• Journal of information and communication convergence engineering
• /
• v.15 no.1
• /
• pp.53-61
• /
• 2017

The preferred feature selection methods for text classification are filter-based. In a common filter-based feature selection scheme, unique scores are assigned to features; then, these features are sorted according to their scores. The last step is to add the top-N features to the feature set. In this paper, we propose an improved global feature selection scheme wherein its last step is modified to obtain a more representative feature set. The proposed method aims to improve the classification performance of global feature selection methods by creating a feature set representing all classes almost equally. For this purpose, a local feature selection method is used in the proposed method to label features according to their discriminative power on classes; these labels are used while producing the feature sets. Experimental results obtained using the well-known 20 Newsgroups and Reuters-21578 datasets with the k-nearest neighbor algorithm and a support vector machine indicate that the proposed method improves the classification performance in terms of a widely known metric ($F_1$).

• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.498-504
• /
• 2004

This paper presents a new text classifier based on a feature projection technique. In feature projections, training documents are represented as the projections on each feature. A classification process is based on individual feature projections. The final classification is determined by the sum from the individual classification of each feature. In our experiments, the proposed classifier showed high performance. Especially, it have fast execution speed and robustness with noisy data in comparison with k-NN and SVM, which are among the state-of-art text classifiers. Since the algorithm of the proposed classifier is very simple, its implementation and training process can be done very simply. Therefore, it can be a useful classifier in text classification tasks which need fast execution speed, robustness, and high performance.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.359-362
• /
• 2002

In this paper, we propose a new feature-based text watermarking for the binary text image. The structure of specific characters from preprocessed text image are modified to embed watermark. Watermark message are embedded and detected by the following method; Hole line disconnect using the connectivity of the character containing a hole, Center line shift using the hole area and Differential encoding using difference of flippable score points. Experimental results show that the proposed method is robust to rotation and scaling distortion.

• Journal of Information Processing Systems
• /
• v.4 no.2
• /
• pp.77-86
• /
• 2008

This research proposes a new neural network for text categorization which uses alternative representations of documents to numerical vectors. Since the proposed neural network is intended originally only for text categorization, it is called NTC (Neural Text Categorizer) in this research. Numerical vectors representing documents for tasks of text mining have inherently two main problems: huge dimensionality and sparse distribution. Although many various feature selection methods are developed to address the first problem, the reduced dimension remains still large. If the dimension is reduced excessively by a feature selection method, robustness of text categorization is degraded. Even if SVM (Support Vector Machine) is tolerable to huge dimensionality, it is not so to the second problem. The goal of this research is to address the two problems at same time by proposing a new representation of documents and a new neural network using the representation for its input vector.

• International Journal of Contents
• /
• v.13 no.4
• /
• pp.70-79
• /
• 2017

Images are an important element in patents and many experts use images to analyze a patent or to check differences between patents. However, there is little research on image analysis for patents partly because image processing is an advanced technology and typically patent images consist of visual parts as well as of text and numbers. This study suggests two methods for using image processing; the Scale Invariant Feature Transform(SIFT) algorithm and Optical Character Recognition(OCR). The first method which works with SIFT uses image feature points. Through feature matching, it can be applied to calculate the similarity between documents containing these images. And in the second method, OCR is used to extract text from the images. By using numbers which are extracted from an image, it is possible to extract the corresponding related text within the text passages. Subsequently, document similarity can be calculated based on the extracted text. Through comparing the suggested methods and an existing method based only on text for calculating the similarity, the feasibility is achieved. Additionally, the correlation between both the similarity measures is low which shows that they capture different aspects of the patent content.

• International Journal of Contents
• /
• v.8 no.1
• /
• pp.30-38
• /
• 2012

Text extraction and binarization are the important pre-processing steps for text recognition. The performance of text binarization strongly related to the accuracy of recognition stage. In our proposed method, the first stage based on line detection and shape feature analysis applied to locate the position of a business card and detect the shape from the complex environment. In the second stage, several local regions contained the possible text components are separated based on the projection histogram. In each local region, the pixels grouped into several connected components based on the connected component labeling and projection histogram. Then, classify each connect component into text region and reject the non-text region based on the feature information analysis such as size of connected component and stroke width estimation.

• KIISE Transactions on Computing Practices
• /
• v.23 no.5
• /
• pp.322-327
• /
• 2017

The classification problem in the field of Natural Language Processing has been studied for a long time. Continuing forward with our previous research, which classifies large-scale text using Convolutional Neural Networks (CNN), we implemented Recurrent Neural Networks (RNN), Long-Short Term Memory (LSTM) and Gated Recurrent Units (GRU). The experiment's result revealed that the performance of classification algorithms was Multinomial Naïve Bayesian Classifier < Support Vector Machine (SVM) < LSTM < CNN < GRU, in order. The result can be interpreted as follows: First, the result of CNN was better than LSTM. Therefore, the text classification problem might be related more to feature extraction problem than to natural language understanding problems. Second, judging from the results the GRU showed better performance in feature extraction than LSTM. Finally, the result that the GRU was better than CNN implies that text classification algorithms should consider feature extraction and sequential information. We presented the results of fine-tuning in deep neural networks to provide some intuition regard natural language processing to future researchers.

• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.4
• /
• pp.381-388
• /
• 2015

The rapid growth of the World Wide Web and online information services has generated and made accessible a huge number of text documents. To analyze texts, selecting important keywords is an essential step. In this paper, we propose a feature selection method that combines a term frequency-inverse document frequency technique and symmetrical conditional probability. The proposed method can identify features with N-gram, the sequential multiword. The effectiveness of the proposed method is demonstrated through a real text data from the machine learning repository, University of California, Irvine.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.10
• /
• pp.104-111
• /
• 1997

It is known as a difficult problem to recognize text-background mixed documents. In this paper a new string extraction algorithm, using mathematical morphology for the document consisting of text and overlapped periodic background pattern, is proposed. The algorithm consists of pattern periodicity feature extraction and background removal. The extracted pattern periodicity feature is used to determine the shape of structuring elements for morphological pre- and post-processing to remove background. The effectiveness of the proposed algorithm over the existing one is also verified through the experiments with various test documents.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.3 no.3
• /
• pp.285-307
• /
• 2009

This paper introduces DICE, a Domain-Independent text Classification Engine. DICE is robust, efficient, and domain-independent in terms of software and architecture. Each module of the system is clearly modularized and encapsulated for extensibility. The clear modular architecture allows for simple and continuous verification and facilitates changes in multiple cycles, even after its major development period is complete. Those who want to make use of DICE can easily implement their ideas on this test bed and optimize it for a particular domain by simply adjusting the configuration file. Unlike other publically available tool kits or development environments targeted at general purpose classification models, DICE specializes in text classification with a number of useful functions specific to it. This paper focuses on the ways to locate the optimal states of a practical text classification framework by using various adaptation methods provided by the system such as feature selection, lemmatization, and classification models.