Evaluation of shape classification techniques based on the signature of the blob

In this paper, we report a study of different preprocessing and classification techniques that can be applied to shape classification using the signature of the blob, or its FFT, as the main feature. Eight well-known classification methods were tested and compared.The results obtained show that, for shapes with a small to medium amount of distortion, all the methods obtained an almost 100% success probability. However, as distortion increased, those not based on the FFT performed better than the other algorithms, at the expense of a small increase in computational time.The samples employed for training and testing purposes were not hand-selected, but were generated by an application developed as part of this study. This application simulates the main distortions that can be produced by a real camera, including shifts, scalings, rotations, affine transformations and noise. We demonstrate that the use of these synthetic images for the training process, instead of manually selected ones, had proven to perform well with real images.A study of the false positive problem is also included, showing that, with the use of SVMs and careful selection of the training set, a large number of false positives can be discarded in the detection step.     

Performance Measures for Neyman–Pearson Classification

In the Neyman-Pearson (NP) classification paradigm, the goal is to learn a classifier from labeled training data such that the probability of a false negative is minimized while the probability of a false positive is below a user-specified level alpha isin (0,1). This work addresses the question of how to evaluate and compare classifiers in the NP setting. Simply reporting false positives and false negatives leaves some ambiguity about which classifier is best. Unlike conventional classification, however, there is no natural performance measure for NP classification. We cannot reject classifiers whose false positive rate exceeds a since, among other reasons, the false positive rate must be estimated from data and hence is not known with certainty. We propose two families of performance measures for evaluating and comparing classifiers and suggest one criterion in particular for practical use. We then present general learning rules that satisfy performance guarantees with respect to these criteria. As in conventional classification, the notion of uniform convergence plays a central role, and leads to finite sample bounds, oracle inequalities, consistency, and rates of convergence. The proposed performance measures are also applicable to the problem of anomaly prediction.     

Discriminant Analysis Based Prognostics of Avionic Systems

In this paper, a novel discriminant analysis based predictive model for preventing false alarms leading to unnecessary replacement of an avionic system component is presented. The model is validated by prediction of false alarms (also known as false positives, type I, or alpha errors) in the left generator shaft of a Sikorsky helicopter UH-60, using the Goodrich health and usage management system (HUMS). The paper presents one of the first approaches based on applying discriminant analysis for prognostics of avionic systems, specifically in the context of identifying false positives within the next 1 or 2 h. In practice, predictions for the next 2 h are sufficient as typical helicopter flight schedules and durations are such that up to 2 h advance notice is most useful. This is an important contribution because drive train components of helicopters are normally very robust with very rare failures; therefore, the cost of unnecessary preventive maintenance based on false alarms is very high.     

Detection of Breast Masses in Mammogram Images Using Growing Neural Gas Algorithm and Ripley’s K Function

Breast cancer is a serious public health problem in several countries. Computer-aided detection/diagnosis systems (CAD/CADx) have been used with relative success in aid of health care professionals. The goal of such systems is not to replace the professionals, but to join forces in order to detect the different types of cancer at an early stage. The main contribution of this work is the presentation of a methodology for detecting masses in digitized mammograms using the growing neural gas algorithm for image segmentation and Ripley’s K function to describe the texture of segmented structures. The classification of these structures is accomplished through support vector machines which separate them in two groups, using shape and texture measures: masses and non-masses. The methodology obtained 89.30% of accuracy and a rate of 0.93 false positives per image.     

基于粗糙集-支持向量机理论的过滤误报警方法

为过滤入侵检测系统报警数据中的误报警,根据报警的根源性和时间性总结出了区分真报警和误报警的19个相关属性,并提出了一种基于粗糙集-支持向量机理论的过滤误报警的方法。该方法首先采用粗糙集理论去除相关属性中的冗余属性,然后将具有约简后的10个属性的报警数据集上的误报警过滤问题转化为分类问题,采用支持向量机理论构造分类器以过滤误报警。实验采用由网络入侵检测器Snort监控美国国防部高级研究计划局1999年入侵评测数据(DARPA99)产生的报警数据,结果表明提出的方法在漏报警约增加1.6%的代价下,可过滤掉约98%的误报警。该结果优于文献中使用相同数据、相同入侵检测系统的其它方法的结果。     

Opcode vector: An efficient scheme to detect soft errors in instructions

Bit flips on instructions may affect the execution of the processor depending on the Instruction Set Architecture (ISA) and the location of the flipped bits. Intrinsically, ISAs may detect bit upsets if the errors on the instructions produce exceptions that halt the execution. In this paper, we explore a dynamic checking of the instructions to detect errors before execution. The scheme is based on loading an approximate representation of the instructions based on a vector that identifies the opcodes used in the program in a special purpose register. During execution, instructions are first checked on the register and on a negative an error is detected as the instruction has an opcode that does not correspond to any of the ones used in the program. Since we use an approximate representation, a small number of false positives can occur for erroneous instructions which may still be detected if they lead to a system crash. The proposed opcode vector scheme is compared with the use of a Bloom filter (BF) that has been previously proposed to detect errors on instructions. In both cases, a check can produce false positives but not false negatives. The Bloom filter is built using all the bits in the instruction. On the other hand, the opcode vector uses only a few bits of the instruction. In both cases, the check is combined with a previous error propagation scheme. In the opcode case, this ensures that all errors corrupt the opcode bits while for the BF, the error propagation reduces the number of false positives. The proposed approach has two main benefits. The first one is an increase in the error detection rate as the set of valid instructions is restricted to those used in the program allowing the detection of invalid instructions even if they do not lead to a system crash. The second one is that errors are detected before the crash. This is done at the cost of adding a small register for the vector of opcodes and some control logic. This is significantly simpler than in the case of the BF that needs to compute several hash functions and access several bits on the register to perform the check. We evaluated this approach on binary files of the ARM Cortex M0 core. According to our findings, the proposed vector of opcodes is more effective to detect errors than the BF and its detection rate is less dependent on the program size. Based on those results, it seems that the proposed method can be an interesting option to detect errors in instructions for systems on which a small overhead can be introduced if it improves reliability.     

An Innovative Neural-Net Method to Detect Temporal Changes in High-Resolution Optical Satellite Imagery

The advent of new high spatial resolution optical satellite imagery has greatly increased our ability to monitor land cover changes from space. Satellite observations are carried out regularly and continuously, and provide a great deal of insight into the temporal changes of land cover use. High spatial resolution imagery better resolves the details of these changes and makes it possible to overcome the "mixed-pixel" problem that is inherent with more moderate resolution satellite sensors. At the same time, high-resolution imagery presents a new challenge over other satellite systems, in that a relatively large amount of data must be analyzed and corrected for registration and classification errors to identify the land cover changes. To obtain the accuracies that are required by many applications to large areas, very extensive manual work is commonly required to remove the classification errors that are introduced by most methods. To improve on this situation, we have developed a new method for land surface change detection that greatly reduces the human effort that is needed to remove the errors that occur with many classification methods that are applied to high-resolution imagery. This change detection algorithm is based on neural networks, and it is able to exploit in parallel both the multiband and the multitemporal data to discriminate between real changes and false alarms. In general, the classification errors are reduced by a factor of 2-3 using our new method over a simple postclassification comparison based on a neural-network classification of the same images.     

DNS‐Class: immediate classification of IP flows using DNS

Nowadays we see a tremendous growth of the Internet, especially in terms of the amont of data being transmitted and new network protocols being introduced. This poses a challenge for network administrators, who need adequate tools for network management. Recent findings show that DNS can contribute valuable information on IP flows and improve traffic visibility in a computer network. In this paper, we apply these findings on DNS to propose a novel traffic classification algorithm with interesting features. We experimentally show that the information carried in domain names and port numbers is sufficient for immediate classification of a highly significant portion of the traffic. We present DNS‐Class: an innovative, fast and reliable flow‐based traffic classification algorithm, which on average yields 99.8% of true positives and < 0.1% of false positives on real traffic traces. The algorithm can work as a major element of a modular system in a cascade architecture. Additionally, we provide an analysis on how various network protocols depend on DNS in terms of flows, packets and bytes. We release the complete source code implementing the presented system as open source. Copyright © 2014 John Wiley & Sons, Ltd.     

Using generalized additive models for construction of nonlinear classifiers in computer-aided diagnosis systems.

Several investigators have pointed out the possibility of using computer-aided diagnosis (CAD) schemes, as second readers, to help radiologists in the interpretation of images. One of the most important aspects to be considered when the diagnostic imaging systems are analyzed is the evaluation of their diagnostic performance. To perform this task, receiver operating characteristic curves are the method of choice. An important step in nearly all CAD systems is the reduction of false positives, as well as the classification of lesions, using different algorithms, such as neural networks or feature analysis, and several statistical methods. A statistical model more often employed is linear discriminant analysis (LDA). However, LDA implies several limitations in the type of variables that it can analyze. In this work, we have developed a novel approach, based on generalized additive models (GAMs), as an alternative to LDA, which can deal with a broad variety of variables, improving the results produced by using the LDA model. As an application, we have used GAM techniques for reducing the number of false detections in a computerized method to detect clustered microcalcifications, and we have compared this with the results obtained when LDA was applied. Employing LDA, the system achieved a sensitivity of 80.52% at a false-positive rate of 1.90 false detections per image. With the GAM, the sensitivity increased to 83.12% and 1.46 false positives per image.     

Vitronic分选设备在太阳能电池片分选中的应用

在太阳能电池片的生产过程中,需要人工按照外观标准要求对太阳能电池片进行检验分类,人员分选效率低且容易产生误判。为了提高分选效率和降低误判。通过采用Vitronic太阳能电池片外观分选设备,将此设备整合在产线设备中。使用该设备测试对太阳能电池片外观进行检测。以达到对太阳能电池片的颜色、几何尺寸、边缘、表面缺陷和印刷质量进行分类。     

防火墙策略建模与其全局冲突分析(英文)

The global view of firewall policy conflict is important for administrators to optimize the policy.It has been lack of appropriate firewall policy global conflict analysis,existing methods focus on local conflict detection.We research the global conflict detection algorithm in this paper.We presented a semantic model that captures more complete classifications of the policy using knowledge concept in rough set.Based on this model,we presented the global conflict formal model,and represent it with OBDD(Ordered Binary Decision Diagram).Then we developed GFPCDA(Global Firewall Policy Conflict Detection Algorithm) algorithm to detect global conflict.In experiment,we evaluated the usability of our semantic model by eliminating the false positives and false negatives caused by incomplete policy semantic model,of a classical algorithm.We compared this algorithm with GFPCDA algorithm.The results show that GFPCDA detects conflicts more precisely and independently,and has better performance.     

Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response

We describe an automated method to locate and outline blood vessels in images of the ocular fundus. Such a tool should prove useful to eye care specialists for purposes of patient screening, treatment evaluation, and clinical study. Our method differs from previously known methods in that it uses local and global vessel features cooperatively to segment the vessel network. We evaluate our method using hand-labeled ground truth segmentations of 20 images. A plot of the operating characteristic shows that our method reduces false positives by as much as 15 times over basic thresholding of a matched filter response (MFR), at up to a 75% true positive rate. For a baseline, we also compared the ground truth against a second hand-labeling, yielding a 90% true positive and a 4% false positive detection rate, on average. These numbers suggest there is still room for a 15% true positive rate improvement, with the same false positive rate, over our method. We are making all our images and hand labelings publicly available for interested researchers to use in evaluating related methods.     

Computerized detection of pulmonary embolism in spiral CT angiography based on volumetric image analysis

A fully automated method for computerized detection of pulmonary embolism in spiral computed tomography angiography was developed based on volumetric image analysis. The detection method is based on segmentation of pulmonary vessels to limit the search space, and analysis of several three-dimensional features inside segmented vessel volume. The features utilized are vascular size, local contrast based on mathematical morphology, degree of curvilinearity based on second derivatives, and geometric features such as volume and length. Detection results were obtained for 19 clinical data sets and the performance of the method was evaluated. Using the number and locations of thrombi diagnosed by radiologists as the gold standard, 100% sensitivity was achieved with 7.7 false positives per case, and 85% sensitivity was obtained with 2.6 false positives. For identification of all the positive cases as positive, i.e., detection of at least one thrombus per positive case, 1.9 false positives per case were obtained. These preliminary results suggest that the method has potential for fully automated detection of pulmonary embolism.     

A fully automated method for lung nodule detection from postero-anterior chest radiographs

In the past decades, a great deal of research work has been devoted to the development of systems that could improve radiologists' accuracy in detecting lung nodules. Despite the great efforts, the problem is still open. In this paper, we present a fully automated system processing digital postero-anterior (PA) chest radiographs, that starts by producing an accurate segmentation of the lung field area. The segmented lung area includes even those parts of the lungs hidden behind the heart, the spine, and the diaphragm, which are usually excluded from the methods presented in the literature. This decision is motivated by the fact that lung nodules may be found also in these areas. The segmented area is processed with a simple multiscale method that enhances the visibility of the nodules, and an extraction scheme is then applied to select potential nodules. To reduce the high number of false positives extracted, cost-sensitive support vector machines (SVMs) are trained to recognize the true nodules. Different learning experiments were performed on two different data sets, created by means of feature selection, and employing Gaussian and polynomial SVMs trained with different parameters; the results are reported and compared. With the best SVM models, we obtain about 1.5 false positives per image (fp/image) when sensitivity is approximately equal to 0.71; this number increases to about 2.5 and 4 fp/image when sensitivity is = 0.78 and = 0.85, respectively. For the highest sensitivity (= 0.92 and 1.0), we get 7 or 8 fp/image.     

Subspace Partitioning for Target Detection and Identification

Detection of a given target or set of targets from observed data is a problem countered in many applications. Regardless of the algorithm selected, detection performance can be severely degraded when the subspace defined by the target data set is singular or ill conditioned. High correlations between target components and their linear combinations lead to false positives and misidentifications, especially for subspace-based detectors. In this paper, we propose a subspace partitioning scheme that allows for detection to be performed in a number of better conditioned subspaces instead of the original subspace. The proposed technique is applied to Raman spectroscopic data analysis. Through both simulation and experimental results, we demonstrate the improvement in the overall detection performance when using the proposed subspace partitioning scheme in conjunction with several subspace detection methods that are commonly used in practice.      

Locating Disturbances in Semiconductor Manufacturing With Stepwise Regression

The ability to locate disturbances in semiconductor manufacturing processes is critical to developing and maintaining a high yield. Analysis of variance (ANOVA), the best current practice for this problem, consists of conducting a series of hypothesis tests at each individual processing step. This approach can lead to excessive false alarms and limited sensitivity when the process contains more than one disturbance. We describe how this problem can be framed as a subset selection problem and propose two new methods based on stepwise regression. Results of over 90 000 Monte Carlo simulations suggest that these new SWR methods locate disturbances with fewer false positives and false negatives than ANOVA. This means process engineers will spend less time responding to false alarms and will be able to locate real disturbances more often.     

Seeing is believing: video classification for computed tomographic colonography using multiple-instance learning

In this paper, we present development and testing results for a novel colonic polyp classification method for use as part of a computed tomographic colonography (CTC) computer-aided detection (CAD) system. Inspired by the interpretative methodology of radiologists using 3-D fly-through mode in CTC reading, we have developed an algorithm which utilizes sequences of images (referred to here as videos) for classification of CAD marks. For each CAD mark, we created a video composed of a series of intraluminal, volume-rendered images visualizing the detection from multiple viewpoints. We then framed the video classification question as a multiple-instance learning (MIL) problem. Since a positive (negative) bag may contain negative (positive) instances, which in our case depends on the viewing angles and camera distance to the target, we developed a novel MIL paradigm to accommodate this class of problems. We solved the new MIL problem by maximizing a L2-norm soft margin using semidefinite programming, which can optimize relevant parameters automatically. We tested our method by analyzing a CTC data set obtained from 50 patients from three medical centers. Our proposed method showed significantly better performance compared with several traditional MIL methods.     

Denoising functional MR images: a comparison of wavelet denoising and Gaussian smoothing

We present a general wavelet-based denoising scheme for functional magnetic resonance imaging (fMRI) data and compare it to Gaussian smoothing, the traditional denoising method used in fMRI analysis. One-dimensional WaveLab thresholding routines were adapted to two-dimensional (2-D) images, and applied to 2-D wavelet coefficients. To test the effect of these methods on the signal-to-noise ratio (SNR), we compared the SNR of 2-D fMRI images before and after denoising, using both Gaussian smoothing and wavelet-based methods. We simulated a fMRI series with a time signal in an active spot, and tested the methods on noisy copies of it. The denoising methods were evaluated in two ways: by the average temporal SNR inside the original activated spot, and by the shape of the spot detected by thresholding the temporal SNR maps. Denoising methods that introduce much smoothness are better suited for low SNRs, but for images of reasonable quality they are not preferable, because they introduce heavy deformations. Wavelet-based denoising methods that introduce less smoothing preserve the sharpness of the images and retain the original shapes of active regions. We also performed statistical parametric mapping on the denoised simulated time series, as well as on a real fMRI data set. False discovery rate control was used to correct for multiple comparisons. The results show that the methods that produce smooth images introduce more false positives. The less smoothing wavelet-based methods, although generating more false negatives, produce a smaller total number of errors than Gaussian smoothing or wavelet-based methods with a large smoothing effect.     

基于感兴趣区域和HOG-MBLBP特征的交通标识检测

交通标识检测中样本类别间的不平衡常常导致分类器的检测性能弱化,为了克服这一问题,该文提出一种基于感兴趣区域和HOG-MBLBP融合特征的交通标识检测方法。首先采用颜色增强技术分割提取出自然背景中交通标识所在的感兴趣区域;然后对标识样本库提取HOG-MBLBP融合特征,并用遗传算法对SVM交叉验证进行参数的优化选取,以此来训练和提升SVM分类器性能;最后将提取的感兴趣区域图像的HOG-MBLBP特征送入训练好的SVM多分类器,进行进一步的精确检测和定位,剔除误检区域。在自建的中国交通标识样本库上进行了实验,结果表明所提方法能达到99.2%的分类准确度,混淆矩阵结果也表明了该方法的优越性。