Search

The issues in clustering, the unsupervised classification of patterns, have been addressed in many contexts and by researchers in many disciplines. Its broad appeal and application as one of the steps in exploratory data analysis is well-known. Literature on the pattern clustering methods, algorithms is surveyed. The authors have tried to explore the performance of hierarchical clustering method in this paper. [ABSTRACT FROM AUTHOR]

With the development of digital cameras, the digital photographs were flooded in our life. How to classify images efficiently in huge image database becomes an important research topic. In recent years, the related researches of the image classification are based on semantics. The scene image classification has received much attention especially because it contains plenty semantics. It is a difficult challenge to classify the scene images accurately. This paper tries to use particle swarm optimization (PSO) algorithm that has biological characteristic, and to train with the scene images of semantics. We can get a scene transformation matrix during the process. The scene transformation matrix can be used to classify scene images, which are close to human's semantics. The experiment shows our proposed method has great correct classification rate. [ABSTRACT FROM AUTHOR]

In recent years, the semiconductor industry has been a high-growth business. Yield improvement becomes more and more important for semiconductor manufacturing process and it's the important element to ensure the profitability. Defect spatial patterns impede yield and it reveal the root causes of the occurred defects. This research developed a defect spatial pattern recognition methodology. In this research, defect spatial patterns are classified into seven categories, Curve Type, Line Type, Local Type, Ring Type, Radial Type, and Repeat Type and Die Edge Type. Original defects are filtered to eliminate random defects. With random defect removed, a clustering method is designed to cluster systematic defects. Clustered defects are then analyzed with minimum rectangle. A feature extraction procedure based on wavelet transform is developed to extract features that represent different defect patterns. By setting feature vectors into feature space and applying hierarchical agglomerative algorithm to clustering, it is expected to reach the goal of description and classification. The presented methodology is verified with real industrial data from a famous semiconductor company. The experimental results show the presented methodology is able to recognize defect patterns with recognition accuracy of 95%. [ABSTRACT FROM AUTHOR]