Nuo Zhang

Image representation and classification based on data compression

With the development of the information technology, the number of different electronic information has been increased rapidly. In which, for enormous number of digital images the demand of automatic classification technology exceeded human processing capacity. As an automatic classification technique, representing and classifying text-transformed image based on data compression is proposed in this paper. In the step of transforming image into text, image is divided into segments which are replaced as characters. Then, the similarity between compressibility vectors is used in the classification step. In which, we focus on the compressibility of the text string. Finally, the effectivity of the proposed method is verified in our experiments.

A Novel Document Analysis Method Using Compressibility Vector

Similarity analysis and keyword extraction are widely used as document relation analysis techniques. These methods are based on dictionary-base morphological analysis. However, they cannot meet the need when Internet grows fast and new words appear but dictionary can not be renewed fast enough. In this study, we propose a new document relation analysis method based on the documents compressibility. The effectiveness of the proposed method will be examined in simulations.

Text-Transformed Image Classification Based on Data Compression

Image data analysis technology occupies an important position in processing multimedia information. Due to the wide usage of digital images, automatic classification technology with high capacity is necessary for processing enormous number of digital images. In this paper, we propose an automatic classification technique which representing text-transformed image based on data compression. Images are first transformed into texts, which are then divided into segments and replaced by characters. Then, instead of using texts themselves, the similarity between compressibility vectors of texts are used in the classification step, in which we focus on the compressibility of the text string. Finally, the effectivity of the proposed method is verified in our experiments.

Image Feature Description by Frequent Patterns

The classification of image data becomes important, due to the increasing application of digital images, unsupervised classification technology with high capacity is necessary for processing digital images. In this paper, we propose an unsupervised approach of image pattern description and classification. In order to collect frequently appeared patterns in images, a compressibility feature space is built in an unsupervised manner. Based on this feature space the proposed approach transforms images to sequences, which are then divided into segments and replaced by characters. Finally, the similarities among compressibility vectors of texts are used for classification, instead of using texts themselves. Our experiments showed that the proposed approach is effective.

Texture image description based on data compression

Texture analysis is important in many application fields in image processing. There are four domains, texture classification, texture segmentation, texture synthesis and shape from texture, in texture analysis. Generally, there are two phrases in texture classification process: the learning phase and the recognition phase. In this study, we introduce an approach for texture classification. Our approach is based on the consideration of searching the essential feature of frequent pattern in texture images, and the learning phase is not necessary. To find out the frequent pattern in a texture image, data compression is used in our approach. Data compression helps us to extract the longest and frequent features, without complicated computation, in out approach. The simulation results will show good performance of our approach.

Documents Clustering Based on Optimized Compressibility Vector Space

To access and store large-scale electrical documents becomes possible due to the high performance of computer hardware and broadband accessible network. In order to handle these increasing number of documents properly, a efficient doc- ument representation model is as important as the classification algorithms. Several text representation methods, such as bag- of-words and N-gram models, have been widely used. Another representation approach named pattern representation scheme using data compression (PRDC) has been proposed lately. It does not only independently process data of linguistic text, but also processes multimedia data effectively. In this study, we will propose a method to improve PRDC approach and compare it with the two aforementioned methods. The performances will be compared in terms of clustering ability. Experiment results will show that the proposed method can provide better performance than that of the other two methods and also the PRDC.