证研究,并从产业结构合理化和产业结构高级化两个维度进行分析。研究发现：①产业结构变迁会显著影响中国CO2排放总量,绿色税收对其影响具有门槛效应;②在达到门槛值之前,绿色税收有效地促进了产业结构合理化和产业结构高级化对碳排放的影响。跨越门槛值以后,绿色税收对产业结构变迁的作用出现差异。一方面,绿色税收对产业结构高级化的碳减排机制仍具有促进效应,但相比达到门槛值之前,作用有所降低;另一方面,绿色税收表现出对产业结构合理化的碳排放效应具有抑制作用;③部分省份的绿色税收强度在2009年后跨越了门槛值,消费税改革可能是这种变化出现的主要原因。基于实证结论,本文提出了相应的政策建议。 相似文献
19.
Internet of things (IoT) coupled with mobile cloud computing has made a paradigm shift in the service sector. IoT-assisted mobile cloud based e-healthcare services are making giant strides and are likely to change the conventional ways of healthcare service delivery. Though numerous approaches for preventing unauthorized access to information exchanged between a mobile phone and cloud platform do exist, but there is no security mechanism to prevent unauthorized access by the cloud administrators. With an aim to ensure security of client data such as Electronic Patient Records (EPR), we propose a novel high-capacity and reversible data hiding approach for securely embedding EPR within the medical images using Optimal Pixel Repetition (OPR). OPR converts every pixel of the input image to a 2 × 2 block to facilitate reversibility by ensuring all the pixels in a 2 × 2 block to have different values. Since a 2 × 2 block is comprised of 4-pixel elements, which could be arranged in sixteen possible ways; we generate a lookup table corresponding to sixteen possible positions of pixels. EPR hiding in each block is achieved by permuting the pixels of a block according to the four-bit word of secret data, resulting in a histogram invariant stego image. The histogram invariance improves the robustness of the proposed scheme to statistical attacks. A stego image is said to hide embedded data securely, when it provides better imperceptivity for an appreciably high payload. Thus, while using information embedding approach for securing client data on a mobile-cloud platform, high imperceptivity is a desirable feature. Experimental results show that average PSNR obtained is 42 dB for payload 1.25 bpp by our scheme, showing its effectiveness for preventing unauthorized access to client’s sensitive data. 相似文献
20.
To retrieve the information from the serious distorted received signal is the key challenge of communication signal processing. The chaotic baseband communication promises theoretically to eliminate the inter-symbol interference (ISI), however, it needs complicated calculation, if it is not impossible. In this paper, a genetic algorithm support vector machine (GA-SVM) based symbol detection method is proposed for chaotic baseband wireless communication system (CBWCS), by this way, treating the problem from a different viewpoint, the symbol decoding process is converted to be a binary classification through GA-SVM model. A trained GA-SVM model is used to decode the symbols directly at the receiver, so as to improve the bit error rate (BER) performance of the CBWCS and simplify the symbol detection process by removing the channel identification and the threshold calculation process as compared to that using the calculated threshold to decode symbol in the traditional methods. The simulation results show that the proposed method has better BER performance in both the static and time-varying wireless channels. The experimental results, based on the wireless open-access research platform, indicate that the BER of the proposed GA-SVM based symbol detection approach is superior to the other counterparts under a practical wireless multipath channel. 相似文献