Intelligent feature extraction and classification of anuran vocalizations

An intelligent identification system for mixed anuran vocalizations is developed in this work to provide the public to easily consult online. The raw mixed anuran vocalization samples are first filtered by noise removal, high frequency compensation, and discrete wavelet transform techniques in order. An adaptive end-point detection segmentation algorithm is proposed to effectively separate the individual syllables from the noise. Six features, including spectral centroid, signal bandwidth, spectral roll-off, threshold-crossing rate, spectral flatness, and average energy, are extracted and served as the input parameters of the classifier. Meanwhile, a decision tree is constructed based on several parameters obtained during sample collection in order to narrow the scope of identification targets. Then fast learning neural-networks are employed to classify the anuran species based on feature set chosen by wrapper feature selection method. A series of experiments were conducted to measure the outcome performance of the proposed work. Experimental results exhibit that the recognition rate of the proposed identification system can achieve up to 93.4%. The effectiveness of the proposed identification system for anuran vocalizations is thus verified.     

Motif analysis for automatic segmentation of CT surface contours into individual surface features

This paper presents a new layer-based technique for automatic high-level segmentation of 3-D surface contours into individual surface features through motif analysis. The procedure starts from a contour-based surface model representing a composite surface area of an object. For each of the surface contours, a relative turning angle (RTA) map is derived. The RTA map usually contains noise and minor features. Algorithms based on motif analysis are applied for extracting a main profile of the RTA map free from background noise and other minor features. All feature points on the extracted profile are further identified from the extracted main profile through further motif analysis. The original contour is thus partitioned into individual segments with the identified feature points. A collection of consecutive contour segments among different layers form an individual 3-D surface feature of the original composite surface. The developed approach using motif analysis is particularly useful for the identification of smooth joins between individual surface features and for the elimination of superposed noise and unwanted minor features.     

A systematic method for fingerprint ridge orientation estimation and image segmentation

This paper proposes a scheme for systematically estimating fingerprint ridge orientation and segmenting fingerprint image by means of evaluating the correctness of the ridge orientation based on neural network. The neural network is used to learn the correctness of the estimated orientation by gradient-based method. The trained network is able to distinguish correct and incorrect ridge orientations, and as a consequence, the falsely estimated ridge orientation of a local image block can be corrected using the around blocks of which orientations are correctly estimated. A coarse segmentation can also be done based on the trained neural network by taking the blocks of correctly estimated orientation as foreground and the blocks of incorrectly estimated orientation as background. Besides, following the steps of estimating ridge orientation correctness, a secondary segmentation method is proposed to segment the remaining ridges which are the afterimage of the previously scanned fingers. The proposed scheme serves for minutiae detection and is compared with VeriFinger 4.2 published by Neurotechnologija Ltd. in 2004, and the comparison shows that the proposed scheme leads to an improved accuracy of minutiae detection.     

A cost-effective and automatic surface defect inspection system for hot-rolled flat steel

Defective steel brings economic and commercial reputation losses to the hot-strip manufacturers, and one of the main difficulties in using machine-vision-based technique for steel surface inspection is time taken to process the massive images suffering from uneven illumination. This paper develops a modular and cost-effective AOI system for hot-rolled flat steel in real time. Firstly, a detailed system topology is constructed according to the design goals covering the vast majority of steel mills, lighting setup and typical defect patterns are presented as well. Secondly, the image enhancement method is designed to overcome the uneven-lighting, over- or under-exposure. Thirdly, the defect detection algorithm is developed based on variance, entropy and average gradient derived from non-overlapping 32×32 pixel blocks of steel surface images. Fourthly, the proposed algorithms are implemented on FPGA in parallel to improve the inspection speed. Finally, 18,071 contiguous images (4096×1024 pixel) acquired from 7 defective steel rolls have been inspected by the realized AOI system to evaluate the performance. The experimental results show that the proposed method is speedy and effective enough for real applications in the hot-rolled steel manufacturing, with 92.11% average accuracy while 5.54% false-negative rate.     

弹底底火表面缺陷图像分割方法

枪弹弹底底火检测是枪弹质量控制的核心,为了有效分割弹底底火表面缺陷图像,提出一种新的分割方法。该方法针对弹底检测要求及弹底图像基本特征,首先大致确定待检测的底火部分图像,对其运用Log算子进行边缘检测确定底火圆边缘;然后分析了Hough变换和最小二乘法圆拟合的圆检测算法的各自优缺点,提出了改进Hough变换和最小二乘法圆拟合相结合的圆检测算法,以获得较精确的底火圆圆心和半径;最后利用底火圆圆心和半径提取底火圆图像,利用统计阈值分割底火表面缺陷,利用数学形态学优化分割结果。通过实验表明,运用此方法分割弹底底火表面缺陷,平均误分割率低于10%,平均偏差小于17个像素,表现出较好的准确性和鲁棒性。     

New training strategies for RBF neural networks for X-ray agricultural product inspection

Classification of real-time X-ray images of pistachio nuts is discussed. The goal is to reduce the percentage of infested nuts while not rejecting more than a few percent of the good nuts. Radial basis function (RBF) neural network classifiers are emphasized. New training procedures are developed that allow samples such as those that are near decision boundaries to be treated differently from other samples. New clustering methods and new cluster classes are advanced to select and separately control various RBF parameters. These advancements are shown to be of use in this application.     

A defect prediction method for software versioning

New methodologies and tools have gradually made the life cycle for software development more human-independent. Much of the research in this field focuses on defect reduction, defect identification and defect prediction. Defect prediction is a relatively new research area that involves using various methods from artificial intelligence to data mining. Identifying and locating defects in software projects is a difficult task. Measuring software in a continuous and disciplined manner provides many advantages such as the accurate estimation of project costs and schedules as well as improving product and process qualities. This study aims to propose a model to predict the number of defects in the new version of a software product with respect to the previous stable version. The new version may contain changes related to a new feature or a modification in the algorithm or bug fixes. Our proposed model aims to predict the new defects introduced into the new version by analyzing the types of changes in an objective and formal manner as well as considering the lines of code (LOC) change. Defect predictors are helpful tools for both project managers and developers. Accurate predictors may help reducing test times and guide developers towards implementing higher quality codes. Our proposed model can aid software engineers in determining the stability of software before it goes on production. Furthermore, such a model may provide useful insight for understanding the effects of a feature, bug fix or change in the process of defect detection.

Automatic plaque segmentation based on hybrid fuzzy clustering and k nearest neighborhood using virtual histology intravascular ultrasound images

Thin cap fibroatheroma (TCFA) or “vulnerable plaque” is responsible for the majority of coronary artery death. Virtual Histology Intravascular Ultrasound (VH-IVUS) image is a clinically available method for visualizing color coded tissue maps. However, this technique has considerable limitations in providing medical relevant information for identifying vulnerable plaque. The aim of this paper is to improve the identification of TCFA in VH-IVUS image. Therefore, this paper proposes a set of algorithms for segmentation, feature extraction, and plaque type classification to accurately identify TCFA. A hybrid model using the FCM and kNN (HFCM-kNN) is proposed to accurately segment the VH-IVUS image. The proposed technique is capable of eliminating outliers and detecting clusters with different densities in VH-IVUS image. The next process is extracting plaque features to provide an accurate definition of the unstable (vulnerable) plaque. To achieve the above contribution, five algorithms are proposed to extract significant features from VH-IVUS images. Machine learning approaches are applied for training 440 in-vivo images obtained from 8 patients. Results proved the dominance of the proposed method for TCFA detection with accuracy rate of 98.02% compared with the 76.5% obtained by the cardiologist decision. Moreover, by validation of VH-IVUS images and their corresponding Optical Coherence Tomography (OCT) images, accuracy of 92.85% is achieved.     

基于神经网络的高效智能入侵检测系统

描述了一种采用人工神经网络技术的高效实时入侵检测模型,对网络数据处理、神经网络的训练及其算法、神经网络的检测及其算法进行了详细的论述,目的是用神经网络的优势来改进现存入侵检测系统中的一些不足之处,使入侵检测系统效率更高,更具智能化。     

Selecting informative data for defect segmentation from imbalanced datasets via active learning

The storage and labeling of industrial data incur significant costs during the development of defect detection algorithms. Active learning solves these problems by selecting the most informative data among the given unlabeled data. The existing active learning methods for image segmentation focus on studying natural images and medical images, with less attention given to industrial images, and little research has been performed on imbalanced data. To solve these problems, we propose an active learning framework to selecting informative data for defect segmentation under imbalanced data. In the initialization stage, the framework uses self-supervised learning to initialize the data so that the initialization data contain more defect data, thereby solving the cold-start problem. During the iterative stage, we design the main body of the active learning framework, which is composed of a segmentation learner and a reconstruction learner. These learners use supervised learning to further improve the framework’s ability to select informative data. The experimental results obtained on public and self-owned datasets show that the framework can save 70% of the required storage space and greatly reduce the cost of labeling. The intersection over union value proves that the designed framework can achieve the equivalent effect of labeling the whole dataset by labeling partial data.     

Image segmentation by pixel classification

A fast boundary finding algorithm is presented which works without threshold operation and without any interactive control. The procedure can be described as a hierarchical two-step algorithm. In the first step the image is divided into two disjunct regions, one of them including the whole object of interest.In the second step the problem of boundary finding is suggested as a classification problem, which means that for any pixel a four-dimensional feature vector is computed which allows classification of pixels into contour elements and any other pixels.The algorithm was tested on several thousand cell images and can be easily adapted to other problems by modification of a set of parameters.     

Projection based method for segmentation of human face and its evaluation

We detect facial features and then circumscribe each facial feature with the smallest rectangle possible by using vertical and horizontal gray value projections of pixels. The result is evaluated with respect to the manually located enclosing rectangle on the images of a publicly available database.     

LED cosmetic flaw vision inspection system

The paper describes a vision inspection system that is developed to detect diffused LED defects, namelyscratches, bubbles, contamination, blister/blemish, fuzzy dome andoff centre defects in less than 200 ms using a 200 MHz Pentium PC, a Matrox Genesis frame grabber and a Pulnix high speed camera. Various image-processing techniques are utilised for the inspection task. A machine vision approach that comprises pre-processing, image segmentation, clean up and feature extraction operations is implemented to perform the automated cosmetic flaw inspection. Based on 200 LED samples, the system was found to be 100% accurate in detecting LED dome defects on LEDs of different colour and intensity. The system can also classify defects into different categories and was found to be 90% accurate.     

A Kolmogorov-Smirnov statistic based segmentation approach to learning from imbalanced datasets: With application in property refinance prediction

Classification is an important task in data mining. Class imbalance has been reported to hinder the performance of standard classification models. However, our study shows that class imbalance may not be the only cause to blame for poor performance. Rather, the underlying complexity of the problem may play a more fundamental role. In this paper, a decision tree method based on Kolmogorov-Smirnov statistic (K-S tree), is proposed to segment the training data so that a complex problem can be divided into several easier sub-problems where class imbalance becomes less challenging. K-S tree is also used to perform feature selection, which not only selects relevant variables but also removes redundant ones. After segmentation, a two-way re-sampling method is used at the segment level to empirically determine the optimal sampling percentage and the rebalanced data is used to fit logistic regression models, also at the segment level. The effectiveness of the proposed method is demonstrated through its application on property refinance prediction.     

基于文件静态信息的木马检测模型

提出了一种基于文件静态信息检测木马文件的新方法,并以PE文件为分析对象,利用决策树与基于BP学习算法的分层网络,设计了基于文件静态信息的木马检测模型,实验证明,该模型能有效地判断文件是否为木马文件。     

Visual surveillance by dynamic visual attention method

This paper describes a method for visual surveillance based on biologically motivated dynamic visual attention in video image sequences. Our system is based on the extraction and integration of local (pixels and spots) as well as global (objects) features. Our approach defines a method for the generation of an active attention focus on a dynamic scene for surveillance purposes. The system segments in accordance with a set of predefined features, including gray level, motion and shape features, giving raise to two classes of objects: vehicle and pedestrian. The solution proposed to the selective visual attention problem consists of decomposing the input images of an indefinite sequence of images into its moving objects, defining which of these elements are of the user's interest at a given moment, and keeping attention on those elements through time. Features extraction and integration are solved by incorporating mechanisms of charge and discharge—based on the permanency effect—, as well as mechanisms of lateral interaction. All these mechanisms have proved to be good enough to segment the scene into moving objects and background.     

A novel neural network method for shortest path tree computation

Shortest path tree (SPT) computation is a critical issue in many real world problems, such as routing in networks. It is also a constrained optimization problem, which has been studied by many authors in recent years. Typically, it is solved by heuristic algorithms, such as the famous Dijkstra's algorithm, which can quickly provide a good solution in most instances. However, with the scale of problem increasing, these methods are inefficient and may consume a considerable amount of CPU time. Neural networks, which are massively parallel models, can solve this question easily. This paper presents an efficient modified continued pulse coupled neural network (MCPCNN) model for SPT computation in a large scale instance. The proposed model is topologically organized with only local lateral connections among neurons. The start neuron fires first, and then the firing event spreads out through the lateral connections among the neurons, like the propagation of a wave. Each neuron records its parent, that is, the neighbor which caused it to fire. It proves that the generated wave in the network spreads outward with travel times proportional to the connection weight between neurons. Thus, the generated path is always the global optimal shortest path from the source to all destinations. The proposed model is also applied to generate SPTs for a real given graph step by step. The effectiveness and efficiency of the proposed approach is demonstrated through simulation and comparison studies.     

An automatic inspection system for printed wiring board masks

This paper describes an automatic inspection system for printed wiring board masks. This system utilizes a hierarchical defect detection algorithm developed for inspecting high precision mask patterns for both printed wiring boards and integrated circuits. This algorithm makes use of geometrical characteristics of mask patterns to discriminate defects. Sufficient defect detection capability, as well as high inspection throughput, has been accomplished by hardware-implementation of the algorithm and inspection result utilization through retouching machines.     

Feature extraction and image segmentation using self-organizing networks

Feature extraction and image segmentation (FEIS) are two primary goals of almost all image-understanding systems. They are also the issues at which we look in this paper. We think of FEIS as a multilevel process of grouping and describing at each level. We emphasize the importance of grouping during this process because we believe that many features and events in real images are only perceived by combining weak evidence of several organized pixels or other low-level features. To realize FEIS based on this formulation, we must deal with such problems as how to discover grouping rules, how to develop grouping systems to integrate grouping rules, how to embed grouping processes into FEIS systems, and how to evaluate the quality of extracted features at various levels. We use self-organizing networks to develop grouping systems that take the organization of human visual perception into consideration. We demonstrate our approach by solving two concrete problems: extracting linear features in digital images and partitioning color images into regions. We present the results of experiments on real images.