Search

Self-organizing feature maps (SOFM) can learn both the distribution and topology of the input vectors they are trained on. According to this characteristic, we construct neural networks with a family of self-organizing feature maps to cluster the input data space. The proposed algorithm in this paper defines a novel similarity measure, topological similarity, and employs some new concepts, such as SOFM family, UsageFactor. The clustering algorithm handles the clusters with arbitrary shapes and avoid the limitations of the conventional clustering algorithms. We conclude our paper by several experiments with synthetic and standard data set of different characteristics, which show good performance of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Image segmentation is an important component in image processing, pattern recognition and computer vision. Many segmentation algorithms have been proposed. However, segmentation methods for both noisy and noise-free images have not been studied in much detail. Neutrosophic set (NS), a part of neutrosophy theory, studies the origin, nature, and scope of neutralities, as well as their interaction with different ideational spectra. However, neutrosophic set needs to be specified and clarified from a technical point of view for a given application or field to demonstrate its usefulness. In this paper, we apply neutrosophic set and define some operations. Neutrosphic set is integrated with an improved fuzzy c-means method and employed for image segmentation. A new operation, α-mean operation, is proposed to reduce the set indeterminacy. An improved fuzzy c-means (IFCM) is proposed based on neutrosophic set. The computation of membership and the convergence criterion of clustering are redefined accordingly. We have conducted experiments on a variety of images. The experimental results demonstrate that the proposed approach can segment images accurately and effectively. Especially, it can segment the clean images and the images having different gray levels and complex objects, which is the most difficult task for image segmentation. [ABSTRACT FROM AUTHOR]

The current paper proposes a font classification method for document images that uses non-negative matrix factorization (NMF), that is able to learn part-based representations of objects. The basic idea of the proposed method is based on the fact that the characteristics of each font are derived from parts of individual characters in each font rather than holistic textures. Spatial localities, parts composing of font images, are automatically extracted using NMF and, then, used as features representing each font. Using hierarchical clustering algorithm, these feature sets are generalized for font classification, resulting in the prototype templates construction. In both the prototype construction and font classification, earth mover's distance (EMD) is used as the distance metric, which is more suitable for the NMF feature space than Cosine or Euclidean distance. In the experimental results, the distribution of features and the appropriateness of the features specifying each font are investigated, and the results are compared with a related algorithm: principal component analysis (PCA). The proposed method is expected to improve the performance of optical character recognition (OCR), document indexing and retrieval systems, when such systems adopt a font classifier as a preprocessor. [ABSTRACT FROM AUTHOR]

This paper presents a gray-scale skeletonization algorithm based on the gray weighted distance transformation (GWDT). The proposed algorithm is conceptually simple and could be used to process nonuniformly distributed gray-scale images. The algorithm can detect the hollows on the gray-scale image, a feature that is often ignored in other skeletonization algorithms, and improves the quality of the skeleton. [ABSTRACT FROM AUTHOR]