• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1833-1848
• /
• 2022

Named entity recognition (NER) is an important basic task in the field of Natural Language Processing (NLP). Recently deep learning approaches by extracting word segmentation or character features have been proved to be effective for Chinese Named Entity Recognition (CNER). However, since this method of extracting features only focuses on extracting some of the features, it lacks textual information mining from multiple perspectives and dimensions, resulting in the model not being able to fully capture semantic features. To tackle this problem, we propose a novel Multi-view Semantic Feature Fusion Model (MSFM). The proposed model mainly consists of two core components, that is, Multi-view Semantic Feature Fusion Embedding Module (MFEM) and Multi-head Self-Attention Mechanism Module (MSAM). Specifically, the MFEM extracts character features, word boundary features, radical features, and pinyin features of Chinese characters. The acquired font shape, font sound, and font meaning features are fused to enhance the semantic information of Chinese characters with different granularities. Moreover, the MSAM is used to capture the dependencies between characters in a multi-dimensional subspace to better understand the semantic features of the context. Extensive experimental results on four benchmark datasets show that our method improves the overall performance of the CNER model.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.151-154
• /
• 2008

In this paper, this program which is Retrieval System using Image Gray-scale histogram and Edge features is used to reduce the errors incurred by inputting methods which are used in a current Retrieval System. The Retrieval Algorithm is proceeding with several steps which are extracting features of images quality, extracting edge features and refining images, analysing extracted features, retaining important information from analyzed features, retrieving retained information from database, extracting and comparing among images from retrieved database. The proposed Retrieval System is used for a fast retrieval with accuracy and it is confirmed through simulations.

• Proceedings of the IEEK Conference
• /
• 2000.11d
• /
• pp.65-68
• /
• 2000

This paper describes an approach for extracting invariant features using a view-based representation and recognizing an object with a high speed search method in FLIR. In this paper, we use a reformulated eigenspace technique based on robust estimation for extracting features which are robust for outlier such as noise and clutter. After extracting feature, we recognize an object using a partial distance search method for calculating Euclidean distance. The experimental results show that the proposed method achieves the improvement of recognition rate compared with standard PCA.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.2
• /
• pp.373-380
• /
• 1994

In this paper, we proposed a method of extracting optimum features of speech signal to adjust signal level. For extracting features of speech signal we used FRLS(Fast Recursive Least Square) algorithm, we adjusted each frames of equal to constant level, and extracted optimum features of speech signal by using equalized autocorrelation function proposed in this paper.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.5
• /
• pp.559-565
• /
• 1988

A new valley operator is presented for extracting sketch features which contain valleys and edges subject to local intensities. It is a very simple operator using the local probablities in a 3x3 local window. Experimental results show its excellent performance over the existing valley or edge operators.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.181-183
• /
• 2006

Digital topographic map in Korea contains layers of spatial and attribute data for 8 land features such as railroads, watercourses, roads, buildings and etc. Some of the layers such as building and forest don't include any information about height, which can be just prepared by interpretation of remote sensed data or field survey. LiDAR(Light Detection And Ranging) data using active pulse and digital camera provides data about height and form of land features. LiDAR data can be used not only to extract the outline of land features but also to estimate the height. This study presents technical availability for extraction and estimation of land feature's outline and height using LiDAR data which composes of natural and artificial land features, and digital aerial photograph which was taken simultaneously with the LiDAR. The estimated location, outline and height of land features were compared with the field survey data, and we could find that LiDAR data and digital aerial photograph can be a useful source for estimating the height of land features as well as extracting the outline.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.773-779
• /
• 1996

Dried oak mushroom have complex and various visual features. Grading and sorting of dried oak mushrooms has been done by the human expert. Though actions involved in human grading looked simple, a decision making underneath the simple action comes from the result of the complex neural processing of the visual image. Through processing details involved in human visual recognition has not been fully investigated yet, it might say human can recognize objects via one of three ways such as extracting specific features or just image itself without extracting those features or in a combined manner. In most cases, extracting some special quantitative features from the camera image requires complex algorithms and processing of the gray level image requires the heavy computing load. This fact can be worse especially in dealing with nonuniform, irregular and fuzzy shaped agricultural products, resulting in poor performance because of the sensitiveness to the crisp criteria or specific ules set up by algorithms. Also restriction of the real time processing often forces to use binary segmentation but in that case some important information of the object can be lost. In this paper, the neuro net based real time recognition algorithm was proposed without extracting any visual feature but using only the directly captured raw gray images. Specially formated adaptable size of grids was proposed for the network input. The compensation of illumination was also done to accomodate the variable lighting environment. The proposed grading scheme showed very successful results.

• Proceedings of the IEEK Conference
• /
• 2001.06c
• /
• pp.77-80
• /
• 2001

In general, the informations of the inner image that user interested in are limited to a special domain. In this paper, as using Wavelet Transform for dividing image into high frequency and low frequency, We can separate foreground including many data. After calculating object boundary of separated part, We extract special features using Color Coherence Vector. According to results of this experiment, the method of comparing data extracting foreground features is more effective than comparing data extracting features of entire image when we extract the image user interested in.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.04a
• /
• pp.328-331
• /
• 2000

In this paper , we propose a texture feature extraction method of reduce the massive computational time on extracting texture, features of large sized medical such as MRI, CT-scan , and an index structure, called GLTFT, to speed up the retrieval performance. For these, the original image is transformed into a compressed image by Wavelet transform , and textural features such as contrast, energy, entropy, and homogeneity of the compressed image is extracted by using GLCM(Gray Level Co-occurrence Metrix) . The proposed index structure is organized by using the textural features. The processing in compressed domain can give the solution of storage space and the reduction of computational time of feature extracting . And , by GLTFT index structure, image retrieval performance can be expected to be improved by reducing the retrieval range . Our experiment on 270 MRIs as image database shows that shows that such expectation can be got.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1607-1615
• /
• 1996

A new simply computable operator named DBAH(difference between arithmetic mean and mean)and fuzzy reasoning technique of local thresholds for extracting sketch features are proposed in this paper.The DBAH operator provides some advantages, for example dependence on local intensities and small reponses with small rates of intensity change in very dark regions. Also, the proposed fuzzy reasoning technique has a good performance extracting sketch features without human intervention.