• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.11
• /
• pp.2271-2283
• /
• 2015

In this paper, we propose a method which infers an accurate disparity map for radiometrically varying stereo images. For this end, firstly, we transform the input color images to the log-chromaticity color space from which a linear relationship can be established during constructing a joint pdf between input stereo images. Based on this linear property, we present a new stereo matching cost by combining weighted mutual information and the SIFT (Scale Invariant Feature Transform) descriptor with segment-based plane-fitting constraints to robustly find correspondences for stereo image pairs which undergo radiometric variations. Experimental results show that our method outperforms previous methods and produces accurate disparity maps even for stereo images with severe radiometric differences.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.509-516
• /
• 2004

Semantic interpretation of image is incomplete without some mechanism for understanding semantic content that is not directly visible. For this reason, human assisted content-annotation through natural language is an attachment of textual description to image. However, keyword-based retrieval is in the level of syntactic pattern matching. In other words, dissimilarity computation among terms is usually done by using string matching not concept matching. In this paper, we propose a method for computerized semantic similarity calculation In WordNet space. We consider the edge, depth, link type and density as well as existence of common ancestors. Also, we have introduced method that applied similarity measurement on semantic image retrieval. To combine wi#h the low level features, we use the spatial color distribution model. When tested on a image set of Microsoft's 'Design Gallery Line', proposed method outperforms other approach.

• Journal of Korea Multimedia Society
• /
• v.12 no.11
• /
• pp.1572-1580
• /
• 2009

Combing through entire video files for the purpose of recognizing and retrieving matching movies requires much time and memory space. Instead, most current similar movie-matching methods choose to analyze only a part of each movie's video-image information. Yet, these methods still share a critical problem of erroneously recognizing as being different matching videos that have been altered only in resolution or converted merely with a different codecs. This paper proposes an audio-information-based search algorithm by which similar movies can be identified. The proposed method prepares and searches through a database of movie's spectral peak information that remains relatively steady even with changes in the bit-rate, codecs, or sample-rate. The method showed a 92.1% search success rate, given a set of 1,000 video files whose audio-bit-rate had been altered or were purposefully written in a different codec.

• Korean Journal of Remote Sensing
• /
• v.27 no.1
• /
• pp.51-58
• /
• 2011

Accurate DEM(Digital Elevation Model) generation using satellite images is an active research topic. This paper focuses on generation of a DEM with multiple Kompsat-2 images. For DEM generation, we applied an orbit-attitude sensor model and a RPM sensor model to stereo and multiple Kompsat-2 images respectively. For matching, we used an object-space based matching method. Through the result of this experiment, we could confirm that the sensor model from multiple images is more accurate than the model from stereo images. Also DEM from multiple images gave much better performance than DEM from stereo images.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.7
• /
• pp.1339-1346
• /
• 2015

The traffic identification is a preliminary and essential step for stable network service provision and efficient network resource management. While a number of identification methods have been introduced in literature, the payload signature-based identification method shows the highest performance in terms of accuracy, completeness, and practicality. However, the payload signature-based method's processing speed is much slower than other identification method such as header-based and statistical methods. In this paper, we first classifies signatures by matching type based on range, order, and direction of packet in a flow which was automatically extracted. By using this classification, we suggest a novel method to improve processing speed of payload signature-based identification by reducing searching space.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.5
• /
• pp.455-461
• /
• 2002

This paper presents a method that improves the performance of the personal voice dialling system in which speaker independent phoneme HMM's are used. Since the speaker independent phoneme HMM based voice dialing system uses only the phone transcription of the input sentence, the storage space could be reduced greatly. However, the performance of the system is worse than that of the system which uses the speaker dependent models due to the phone recognition errors generated when the speaker independent models are used. In order to solve this problem, a new method that jointly estimates transformation vectors for the speaker adaptation and transcriptions from training utterances is presented. The biases and transcriptions are estimated iteratively from the training data of each user with maximum likelihood approach to the stochastic matching using speaker-independent phone models. Experimental result shows that the proposed method is superior to the conventional method which used transcriptions only.

• Spatial Information Research
• /
• v.19 no.2
• /
• pp.37-46
• /
• 2011

Recently in the field of GIS(Geographic Information System), data integration from various sources has become an important topic in order to use spatial data effectively. In general, the integration of spatial data is accomplished by navigating corresponding space object and combining the information interacting with each object. But it is very difficult to navigate an object which has correspondence with one in another dataset. Many matching methods have been studied for navigating spatial object. The purpose of this paper is development of method for searching correspondent spatial object considering local position error which is remained even after coordinate transform ation when two different building data sets integrated. To achieve this goal, we performed coordinate transformation and overlapped two data sets and generated blocks which have similar position error. We matched building objects within each block using similarity and ICP algorithm. Finally, we tested this method in the aspect of applicability.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.8B
• /
• pp.1506-1517
• /
• 1999

In this paper, we propose two fast block matching algorithm using the distribution of mean absolute difference (MAD) at the search region overlapped with neighbor blocks and pixel subsapmling. The proposed methods use the lower and upper bound of MAD at the overlapped search region which is calculated from the MAD of neighbor block at that search position and MAD between the current block and neighbor block. In the first algorithm, we can reduce the computational complexity by executing the block matching operation at the only necessary search points. That points are selected using the lower bound of MAD. In the second algorithm, we use the statictical distribution of actual MAD which exists between the lower bound and upper bound of MAD. By using the statistical distribution of actual MAD, we can significantly reduce the computational complexity for motion estimation. after striking space key 2 times.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.5
• /
• pp.696-700
• /
• 2007

A new method that improves the performance of the phonetic transcription based speech recognition system is presented with the speaker-independent phonetic recognizer. Since SI phoneme HMM based speech recognition system uses only the phoneme transcription of the input sentence, the storage space could be reduced greatly. However, the performance of the system is worse than that of the speaker dependent system due to the phoneme recognition errors generated from using SI models. A new training method that iteratively estimates the phonetic transcription and transformation vectors is presented to reduce the mismatch between the training utterances and a set of SI models using speaker adaptation techniques. For speaker adaptation the stochastic matching methods are used to estimate the transformation vectors. The experiments performed over actual telephone line shows that a reduction of about 45% in the error rates could be achieved as compared to the conventional method.

• Korean Journal of Remote Sensing
• /
• v.37 no.1
• /
• pp.169-176
• /
• 2021

The Global Space-based Inter-Calibration System (GSICS) is an international partnership sponsored by World Meteorological Organization (WMO) to continue and improve climate monitoring and to ensure consistent accuracy between observation data from meteorological satellites operating around the world. The objective for GSICS is to inter-calibration from pairs of satellites observations, which includes direct comparison of collocated Geostationary Earth Orbit (GEO)-Low Earth Orbit (LEO) observations. One of the GSICS inter-calibration methods, the Ray-matching technique, is a surrogate approach that uses matched, co-angled and co-located pixels to transfer the calibration from a well calibrated satellite sensor to another sensor. In Korea, the first GEO satellite, Communication Ocean and Meteorological Satellite (COMS), is used to participate in the GSICS program. The National Meteorological Satellite Center (NMSC), which operated COMS/MI, calculated the Radiative Transfer Model (RTM)-based GSICS coefficient coefficients. The L1P reproduced through GSICS correction coefficient showed lower RMSE and Bias than L1B without GSICS correction coefficient applied. The calculation cycles of the GSICS correction coefficients for COMS/MI visible channel are provided annual and diurnal (2, 5, 10, 14-day), but long-term evaluation according to these cycles was not performed. The purpose of this paper is to perform evaluation depending on the annual/diurnal cycles of COMS/MI GSICS correction coefficients based on the ray-matching technique using Suomi-NPP/Visible Infrared Imaging Radiometer Suite (VIIRS) data as reference data. As a result of evaluation, the diurnal cycle had a higher coincidence rate with the reference data than the annual cycle, and the 14-day diurnal cycle was the most suitable for use as the GSICS correction coefficient.