• Smart Media Journal
• /
• v.8 no.2
• /
• pp.58-65
• /
• 2019

Automatic text summarization is a process of shortening a text document by either extraction or abstraction. The abstraction approach inspired by deep learning methods scaling to a large amount of document is applied in recent work. Abstractive text summarization involves utilizing pre-generated word embedding information. Low-frequent but salient words such as terminologies are seldom included to dictionaries, that are so called, out-of-vocabulary(OOV) problems. OOV deteriorates the performance of Encoder-Decoder model in neural network. In order to address OOV words in abstractive text summarization, we propose a copy mechanism to facilitate copying new words in the target document and generating summary sentences. Different from the previous studies, the proposed approach combines accurate pointing information and selective copy mechanism based on bidirectional RNN and bidirectional LSTM. In addition, neural network gate model to estimate the generation probability and the loss function to optimize the entire abstraction model has been applied. The dataset has been constructed from the collection of abstractions and titles of journal articles. Experimental results demonstrate that both ROUGE-1 (based on word recall) and ROUGE-L (employed longest common subsequence) of the proposed Encoding-Decoding model have been improved to 47.01 and 29.55, respectively.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.2
• /
• pp.31-43
• /
• 2000

This paper presents a novel algorithm lot extraction of the eye and mouth fields (facial features) from 2D gray level face images. First of all, it has been found that Eigenfeatures, derived from the eigenvalues and the eigenvectors of the binary edge data set constructed from the eye and mouth fields are very good features to locate these fields. The Eigenfeatures, extracted from the positive and negative training samples for the facial features, ate used to train a MultiLayer Perceptron(MLP) whose output indicates the degree to which a particular image window contains the eye or the mouth within itself. Second, to ensure robustness, the ensemble network consisting of multiple MLPs is used instead of a single MLP. The output of the ensemble network becomes the average of the multiple locations of the field each found by the constituent MLPs. Finally, in order to reduce the computation time, we extracted the coarse search region lot eyes and mouth by using prior information on face images. The advantages of the proposed approach includes that only a small number of frontal faces are sufficient to train the nets and furthermore, lends themselves to good generalization to non-frontal poses and even to other people's faces. It was also experimentally verified that the proposed algorithm is robust against slight variations of facial size and pose due to the generalization characteristics of neural networks.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.6
• /
• pp.123-131
• /
• 2008

In Oriental medicine, the status of a tongue is the important indicator to diagnose the condition of one's health like the physiological and the clinicopathological changes of internal organs in a body. A tongue diagnosis is not only convenient but also non-invasive, and therefore widely used in Oriental medicine. However, the tongue diagnosis is affected by examination circumstances like a light source, patient's posture, and doctor's condition a lot. To develop an automatic tongue diagnosis system for an objective and standardized diagnosis, segmenting a tongue region from a facial image captured and classifying tongue coating are inevitable but difficult since the colors of a tongue, lips, and skin in a mouth are similar. The proposed method includes preprocessing, over-segmenting, detecting the edge with a local minimum over a shading area from the structure of a tongue, correcting local minima or detecting the edge with the greatest color difference, selecting one edge to correspond to a tongue shape, and smoothing edges, where preprocessing consists of down-sampling to reduce computation time, histogram equalization, and edge enhancement, which produces the region of a segmented tongue. Finally, the systematic procedure separated only a tongue region from a face image with a tongue, which was obtained from a digital tongue diagnosis system. Oriental medical doctors' evaluation for the results illustrated that the segmented region excluding a non-tongue region provides important information for the accurate diagnosis. The proposed method can be used for an objective and standardized diagnosis and for an u-Healthcare system.

• Journal of KIISE:Databases
• /
• v.33 no.5
• /
• pp.526-537
• /
• 2006

The most representative approach for efficient storing of XML data is to store XML data in relational databases. The merit of this approach is that it can easily accept the realistic status that most data are still stored in relational databases. This approach needs to convert XML data into relational data or relational data into XML data. The most important issue in the translation is to reflect structural and semantic relations of RDB to XML schema model exactly. Many studies have been done to resolve the issue, but those methods have several problems: Not cover structural semantics or just support explicit referential integrity relations. In this paper, we propose an algorithm for extracting implicit referential integrities automatically. We also design and implement the suggested algorithm, and execute comparative evaluations using translated XML documents. The proposed algorithm provides several good points such as improving semantic information extraction and conversion, securing sufficient referential integrity of the target databases, and so on. By using the suggested algorithm, we can guarantee not only explicit referential integrities but also implicit referential integrities of the initial relational schema model completely. That is, we can create more exact XML schema model through the suggested algorithm.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.3 s.303
• /
• pp.73-80
• /
• 2005

Recently there have been many efforts to support searching and browsing based on the visual content of image and multimedia data. Most existing approaches to content-based image retrieval rely on query by example or user based low-level features such as color, shape, texture. But these methods of query are not easy to use and restrict. In this paper we propose a method for automatic color object extraction and labelling to support multiple queries of content-based image retrieval system. These approaches simplify the regions within images using single colorizing algorithm and extract color object using proposed Color and Spatial based Binary tree map(CSB tree map). And by searching over a large of number of processed regions, a index for the database is created by using proposed labelling method. This allows very fast indexing of the image by color contents of the images and spatial attributes. Futhermore, information about the labelled regions, such as the color set, size, and location, enables variable multiple queries that combine both color content and spatial relationships of regions. We proved our proposed system to be high performance through experiment comparable with another algorithm using 'Washington' image database.

• Journal of Korea Spatial Information System Society
• /
• v.1 no.1 s.1
• /
• pp.5-18
• /
• 1999

Recently, the necessity of automatic knowledge extraction from spatial data stored in spatial databases has been increased. Spatial data mining can be defined as the extraction of implicit knowledge, spatial relationships, or other knowledge not explicitly stored in spatial databases. In order to extract useful knowledge from spatial data, an object management system that can store spatial data efficiently, provide very fast indexing & searching mechanisms, and support a distributed computing environment is needed. In this paper, we designed and implemented an open object management system for spatial data mining, that supports efficient management of spatial, aspatial, and knowledge data. In order to develop this system, we used Open OODB that is a widely used object management system. However, the lark of facilities for spatial data mining in Open OODB, we extended it to support spatial data type, dynamic class generation, object-oriented inheritance, spatial index, spatial operations, etc. In addition, for further increasement of interoperability with other spatial database management systems or data mining systems, we adopted international standards such as ODMG 2.0 for data modeling, SDTS(Spatial Data Transfer Standard) for modeling and exchanging spatial data, and OpenGIS Simple Features Specification for CORBA for connecting clients and servers efficiently.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.11
• /
• pp.31-39
• /
• 2010

In some image processing system or the users who want to see a specific region of image simply, if a part of the image has higher quality than other regions, it would be a nice service. Specifically in mobile environments, preferential service was needed, as the screen size is small. So, JPEG2000 supplies this function. But this doesn't support the process to extract specific regions or service and does the functions to add some techniques. It is called by ROI(Region-of-Interest). In this paper, we use images including human faces, which are processed most preferentially and compressed with high quality. Before an image is served to the users, it is compressed and saved. Here, the face parts are compressed with higher quality than the background which are relatively with lower quality. This technique can offer better service with preferential transferring of the faces, too. Besides, whole regions of the image are compressed with same quality and after searching the faces, they can be preferentially transferred. In this paper, we use a face extraction approach based on neural network and the preferential processing with EBCOT of JPEG2000. For experimentation, we use images having several human faces and evaluate objectively and subjectively, and proved that this approach is a nice one.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.95-102
• /
• 2005

In this paper, we propose a user friendly object-based image retrieval system using the interaction between cortex and hippocampus. Most existing ways of queries in content-based image retrieval rely on query by example or query by sketch. But these methods of queries are not adequate to needs of people's various queries because they are not easy for people to use and restrict. We propose a method of automatic color object extraction using CSB tree map(Color and Spatial based Binary をn map). Extracted objects were transformed to bit stream representing information such as color, size and location by region labelling algorithm and they are learned by the hippocampal neural network using the interplay between cortex and hippocampus. The cells of exciting at peculiar features in brain generate the special sign when people recognize some patterns. The existing neural networks treat each attribute of features evenly. Proposed hippocampal neural network makes an adaptive fast content-based image retrieval system using excitatory learning method that forwards important features to long-term memories and inhibitory teaming method that forwards unimportant features to short-term memories controlled by impression.

• Journal of the Korean Society for information Management
• /
• v.27 no.4
• /
• pp.33-47
• /
• 2010

The growth of IT technology and the popularity of network based information sharing increase the number of digital contents in military area. Thus, there arise issues of finding suitable public information with the growing number of long-term preservation of digital public information. According to the source of raw data and the time of compilation may be variable and there can be existed in many correlations about digital contents. The business service ontology makes knowledge explicit and allows for knowledge sharing among information provider and information consumer for public digital archive engaged in improving the searching ability of digital public information. The business service ontology is at the interface as a bridge between information provider and information consumer. However, according to the difficulty of semantic knowledge extraction for the business process analysis, it is hard to realize the automation of constructing business service ontology for mapping from unformed activities to a unit of business service. To solve the problem, we propose a new business service auto-acquisition method for the first step of constructing a business service ontology based on Enterprise Architecture.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1135-1147
• /
• 2021

In order to geometrically correct high-resolution satellite imagery, the sensor modeling process that restores the geometric relationship between the satellite sensor and the ground surface at the image acquisition time is required. In general, high-resolution satellites provide RPC (Rational Polynomial Coefficient) information, but the vendor-provided RPC includes geometric distortion caused by the position and orientation of the satellite sensor. GCP (Ground Control Point) is generally used to correct the RPC errors. The representative method of acquiring GCP is field survey to obtain accurate ground coordinates. However, it is difficult to find the GCP in the satellite image due to the quality of the image, land cover change, relief displacement, etc. By using image maps acquired from various sensors as reference data, it is possible to automate the collection of GCP through the image matching algorithm. In this study, the RPC of KOMPSAT-3A satellite image was corrected through the extracted matching point using the UAV (Unmanned Aerial Vehichle) imagery. We propose a pre-porocessing method for the extraction of matching points between the UAV imagery and KOMPSAT-3A satellite image. To this end, the characteristics of matching points extracted by independently applying the SURF (Speeded-Up Robust Features) and the phase correlation, which are representative feature-based matching method and area-based matching method, respectively, were compared. The RPC adjustment parameters were calculated using the matching points extracted through each algorithm. In order to verify the performance and usability of the proposed method, it was compared with the GCP-based RPC correction result. The GCP-based method showed an improvement of correction accuracy by 2.14 pixels for the sample and 5.43 pixelsfor the line compared to the vendor-provided RPC. In the proposed method using SURF and phase correlation methods, the accuracy of sample was improved by 0.83 pixels and 1.49 pixels, and that of line wasimproved by 4.81 pixels and 5.19 pixels, respectively, compared to the vendor-provided RPC. Through the experimental results, the proposed method using the UAV imagery presented the possibility as an alternative to the GCP-based method for the RPC correction.