The retrieval using single feature has a certain limitation, which fails to comprehensively describe an image. Aiming at such retrieval defect, this paper proposes an image retrieval method integrating color and texture. Firstly, carry out image segmentation with uniformly-spaced method, and then extract color feature of each segmentation with weighting processing done; and then, extract textur...

This paper describes the techniques we explored to improve the translation of news text in the German-English and HungarianEnglish tracks of the WMT09 shared translation task. Beginning with a convention hierarchical phrase-based system, we found benefits for using word segmentation lattices as input, explicit generation of beginning and end of sentence markers, minimum Bayes risk decoding, and...

We investigate the application of the co-training learning algorithm on the sentence boundary classification problem by using lexical and prosodic information. Co-training is a semisupervised machine learning algorithm that uses multiple weak classifiers with a relatively small amount of labeled data and incrementally uses unlabeled data. The assumption in cotraining is that the classifiers can...

A novel approach utilized in video database objectbased queries is proposed. This new method segments an example video sequence into real world objects using a combination of color image segmentation techniques along with MPEG-1/2 motion vectors. First, the initial frame in the sequence undergoes a color/texture segmentation algorithm that divides the frame into homogenous regions of color and ...

The paper presents a learning method, called Iterative Cross-Training (ICT) , for classifying Web pages in two classification problems, i.e., (1) classification of Thai/non-Thai Web pages, and (2) classification of course/non-course home pages. Given domain knowledge or a small set of labeled data, our method combines two classifiers that are able to effectively use unlabeled examples to iterat...

Recently, texture-based features have been used for digitized historical document image segmentation. It has been proven that these methods work effectively with no a priori knowledge. Moreover, it has been shown that they are robust when they are applied on degraded documents under different noise levels and kinds. In this paper an approach of evaluating CIFED 2014, pp. 41–56, Nancy, 18-21 mar...

The purpose of this work was to apply and test Haralick’s gray level co-occurrence matrix (GLCM) technique for automatic calculation and segmentation of the ischemic stroke volume from CT images. For this task, the 3nearest neighbors classifier was trained to perform stroke and non-stroke area classification. The segmentation and classification results were compared versus a manual segmentation...

This paper develops a new approach to surface modeling and reconstruction which overcomes some important limitations of existing surface representation methods, such as their tendency to impose restrictive assumptions about object topology. The approach features two components. The first is a dynamic, self-organizing, oriented particle system which discovers topological and geometric surface st...

A novel approach identifying and segmenting skin regions within images is presented in this paper. The identification and recognition of facial regions are a central focus of this work. A set of standard images containing facial/skin objects is first manually segmented into the interested regions. These regions are utilized in the training the system. Dominant color features (i.e., the most fre...