Hypothesizing Structures in Edge-Focused Cerebral Magnetic Resonance Images Using Graph-Theoretic Cycle Enumeration

We present a novel method for the automatic generation of structure hypotheses (that is, educated guesses) suitable for recognition in medical images. The notion is that computer-based image analysis cannot be accomplished in a purely bottom-up fashion; the system should first organize the image structure into promising hypotheses, each of which is then compared to elements of the system modelbase for recognition or rejection. In this work, we tackle the hypothesis generation problem, for which computational efficiency is a major concern. We base our approach on segment-based edge-focusing to delineate significant boundaries precisely, and graph-theoretic cycle enumeration to produce natural closures and, therefore, plausible tissue structures of interest from incomplete boundary information. An efficient edge focusing algorithm selects significant fine scale boundaries as those natural descendants (in scale space) of prominent coarse scale edges. The fine scale representation provides the localization precision necessary, while the focusing ensures that only significant contours surviving over a range of scales are considered and so eliminates much of the "clutter" associated with a fine scale edge map. The spatial relationships among the edge segments are stored in the form of a directed graph. Possible extensions (closures) of broken edge segments are searched using time- and space-efficient voting methods. Cycle enumeration techniques for directed graphs then generate the structure hypotheses. The overall paradigm is fairly general and can be used in other problem domains, certainly for images of other parts of the anatomy. We demonstrate the effectiveness of the method with extensive experimental results on various magnetic resonance images of the human brain.     

Pattern recognition and increasing of the computational efficiency of a parallel realization of the probabilistic neural network with homogeneity testing

The research subject is the computational complexity of the probabilistic neural network (PNN) in the pattern recognition problem for large model databases. We examined the following methods of increasing the efficiency of a neural-network classifier: a parallel multithread realization, reducing the PNN to a criterion with testing of homogeneity of feature histograms of input and reference images, approximate nearest-neighbor analyses (Best-Bin First, directed enumeration methods). The approach was tested in facial-recognition experiments with FERET dataset.     

基于图像超分辨极限学习机的极低分辨率人脸识别

极低分辨率图像本身包含的判别信息少且容易受到噪声的干扰,在现有的人脸识别算法下识别率较低。为了解决这一问题,提出一种基于图像超分辨率(SR)极限学习机(ELM)的人脸识别算法。首先,从样本库学习耦合的高低分辨率图像稀疏表达字典,利用高低分辨率表达系数的流形一致性重建高分辨率图像;其次,在超分辨率重建的高分辨率(HR)图像上构建ELM模型,训练获得前向神经网络的连接权值;最后,通过ELM预测输入极低人脸图像的类别属性。实验结果表明,针对于重建后的极低分辨率人脸图片,与协同表示的分类(CRC)人脸识别算法相比,所提算法将识别率分别提升了2%;同时也大幅度缩短了识别的时间。结果表明所提算法能够有效解决极低分辨率图片判决信息不足的问题,具有较好的识别能力。     

Static hand gesture recognition using neural networks

This paper presents a novel technique for hand gesture recognition through human–computer interaction based on shape analysis. The main objective of this effort is to explore the utility of a neural network-based approach to the recognition of the hand gestures. A unique multi-layer perception of neural network is built for classification by using back-propagation learning algorithm. The goal of static hand gesture recognition is to classify the given hand gesture data represented by some features into some predefined finite number of gesture classes. The proposed system presents a recognition algorithm to recognize a set of six specific static hand gestures, namely: Open, Close, Cut, Paste, Maximize, and Minimize. The hand gesture image is passed through three stages, preprocessing, feature extraction, and classification. In preprocessing stage some operations are applied to extract the hand gesture from its background and prepare the hand gesture image for the feature extraction stage. In the first method, the hand contour is used as a feature which treats scaling and translation of problems (in some cases). The complex moment algorithm is, however, used to describe the hand gesture and treat the rotation problem in addition to the scaling and translation. The algorithm used in a multi-layer neural network classifier which uses back-propagation learning algorithm. The results show that the first method has a performance of 70.83% recognition, while the second method, proposed in this article, has a better performance of 86.38% recognition rate.     

Performance evaluation of marked graphs by linear programming

Performance evaluation is an important issue for discrete event dynamic systems, which in many cases can be described in terms of the language of Petri nets. In particular, for marked graphs, a subclass of Petri nets, a formula for performance evaluation is widely known. That is, the ratio of the total execution time to the number of tokens in a cycle gives a lower bound for the cycle time of the system, and the maximum of these ratios over all cycles determines the overall system performance. However, we need to enumerate all directed cycles in a graph to apply this formula of performance evaluation. Carrying out this enumeration for an actual system is often impractical, since the number of cycles in a graph usually grows exponentially with the size of a system. We give a linear algebraic characterization for directed cycles, and based on this result, transform the problem of performance evaluation into a simple linear programming problem. A few explanatory examples are also given.     

Locally linear metric adaptation with application to semi-supervised clustering and image retrieval

Many computer vision and pattern recognition algorithms are very sensitive to the choice of an appropriate distance metric. Some recent research sought to address a variant of the conventional clustering problem called semi-supervised clustering, which performs clustering in the presence of some background knowledge or supervisory information expressed as pairwise similarity or dissimilarity constraints. However, existing metric learning methods for semi-supervised clustering mostly perform global metric learning through a linear transformation. In this paper, we propose a new metric learning method that performs nonlinear transformation globally but linear transformation locally. In particular, we formulate the learning problem as an optimization problem and present three methods for solving it. Through some toy data sets, we show empirically that our locally linear metric adaptation (LLMA) method can handle some difficult cases that cannot be handled satisfactorily by previous methods. We also demonstrate the effectiveness of our method on some UCI data sets. Besides applying LLMA to semi-supervised clustering, we have also used it to improve the performance of content-based image retrieval systems through metric learning. Experimental results based on two real-world image databases show that LLMA significantly outperforms other methods in boosting the image retrieval performance.     

Inexact graph matching for model-based recognition: Evaluation and comparison of optimization algorithms

A method for segmentation and recognition of image structures based on graph homomorphisms is presented in this paper. It is a model-based recognition method where the input image is over-segmented and the obtained regions are represented by an attributed relational graph (ARG). This graph is then matched against a model graph thus accomplishing the model-based recognition task. This type of problem calls for inexact graph matching through a homomorphism between the graphs since no bijective correspondence can be expected, because of the over-segmentation of the image with respect to the model. The search for the best homomorphism is carried out by optimizing an objective function based on similarities between object and relational attributes defined on the graphs. The following optimization procedures are compared and discussed: deterministic tree search, for which new algorithms are detailed, genetic algorithms and estimation of distribution algorithms. In order to assess the performance of these algorithms using real data, experimental results on supervised classification of facial features using face images from public databases are presented.     

An improved species based genetic algorithm and its application in multiple template matching for embroidered pattern inspection

This paper describes an improved genetic algorithm (GA) using the notion of species in order to solve an embroidery inspection problem. This inspection problem is actually a multiple template matching problem which can be formulated as a multimodal optimization problem. In many cases, the run time of the multiple template matching problem is dominated by repeating the similarity calculations and moving the templates over the source image. To cope with this problem, the proposed species based genetic algorithm (SbGA) is capable to determine its neighborhood best values for solving multimodal optimization problems. The SbGA has been statistically tested and compared with other genetic algorithms on a number of benchmark functions. After proving its effectiveness, it is integrated with multi-template matching method, namely SbGA–MTM method to solve the embroidery inspection problem. Furthermore, the notion of bounded partial correlation (BPC) is also adopted as an acceleration strategy, which enhances the overall efficiency. Experimental results indicate that the SbGA–MTM method is proven to solve the inspection problem efficiently and effectively. With the proposed method, the embroidered patterns can be identified and checked automatically.     

A multi-objective intelligent water drop algorithm to minimise cost Of goods sold and time to market in logistics networks

The Intelligent Water Drop (IWD) algorithm is inspired by the movement of natural water drops (WD) in a river. A stream can find an optimum path considering the conditions of its surroundings to reach its ultimate goal, which is often a sea. In the process of reaching such destination, the WD and the environment interact with each other as the WD moves through the river bed. Similarly, the supply chain problem can be modelled as a flow of stages that must be completed and optimised to obtain a finished product that is delivered to the end user. Every stage may have one or more options to be satisfied such as suppliers, manufacturing or delivery options. Each option is characterised by its time and cost. Within this context, multi–objective optimisation approaches are particularly well suited to provide optimal solutions. This problem has been classified as NP hard; thus, this paper proposes an approach aiming to solve the logistics network problem using a modified multi–objective extension of the IWD which returns a Pareto set.Artificial WD, flowing through the supply chain, will simultaneously minimise the cost of goods sold and the lead time of every product involved by using the concept of Pareto optimality. The proposed approach has been tested over instances widely used in literature yielding promising results which are supported by the performance measurements taken by comparison to the ant colony meta-heuristic as well as the true fronts obtained by exhaustive enumeration. The Pareto set returned by IWD is computed in 4 s and the generational distance, spacing, and hyper–area metrics are very close to those computed by exhaustive enumeration. Therefore, our main contribution is the design of a new algorithm that overcomes the algorithm proposed by Moncayo-Martínez and Zhang (2011).This paper contributes to enhance the current body of knowledge of expert and intelligent systems by providing a new, effective and efficient IWD-based optimisation method for the design and configuration of supply chain and logistics networks taking into account multiple objectives simultaneously.     

一种基于SIFT算子的人脸识别方法

高独特性特征的选择以及合适匹配策略的选用是人脸识别技术的关键。讨论了基于仿射不变的几何特征SIFT算子进行人脸识别的方法。SIFT算子的计算复杂度较高,并且不同的人脸表情和图像模糊会加大特征匹配的难度。为克服上述缺点,提出了一种新的算法,将选择6个人脸上感兴趣子区域进行描述,并根据各自的独特性赋予不同的权值,最后在匹配过程中使用相似度的平方来减小偏差数据造成的影响。实验结果表明,该方法能有效减轻表情变化对于身份识别率急剧下降的影响,并可显著减少计算复杂度和特征匹配时间。     

A heuristic procedure for production planning of modern manufacturing systems

The purpose of this paper is to present a new heuristic algorithm based on a feasible enumeration method, developed to solve the machine loading and product-mix decision problems for manufacturing systems based on group technology. It provides an efficient tool for machine load and product-mix analysis to optimally select parts to be manufactured in a limited amount of time available in a given production facility, by applying the group technology concept. A computational algorithm is developed, a sample numerical problem included, and computational results presented. It is shown that the algorithm herein proposed is very efficient from the computational view point. The heuristics imbedded in the feasible enumeration procedure is repreented by a priority rule which has been found to be independent of problem data and general for the class of problem analysed.     

Mitosis event recognition and detection based on evolution of feature in time domain

Mitosis detection and recognition in phase-contrast microscopy image sequences is a fundamental problem in many biomedical applications. Traditionally, researchers detect all mitotic cells from these image sequences with human eyes, which is tedious and time consuming. In recent years, many computer vision technologies were proposed to help humans to achieve the mitosis detection automatically. In this paper, we present an approach which utilized the evolution of feature in the time domain to represent the feature of mitosis. Firstly, the feature of each cell image is extracted by the different method (GIST, SIFT, CNN). Secondly, we construct the levels of motorists according to the steps of mitosis. The pooling method is utilized to handle the feature fusion in each dimension and in different time segments. Third, the pooling features were combined to one vector to represent the characters of this video. Finally, tradition machine learning method SVM is used to handle the mortises recognition problem. In order to demonstrate the performance of our approach, motorists event detection is made in some microscopy image sequences. In the experiment, some classic methods as comparison method are made in this paper. The corresponding experiments also demonstrate the superiority of our approach.     

印章鉴定系统的图像处理研究

在银行的印章鉴定系统中,正确识别票据印章的前提条件是得到高质量的预处理图像。预处理的主要过程是将印章图像三值化,去噪声并进行分割,然后将分割图像送入后续识别模块进行识别。由于票据模式的多样性,背景的复杂性和图像采集的任意性,使得图像的预处理面临较大的困难。文章主要研究了预处理过程中阈值的确定方法,以及去除印章区域复杂噪声的算法。实践证明,在去噪声算法中,通过多种滤波器的有效组合,能得到较高质量的处理图像,从而满足了识别算法的需要。     

The quotient image: class-based re-rendering and recognition withvarying illuminations

The paper addresses the problem of “class-based” image-based recognition and rendering with varying illumination. The rendering problem is defined as follows: Given a single input image of an object and a sample of images with varying illumination conditions of other objects of the same general class, re-render the input image to simulate new illumination conditions. The class-based recognition problem is similarly defined: Given a single image of an object in a database of images of other objects, some of them multiply sampled under varying illumination, identify (match) any novel image of that object under varying illumination with the single image of that object in the database. We focus on Lambertian surface classes and, in particular, the class of human faces. The key result in our approach is based on a definition of an illumination invariant signature image which enables an analytic generation of the image space with varying illumination. We show that a small database of objects-in our experiments as few as two objects-is sufficient for generating the image space with varying illumination of any new object of the class from a single input image of that object. In many cases, the recognition results outperform by far conventional methods and the re-rendering is of remarkable quality considering the size of the database of example images and the mild preprocess required for making the algorithm work     

Efficient Algorithms for the Inference of Minimum Size DFAs

This work describes algorithms for the inference of minimum size deterministic automata consistent with a labeled training set. The algorithms presented represent the state of the art for this problem, known to be computationally very hard.In particular, we analyze the performance of algorithms that use implicit enumeration of solutions and algorithms that perform explicit search but incorporate a set of techniques known as dependency directed backtracking to prune the search tree effectively.We present empirical results that show the comparative efficiency of the methods studied and discuss alternative approaches to this problem, evaluating their advantages and drawbacks.     

多姿态人脸识别

人脸识别在很多场合都有重要的作用,传统的身份验证是采用某种识别号码等方法, 以阻止伤造的发生。由于人的视觉特征如面部,姿态等是相对稳定而且各不相同的,因此采用这些特征进行身份的识别是可行的本文提出了一种处理多姿态人脸识别的多候选类加权识别方法,为了减少姿态变化的影响,提出了相应的预处理法。     

Minimum–Maximum regret redundancy allocation with the choice of redundancy strategy and multiple choice of component type under uncertainty

This paper deals with a redundancy allocation problem in series–parallel systems with the choice of redundancy strategy, including active and cold standby strategies in which component’s time to failure follows an Erlang distribution. The scale parameter of Erlang distribution and consequently the reliability of each component are imprecise in terms of interval data, and only the lower and upper bounds are known. This problem, for the first time, is formulated through Min–Max regret criterion, which is commonly used to define robust solutions. The resulting problem formulation contains an unlimited number of constraints, and a Benders’ decomposition method is implemented to deal with the given problem. This method is compared with an enumeration method to show its effectiveness. The performance of the proposed model using the Benders’ decomposition method is examined over different problem sizes, and the associated results are analyzed.