Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
The KIPS Transactions:PartB
Journal Basic Information
Journal DOI :
Korea Information Processing Society
Editor in Chief :
Volume & Issues
Volume 12B, Issue 7 - Dec 2005
Volume 12B, Issue 6 - Oct 2005
Volume 12B, Issue 5 - Oct 2005
Volume 12B, Issue 4 - Aug 2005
Volume 12B, Issue 3 - Jun 2005
Volume 12B, Issue 2 - Apr 2005
Volume 12B, Issue 1 - Feb 2005
Selecting the target year
Word Extraction from Table Regions in Document Images
Jeong, Chang-Bu ; Kim, Soo-Hyung ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 369~378
DOI : 10.3745/KIPSTB.2005.12B.4.369
Document image is segmented and classified into text, picture, or table by a document layout analysis, and the words in table regions are significant for keyword spotting because they are more meaningful than the words in other regions. This paper proposes a method to extract words from table regions in document images. As word extraction from table regions is practically regarded extracting words from cell regions composing the table, it is necessary to extract the cell correctly. In the cell extraction module, table frame is extracted first by analyzing connected components, and then the intersection points are extracted from the table frame. We modify the false intersections using the correlation between the neighboring intersections, and extract the cells using the information of intersections. Text regions in the individual cells are located by using the connected components information that was obtained during the cell extraction module, and they are segmented into text lines by using projection profiles. Finally we divide the segmented lines into words using gap clustering and special symbol detection. The experiment performed on In table images that are extracted from Korean documents, and shows
accuracy of word extraction.
Optimum Subband Quantization Filter Design for Image Compression
Park, Kyu-Sik ; Park, Jae-Hyun ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 379~386
DOI : 10.3745/KIPSTB.2005.12B.4.379
This paper provides a rigorous theory for analysis of quantization effects and optimum filter bank design in quantized multidimensional subband filter banks. Even though subband filter design has been a hot topic for last decades, a few results have been reported on the subband filter with a quantizer. Each pdf-optimized quantizer is modeled by a nonlinear gain-plus-additive uncorrelated noise and embedded into the subband structure. Using polyphase decomposition of the analysis/synthesis filter banks, we derive the exact expression for the output mean square quantization error. Based on the minimization of the output mean square error, the technique for optimal filter design methodology is developed. Numerical design examples for optimum nonseparable paraunitary and biorthogonal filter banks are presented with a quincunx subsampling lattice. Through the simulation,
decreases in MSE have been observed compared with subband filter with no quantizers especially for low bit rate cases.
Vision-Based Self-Localization of Autonomous Guided Vehicle Using Landmarks of Colored Pentagons
Kim Youngsam ; Park Eunjong ; Kim Joonchoel ; Lee Joonwhoan ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 387~394
DOI : 10.3745/KIPSTB.2005.12B.4.387
This paper describes an idea for determining self-localization using visual landmark. The critical geometric dimensions of a pentagon are used here to locate the relative position of the mobile robot with respect to the pattern. This method has the advantages of simplicity and flexibility. This pentagon is also provided nth a unique identification, using invariant features and colors that enable the system to find the absolute location of the patterns. This algorithm determines both the correspondence between observed landmarks and a stored sequence, computes the absolute location of the observer using those correspondences, and calculates relative position from a pentagon using its (ive vortices. The algorithm has been implemented and tested. In several trials it computes location accurate to within 5 centimeters in less than 0.3 second.
A New Shadow Removal Method using Color Information and History Data
Choi Hye-Seung ; Wang Akun ; Soh Young-Sung ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 395~402
DOI : 10.3745/KIPSTB.2005.12B.4.395
Object extraction is needed to track objects in color traffic image sequence. To extract objects, we use background differencing method based on MOG(Mixture of Gaussians). In extracted objects, shadows may be included. Due to shadows, we may not find exact location of objects and sometimes we find adjacent objects are glued together. Many methods have been proposed to remove shadows. Conventional methods usually assume that color and texture information are preserved under the shadow. Thus these methods do not work well if these assumptions do not hold. In this paper, we propose a new robust shadow removal method which works well in those situations. First we extract shadow pixel candidates by analysing color information and compute the ratio of shadow pixel candidates over the total number of Pixels. W the ratio is reasonable, we remove shadow candidate Pixels and if not, we use data in history array containing Previous removal records. We applied the method to real color traffic image sequences and obtained good results.
Shot Transition Detection by Compensating Camera Operations
Jang Seok-Woo ; Choi Hyung-Il ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 403~412
DOI : 10.3745/KIPSTB.2005.12B.4.403
In this paper, we propose an effective method for detecting and classifying shot transitions in video sequences. The proposed method detects and classifies shot transitions including cuts, fades and dissolves by compensating camera operations in video sequences, so that our method prevents false positives resulting from camera operations. Also, our method eliminates local moving objects in the process of compensating camera operations, so that our method prevents errors resulting from moving objects. In the experiments, we show that our shot transition approach can work as a promising solution by comparing the proposed method with previously known methods in terms of performance.
A Fuzzy Agent System to Control the State Transition for an Autonomous Decision Making on Taxi Driving
Lim, Chun-Kyu ; Kang, Byung-Wook ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 413~420
DOI : 10.3745/KIPSTB.2005.12B.4.413
In this paper, we apply software agents, which use fuzzy logic and make autonomous decisions according to state transitions, to car driving environment. We carry out an experiment on artificial intelligent car driving in terms of real-time reactive agents. Inference techniques for constructing real-time reactive agents consider the settings with max-product inference, n-fuzzy rules, and n-associatives (
). Then we perform defuzzification processes, extract a central value, and work out inference processes.
Semi-Fragile Image Watermarking for Authentication Using Wavelet Packet Transform Based on The Subband Energy
Park, Sang-Ju ; Kwon, Tae-Hyeon ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 421~428
DOI : 10.3745/KIPSTB.2005.12B.4.421
A new method of Semi-fragile image watermarking which ensures the integrity of the contents of digital image is presented. Proposed watermarking scheme embeds watermark in the form of quantization noise on the wavelet transform coefficients in a specific mid frequency subbands selected from a wavelet packet decomposition based on energy distribution of wavelet transform coefficients. By controlling the strength of embedded watermark using HVS (Human Visual System) characteristic, it is imperceptible by a human viewer while robust against non-malicious attack such as compression for storage and/or transmission. When an attack is applied on the original image, it is highly probable that wavelet transform coefficients not only at the exact attack positions but also the neighboring ones are modified. Therefore, proposed authentication method utilizes whether both current coefficient and its neighbors are damaged. together. So it can efficiently detect and accurately localize attacks inflicted on the content of original image. Decision threshold for authentication can be user controlled for different application areas as needed.
A Simple Stereo Matching Algorithm using PBIL and its Alternative
Han Kyu-Phil ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 429~436
DOI : 10.3745/KIPSTB.2005.12B.4.429
A simple stereo matching algorithm using population-based incremental learning(PBIL) is proposed in this paper to decrease the general problem of genetic algorithms, such as memory consumption and inefficiency of search. PBIL is a variation of genetic algorithms using stochastic search and competitive teaming based on a probability vector. The structure of PBIL is simpler than that of other genetic algorithm families, such as serial and parallel ones, due to the use of a probability vector. The PBIL strategy is simplified and adapted for stereo matching circumstances. Thus, gene pool, chromosome crossover, and gene mutation we removed, while the evolution rule, that fitter chromosomes should have higher survival probabilities, is preserved. As a result, memory space is decreased, matching rules are simplified and computation cost is reduced. In addition, a scheme controlling the distance of neighbors for disparity smoothness is inserted to obtain a wide-area consistency of disparities, like a result of coarse-to-fine matchers. Because of this scheme, the proposed algorithm can produce a stable disparity map with a small fixed-size window. Finally, an alterative version of the proposed algorithm without using probability vector is also presented for simpler set-ups.
Speaker Normalization using Gaussian Mixture Model for Speaker Independent Speech Recognition
Shin, Ok-Keun ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 437~442
DOI : 10.3745/KIPSTB.2005.12B.4.437
For the purpose of speaker normalization in speaker independent speech recognition systems, experiments are conducted on a method based on Gaussian mixture model(GMM). The method, which is an improvement of the previous study based on vector quantizer, consists of modeling the probability distribution of canonical feature vectors by a GMM with an appropriate number of clusters, and of estimating the warp factor of a test speaker by making use of the obtained probabilistic model. The purpose of this study is twofold: improving the existing ML based methods, and comparing the performance of what is called 'soft decision' method with that of the previous study based on vector quantizer. The effectiveness of the proposed method is investigated by recognition experiments on the TIMIT corpus. The experimental results showed that a little improvement could be obtained tv adjusting the number of clusters in GMM appropriately.
Video Fingerprinting System through Zero-based Code Modulation Technique
Choi Sun Young ; Lee Hae-Yeoun ; Kang In Koo ; Lee Heung-Kyu ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 443~450
DOI : 10.3745/KIPSTB.2005.12B.4.443
Digital fingerprinting is a contents-protection technique, where customer information is inserted into digital contents. Fingerprinted contents undergo various attacks. Especially, attackers can remove easily the inserted fingerprint by collusion attacks, because digital fingerprinting inserts slightly different codes according to the customers. Among collusion attacks, averaging attack is a simple, fast, and efficient attack. In this paper, we propose a video fingerprinting system that is robust to the averaging attack. In order to achieve code efficiency and robustness against the averaging attack, we adopt anti-collusion code (fingerprint code) from GD-PBIBD theory. When the number of users is increased, the size of fingerprint code also grows. Thus, this paper addresses a zero-based code modulation technique to embed and detect this fingerprint code efficiently. We implemented a blind video fingerprinting system based on our proposed technique and performed experiments on various colluding cases. Based on the results, we could detect most of colluders. In the worst case, our scheme could trace at least one colluder successfully.
An efficient and Low-Complexity Frame-Skipping Transcoder System Architecture
Kim Sung-Min ; Kim Hyun-Hee ; Park Si-Yong ; Chun Ki-Dong ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 451~458
DOI : 10.3745/KIPSTB.2005.12B.4.451
The transcoding is a solution which is able to adapt to heterogeneous clients of requesting a different playback rate of multimedia data. Thus, The transcoding needs decoding and encoding. In general, previous studies to reduce complexity have a problem, the degradation of visual quality On the contrary, previous studies to reduce the degradation of visual quality lead to heavy computation. Thus, many researchers have studied a solution between the complexity and the degradation of visual quality. But until now, most researches of this region have dealt with the transcoder itself, such researches about a server's assistance to improve the performance of transcoder is rarely studied. In case of servicing multimedia data to heterogeneous clients which have low capabilities, the assistance of server side is able to reduce frames with processing in the transcoder and improve the performance of the transcoder. Thus in this paper, we propose the frame-skipping transcoder system architecture that takes into consideration transcoder and server side to reduce the complexity of the transcoder.
Asymmetric distributed multi server architecture for efficient method of client connection process at online game servers
Hwang Doh-Yeun ; Lee Nam-Jae ; Kwak Hoon-Sung ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 459~464
DOI : 10.3745/KIPSTB.2005.12B.4.459
The online game system could be largely divided into two parts: servers and clients. Clients accesses to a game server and analyzes the packets transmitted from a server. A game server manages users information and database. U a game server allows a new client to access the server to execute a game, it should accept the access request of the new client maintaining the online connection of the existing users. In this paper, we compare Process method and Thread method within the multiple jobs process methods of a server. Then we propose an asymmetric distributed multi server architecture that is adequate to asymmetric distributed architecture that is widely applied to most game servers. The proposed asymmetric distributed multi server architecture includes login server, game server, communication server and database server to perform its own feature independently. Comparing its other architectures, it shows better performance economically and technically. Especially it improves the stability and expandability of a server.
3D First Person Shooting Game by Using Eye Gaze Tracking
Lee, Eui-Chul ; Park, Kang-Ryoung ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 465~472
DOI : 10.3745/KIPSTB.2005.12B.4.465
In this paper, we propose the method of manipulating the gaze direction of 3D FPS game's character by using eye gaze detection from the successive images captured by USB camera, which is attached beneath HMB. The proposed method is composed of 3 parts. At first, we detect user's pupil center by real-time image processing algorithm from the successive input images. In the second part of calibration, when the user gaze on the monitor plane, the geometric relationship between the gazing position of monitor and the detected position of pupil center is determined. In the last part, the final gaze position on the HMD monitor is tracked and the 3D view in game is controlled by the gaze position based on the calibration information. Experimental results show that our method can be used for the handicapped game player who cannot use his(or her) hand. Also, it can Increase the interest and the immersion by synchronizing the gaze direction of game player and the view direction of game character.
Interaction between Information Structure and Menu Design on Information Searching and Attitude in WWW
Yu Byeong-Min ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 473~478
DOI : 10.3745/KIPSTB.2005.12B.4.473
The purpose of this study was to investigate the interaction effect of Web site menu designs and information structures on two information searching performances (searching and browsing) and three measures of users' attitudes (appeal, usability, and disorientation). Pronounced interaction effects occurred across four dependent variables except searching when decreasing and increasing information structure were combined with a simple selection menu and a pull-down menu. Further studies are needed to investigate additional interactions among factors of interface and information structure of Web sites.
A Statistical Approach for Extracting and Miming Relation between Concepts
Kim Hee-soo ; Choi Ikkyu ; Kim Minkoo ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 479~486
DOI : 10.3745/KIPSTB.2005.12B.4.479
The ontology was proposed to construct the logical basis of semantic web. Ontology represents domain knowledge in the formal form and it enables that machine understand domain knowledge and provide appropriate intelligent service for user request. However, the construction and the maintenance of ontology requires large amount of cost and human efforts. This paper proposes an automatic ontology construction method for defining relation between concepts in the documents. The Proposed method works as following steps. First we find concept pairs which compose association rule based on the concepts in domain specific documents. Next, we find pattern that describes the relation between concepts by clustering the context between two concepts composing association rule. Last, find generalized pattern name by clustering the clustered patterns. To verify the proposed method, we extract relation between concepts and evaluate the result using documents set provide by TREC(Text Retrieval Conference). The result shows that proposed method cant provide useful information that describes relation between concepts.
Incremental Generation of A Decision Tree Using Global Discretization For Large Data
Han, Kyong-Sik ; Lee, Soo-Won ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 487~498
DOI : 10.3745/KIPSTB.2005.12B.4.487
Recently, It has focused on decision tree algorithm that can handle large dataset. However, because most of these algorithms for large datasets process data in a batch mode, if new data is added, they have to rebuild the tree from scratch. h more efficient approach to reducing the cost problem of rebuilding is an approach that builds a tree incrementally. Representative algorithms for incremental tree construction methods are BOAT and ITI and most of these algorithms use a local discretization method to handle the numeric data type. However, because a discretization requires sorted numeric data in situation of processing large data sets, a global discretization method that sorts all data only once is more suitable than a local discretization method that sorts in every node. This paper proposes an incremental tree construction method that efficiently rebuilds a tree using a global discretization method to handle the numeric data type. When new data is added, new categories influenced by the data should be recreated, and then the tree structure should be changed in accordance with category changes. This paper proposes a method that extracts sample points and performs discretiration from these sample points to recreate categories efficiently and uses confidence intervals and a tree restructuring method to adjust tree structure to category changes. In this study, an experiment using people database was made to compare the proposed method with the existing one that uses a local discretization.
A Design and Implementation of Web Robot by Using Genre-based Categorization and Subject-based Categorization
Lee Yong-Bae ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 499~506
DOI : 10.3745/KIPSTB.2005.12B.4.499
It still has some restrictions to collect a specialized information with only the function of existing web robot which collect an enormous of data by circulating through the internet. Therefore, in this paper the functions of the current web robot and its application areas are analyzed and the limitations of collecting a specialized information are found out. Also we define what functions are necessary for a web robot in order to collect a specialized information. Then the designed structure is described. There are two critical functions which are applied to web robot. One is a genre-based categorization that classifies the text by the type, and the other is a content-based categorization by the subject. Most of all, genre-based categorization is used as fundamental feature which enables web robot to collect the aimed documents efficiently.
Hangul Vowel Input System for Electronic Networking Devices
Kang Seung-Shik ; Hahn Kwang-Soo ;
The KIPS Transactions:PartB, volume 12B, issue 4, 2005, Pages 507~512
DOI : 10.3745/KIPSTB.2005.12B.4.507
There is a limitation of using a small number of input buttons for writing Hangul words on hand-held devices. As a quick and convenient way of implementing Hangul vowels by small number of buttons, we propose a vowel input system in which vowels are fabricated from eight vowels. Our input system supports a fast input speed by making all the diphthong from one or two strokes. It also adopts a multiple input method for diphthong that users can make a diphthong in a user-friendly way of vowel writing formation or pronunciation similarity. Furthermore, we added an error correction functionality for the similar vowels that are caused by vowel harmony rules. When the proposed method is compared to the previous ones, our method outperformed in the input speed and error correction.