Search

In machine vision, template matching is key component and used usefully in various tasks such as pick and place, mark identification, and alignment. In this paper, we propose fast template matching algorithm using edge projection. Proposed algorithm reduces the search problem from 2D into 1D using edge projection within the 2D template area. By this, it could effectively reduce the computational burden. Also, it gives comparable discriminating power compared to template matching using intensity. In this paper, rotation and translation search is implemented to cope with typical machine vision application where the height between camera and target object is fixed. [ABSTRACT FROM AUTHOR]

This paper proposes a novel method for the recognition of passports based on a FCM-based RBF network. First, for the extraction of individual codes for recognizing, this paper targets code sequence blocks including individual codes by applying Sobel masking, horizontal smearing and a contour tracking algorithm on the passport image. As the last step, individual codes are recovered and extracted from the binarized areas by applying CDM masking and vertical smearing. This paper also proposes a FCM-based RBF network that adapts the FCM algorithm for the middle layer. This network is applied to the recognition of individual codes. The results of the experiments for performance evaluation on the real passport images showed that the proposed method has the better performance compared with other approaches. [ABSTRACT FROM AUTHOR]

In this paper, we propose a partitional approach for estimating null value (1) Firstly, we utilize stepwise regression to select the important attributes from the database. (2) Secondly, we use a partitional approach to build the data category. The data partitioned by the first two important attributes. (3) Thirdly, we apply the clustering method to cluster output data. (4) Fourthly, Calculate the degree of influential between the attributes. There are two ways to calculate the degree of influential. One is correlation coefficient and the other is regression coefficients. (5) To verify our method, this paper utilizes a practical human resource database in Taiwan, and Mean of Absolute Error Rate (MAER) as evaluation criterion to compare with other methods; it is shown that our proposed method proves better than other methods for estimating null values in relational database systems. [ABSTRACT FROM AUTHOR]

In this paper, we discuss the conditioning issue in D-S evidence theory in multi-dimensional space. Based on Dempster conditioning, Bayes' rule and product rule, which are similar to that in probability theory, are presented in this paper. Two kinds of conditional independence called weak conditional independence and strong conditional independence are introduced, which can significantly simplify the inference process when evidence theory is applied to practical application. [ABSTRACT FROM AUTHOR]

In this paper we improve on the supervised classification method developed in Kornienko et al. (2002) by the introduction of Principal Components Analysis to the inference process. We also extend the classifier from dealing with binomial (two-class) problems only to multinomial (multi-class) problems. The application to which the MML criterion has been applied in this paper is the classification of objects via a linear hyperplane, where the objects are able to come from any multi-class distribution. The inclusion of Principal Component Analysis to the original inference scheme reduces the bias present in the classifier's search technique. Such improvements lead to a method which, when compared against three commercial Support Vector Machine (SVM) classifiers on Binary data, was found to be as good as the most successful SVM tested. Furthermore, the new scheme is able to classify objects of a multiclass distribution with just one hyperplane, whereas SVMs require several hyperplanes. Keywords: Machine Learning, Knowledge discovery and data mining. [ABSTRACT FROM AUTHOR]

This paper provides a framework of using news articles and economic data to model the exchange rate changes between Euro and US dollars. Many studies have conducted on the approach of regressing exchange rate movement using numerical data such as macroeconomic indicators. However, this approach is effective in studying the long term trend of the movement but not so accurate in short to middle term behaviour. Recent research suggests that the market daily movement is the result of the market reaction to the daily news. In this paper, it is proposed to use text mining methods to incorporate the daily economic news as well as economic and political events into the prediction model. While this type of news is not included in most of existing models due to its non-quantitative nature, it has important influence in short to middle terms of market behaviour. It is expected that this approach will lead to an exchange rate model with improved accuracy. [ABSTRACT FROM AUTHOR]

This paper introduces a classification system that exploits the content information as well as citation structure for scientific paper classification. The system first applies a content-based statistical classification method which is similar to general text classification. We investigate several classification methods including K-nearest neighbours, nearest centroid, naive Bayes and decision trees. Among those methods, the K-nearest neighbours is found to outperform others while the rest perform comparably. Using phrases in addition to words and a good feature selection strategy such as information gain can improve system accuracy and reduce training time in comparison with using words only. To combine citation links for classification, the system proposes an iterative method to update the labellings of classified instances using citation links. Our results show that, combining contents and citations significantly improves the system performance. [ABSTRACT FROM AUTHOR]

In content-based image retrieval (CBIR), the user usually poses several labelled images and then the system attempts to retrieve all the images relevant to the target concept defined by these labelled images. It may be helpful if the system can return relevant images where the regions of interest (ROI) are explicitly located. In this paper, this task is accomplished with the help of multi-instance learning techniques. In detail, this paper proposes the CkNN-ROI algorithm, which regards each image as a bag comprising many instances and picks from positive bag the instance that has great chance to meet the target concept to help locate ROI. Experiments show that the proposed algorithm can efficiently locate ROI in CBIR process. [ABSTRACT FROM AUTHOR]

Minimal change is a fundamental principle for modelling system dynamics. In this paper, we study the issue of minimal change for Computational Tree Logic (CTL) model update. We first consider five primitive updates which capture the basic update operations in the CTL model. Based on these primitive updates, we then define the minimal change criteria for CTL model update and develop formal algorithms that embed the underlying minimal change principle. We also present the well known microwave oven scenario to demonstrate our update algorithms. Our work presented in this paper can be viewed as the first formalization towards an integration of model checking and model updating for system modification. [ABSTRACT FROM AUTHOR]

This paper presents a method that enable a domestic robot to show emotions with its facial expressions. The previous methods using built-in facial expressions were able to show only scanty face. To express faces showing complex emotion, mixed emotions and different strengths of emotions, more facial expressions are needed. We have therefore developed a system that converts emotions into "Ifbot" robot's facial expressions automatically. They are created from emotion parameters, which represent its emotions. Content Areas: Entertainment and AI, robotics. [ABSTRACT FROM AUTHOR]