This work presents a new iris recognition method based on steerable pyramid transform. This method consists of four steps: localization, normalization, features extraction and matching. After locating the iris boundar...
详细信息
This work presents a new iris recognition method based on steerable pyramid transform. This method consists of four steps: localization, normalization, features extraction and matching. After locating the iris boundaries by Hough Transform, normalization is operated by unwrapping the circular ring and isolating the noisy regions. Steerable pyramid filters are then used to capture orientation details from the iris texture. The features are extracted on each filtered sub-image to form a fixed length feature vector which will be compared to other vectors in the matching step. This technique has been tested on infrared light iris images. It has been compared, in both identification and verification modes, to known methods.
A quick 3D needle segmentation algorithm for 3D US data is described in this paper. The algorithm includes the 3D Quick Randomized Hough Transform (3DGHT), which is based on the 3D Randomized Hough Transform and coars...
详细信息
Software metrics are collected at various phases of the software development process. These metrics contain the information of the software and can be used to predict software quality in the early stage of software li...
详细信息
Software metrics are collected at various phases of the software development process. These metrics contain the information of the software and can be used to predict software quality in the early stage of software life cycle. Intelligent computing techniques such as data mining can be applied in the study of software quality by analyzing software metrics. Clustering analysis, which can be considered as one of the data mining techniques, is adopted to build the software quality prediction models in the early period of software testing. In this paper, a new clustering method called Affinity Propagation is investigated for the analysis of two software metric datasets extracted from real-world software projects. Meanwhile, K-Means clustering method is also applied for comparison. The numerical experiment results show that the Affinity Propagation algorithm can be applied well in software quality prediction in the very early stage, and it is more effective on reducing Type II error.
In classification of a multispectral remote sensing image, it is usually difficult to obtain higher classification accuracy if we only consider the image's spectral feature or texture feature alone. In this paper,...
详细信息
In classification of a multispectral remote sensing image, it is usually difficult to obtain higher classification accuracy if we only consider the image's spectral feature or texture feature alone. In this paper, we present a new approach by applying the Ant Colony Optimization (ACO) algorithm to find a multi-feature vector composed of spectral and texture features in order to get a better result in the classification. The experimental results show that ACO algorithm is helpful in subset searching of the features used to classify the multispectral remote sense image. Using the combination of the spectral and texture features obtained by ACO in classification always produces a better accuracy.
Some techniques have been applied to improving software quality by classifying the software modules into fault-prone or non fault-prone categories. This can help developers focus on some high risk fault-prone modules....
详细信息
ISBN:
(纸本)9781424441969
Some techniques have been applied to improving software quality by classifying the software modules into fault-prone or non fault-prone categories. This can help developers focus on some high risk fault-prone modules. In this paper, a distribution-based Bayesian quadratic discriminant analysis (D-BQDA) technique is experimental investigated to identify software fault-prone modules. Experiments with software metrics data from two real projects indicate that this technique can classify software modules into a proper class with a lower misclassification rate and a higher efficiency.
To overcome the main drawbacks of global minimal for active contour models (L. D. Cohen and Ron Kimmel) that the contour is only extracted partially for low SNR images, Method of boundary extraction based on Schrö...
详细信息
To overcome the main drawbacks of global minimal for active contour models (L. D. Cohen and Ron Kimmel) that the contour is only extracted partially for low SNR images, Method of boundary extraction based on Schrödinger Equation is proposed. Our Method is based on computing the numerical solutions of initial value problem for second order nonlinear Schrödinger equation by using discrete Fourier Transformation. Schrödinger transformation of image is first given. We compute the probability P(b,a) that a particle moves from a point a to another point b according to I-Type Schrödinger transformation of image and obtain boundary of object by using quantum contour model.
As the development of CG industry and online games, the requirements of efficient texture synthesis methods are more and more exigent. It is one of the toughest problems while rendering the huge scenes efficiently and...
详细信息
As the development of CG industry and online games, the requirements of efficient texture synthesis methods are more and more exigent. It is one of the toughest problems while rendering the huge scenes efficiently and effectively. In this paper we propose an efficient texture synthesis algorithm by using wavelet technique. Much different from former texture synthesis methods, the method in this paper synthesizes high resolution texture by using lower resolution component decomposed by wavelet transform, which can improve the synthesis efficiency greatly for either stochastic texture or structural one. By using this method, we can also supply an effective control mechanism especially for the structural texture samples. The result shows that we make improvements both on efficiency and effect.
As a kind of powerful anti-counterfeiting device, diffractive optically variable image (DOVI) has been developed and widely used in information security field. However, the identification of DOVI today by bare eyes is...
详细信息
As a kind of powerful anti-counterfeiting device, diffractive optically variable image (DOVI) has been developed and widely used in information security field. However, the identification of DOVI today by bare eyes is not reliable. In this paper we investigate the recognition of DOVI with machine learning method, and five kinds of algorithms, namely quadratic discriminate analysis (QDA), linear discriminate analysis (LDA), regularized discriminate analysis (RDA), leave-one-out covariance matrix estimate (LOOC), and Kullback-Leibler information measure based method (KLIM) are applied to the recognition of DOVI. Considering both time cost and correct classification rate, KLIM classifier exceeds others.
Combining bottom-up and top-down attention influences, a novel region extraction model which based on object-accumulated visual attention mechanism is proposed in this paper. Compared with early research, the new appr...
详细信息
Combining bottom-up and top-down attention influences, a novel region extraction model which based on object-accumulated visual attention mechanism is proposed in this paper. Compared with early research, the new approach brings in prior information at the proper time, updates scan path dynamically, needs less computational resources and reduces the probability to direct the attention to a less-meaning area. The application to search an airport target in remote sensing image was provided, through which the novel mechanism that how visual attention chose the area was described. Compared with another two region extraction models, experimental results confirm the effectiveness of the approach proposed in this paper.
In this paper, we describe four important indirect methods which be used to extract the fetal Electrocardiogram (FECG) signal from an ECG recorded on the mother's abdomen. These methods include the following ones:...
详细信息
In this paper, we describe four important indirect methods which be used to extract the fetal Electrocardiogram (FECG) signal from an ECG recorded on the mother's abdomen. These methods include the following ones: singular value decomposition (SVD) method, independent component analysis (ICA) method, wavelet based methods and adaptive filtering method. The mentioned methods use signal processing techniques for extracting FECG from abdominal electrocardiogram (AECG). We have explained advantages and disadvantages of each method. The methods have also applied on both synthetic and real ECG signals. Efficiencies of the methods compared together based on three important criterions and results are stated and best method based on three criterions is selected.
暂无评论