• Investigative Magnetic Resonance Imaging
• /
• v.3 no.2
• /
• pp.179-187
• /
• 1999

Purpose : This paper introduces a computationally inexpensive context-dependent classification of multi-echo MRI with Bayes compound decision model. In order to produce accurate region segmentation especially in homogeneous area and along boundaries of the regions, we propose a classification method that uses contextual information of local enighborhood system in the image. Material and Methods : The performance of the context free classifier over a statistically heterogeneous image can be improved if the local stationary regions in the image are disassociated from each other through the mechanism of the interaction parameters defined at he local neighborhood level. In order to improve the classification accuracy, we use the contextual information which resolves ambiguities in the class assignment of a pattern based on the labels of the neighboring patterns in classifying the image. Since the data immediately surrounding a given pixel is intimately associated with this given pixel., then if the true nature of the surrounding pixel is known this can be used to extract the true nature of the given pixel. The proposed context-dependent compound decision model uses the compound Bayes decision rule with the contextual information. As for the contextual information in the model, the directional transition probabilities estimated from the local neighborhood system are used for the interaction parameters. Results : The context-dependent classification paradigm with compound Bayesian model for multi-echo MR images is developed. Compared to context free classification which does not consider contextual information, context-dependent classifier show improved classification results especially in homogeneous and along boundaries of regions since contextual information is used during the classification. Conclusion : We introduce a new paradigm to classify multi-echo MRI using clustering analysis and Bayesian compound decision model to improve the classification results.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06b
• /
• pp.165-170
• /
• 1998

This paper presents a new prediction method RBP region-based prediction model where the context used for prediction contains regions instead of individual pixels. There is a meaningful property that RBP can partition a cartoon image into two distinctive types of regions, one containing full-color backgrounds and the other containing boundaries, edges and home-chromatic areas. With the development of computer techniques, synthetic images created with CG (computer graphics) becomes attactive. Like the demand on data compression, it is imperative to efficiently compress synthetic images such as cartoon animation generated with CG for storage of finite capacity and transmission of narrow bandwidth. This paper a lossy compression method to full-color regions and a lossless compression method to homo-chromatic and boundaries regions. Two criteria for partitioning are described, constant criterion and variable criterion. The latter criterion, in form of a linear function, gives the different threshold for classification in terms of contents of the image of interest. We carry out experiments by applying our method to a sequence of cartoon animation. We carry out experiments by applying our method to a sequence of cartoon animation. Compared with the available image compression standard MPEG-1, our method gives the superior results in both compression ratio and complexity.

• Korean Journal of Remote Sensing
• /
• v.33 no.6_2
• /
• pp.1089-1100
• /
• 2017

This paper presented a method using past land cover maps in image segmentation and training set collection for updating land cover maps. In this method, the object boundaries in past land cover maps were used for segmenting image clearly. Also, the classes of past land cover maps were used to extract additional informative training set from the initial classification result using a small number of initial training set. To evaluate the applicability of proposed method, a case study for updating land cover maps was carried out using middle-level land cover maps and WorldView-2 image in the Taean-gun, South Korea. As a result of the case study, the confusions between urban and barren, paddy/dry field and grassland in the initial classification result were reduced by adding training set. In addition, the object segmentation using boundaries of past land cover map cleared land cover boundaries and improved classification accuracy. Based on the result of case study, the proposed method using past land cover maps is expected to be useful for updating land cover maps.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.126-129
• /
• 2005

Change detections is carried out under the assumption that pixel boundaries of geometrically corrected time series satellite images cover the same location. However that assumption can be wrong when shifts in the pointing direction of a satellite sensor occurs. Currently, although the influence of misregistration on landcover change detection has been investigated, there has been little research on the influence of pointing direction shifts of a satellite sensor. In this study, a simple method for reducing the effects of pointing direction shifts of a satellite sensor is proposed: the classification of two ASTER images was carried out using the linear spectral mixture analysis, the two classification results were resampled into a geometrically fixed grid, and then the change detection of the two ASTER images was carried out by comparing the resampled classification results of the two images. The proposed method showed high performance in discriminating between changed areas and unchanged areas by removing the pointing direction shifts of a satellite sensor.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.191-194
• /
• 2002

In this paper, a new GA-based methodology with information granules is suggested for construction of the fuzzy classifier. We deal with the selection of the fuzzy region as well as two major classification problems-the feature selection and the pattern classification. The proposed method consists of three steps: the selection of the fuzzy region, the construction of the fuzzy sets, and the tuning of the fuzzy rules. The genetic algorithms (GAs) are applied to the development of the information granules so as to decide the satisfactory fuzzy regions. Finally, the GAs are also applied to the tuning procedure of the fuzzy rules in terms of the management of the misclassified data (e.g., data with the strange pattern or on the boundaries of the classes). To show the effectiveness of the proposed method, an example-the classification of the Iris data, is provided.

• The KIPS Transactions:PartB
• /
• v.16B no.4
• /
• pp.271-280
• /
• 2009

In this paper, we propose a smoke detection method using region growing method in outdoor video sequences. Our proposed method is composed of three steps; the initial change area detection step, the boundary finding and expanding step, and the smoke classification step. In the first step, we use a background subtraction to detect changed areas in the current input frame against the background image. In difference images of the background subtraction, we calculate a binary image using a threshold value and apply morphology operations to the binary image to remove noises. In the second step, we find boundaries of the changed areas using labeling algorithm and expand the boundaries to their neighbors using the region growing algorithm. In the final step, ellipses of the boundaries are estimated using moments. We classify whether the boundary is smoke by using the temporal information.

• Korean Journal of Remote Sensing
• /
• v.36 no.1
• /
• pp.29-39
• /
• 2020

Forest fire is a critical disaster that causes massive destruction of forest ecosystem and economic loss. Hence, accurate estimation of the burned area is important for evaluation of the degree of damage and for preparing baseline data for recovery. Since most of the area size damaged by wildfires in Korea is less than 1 ha, it is necessary to use satellite or drone images with a resolution of less than 10m for detecting the damage area. This paper aims to detect wildfire-damaged area from a Kompsat-3 image using the indices such as NDVI (normalized difference vegetation index) and FBI (fire burn index) and to examine the classification characteristics according to the methods such as Otsu thresholding and ISODATA(iterative self-organizing data analysis technique). To mitigate the salt-and-pepper phenomenon of the pixel-based classification, a gaussian filter was applied to the images of NDVI and FBI. Otsu thresholding and ISODATA could distinguish the burned forest from normal forest appropriately, and the salt-and-pepper phenomenon at the boundaries of burned forest was reduced by the gaussian filter. The result from ISODATA with gaussian filter using NDVI was closest to the official record of damage area (56.9 ha) published by the Korea Forest Service. Unlike Otsu thresholding for binary classification,since the ISODATA categorizes the images into multiple classes such as(1)severely burned area, (2) moderately burned area, (3) mixture of burned and unburned areas, and (4) unburned area, the characteristics of the boundaries consisting of burned and normal forests can be better expressed. It is expected that our approach can be utilized for the high-resolution images obtained from other satellites and drones.

• MALSORI
• /
• no.35_36
• /
• pp.131-143
• /
• 1998

This study describes an algorithm for the F0 contour generation system for Korean sentences and its evaluation results. 400 K-ToBI labeled utterances were used which were read by one male and one female announcers. F0 contour generation system uses two classification trees for prediction of K-ToBI labels for input text and 11 regression trees for prediction of F0 values for the labels. Evaluation results of the system showed 77.2% prediction accuracy for prediction of IP boundaries and 72.0％ prediction accuracy for AP boundaries. Information of voicing and duration of the segments was not changed for F0 contour generation and its evaluation. Evaluation results showed 23.5Hz RMS error and 0.55 correlation coefficient in F0 generation experiment using labelling information from the original speech data.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.242-242
• /
• 2015

Monitoring the land cover changes in Nakdong River Basins using the multi-temporal remote sensing datasets is necessary for preserving properties in the river basins and monitoring the environmental changes in the river basins after the 4 major river restoration project. This research aims to monitor the land cover changes using the multi-temporal Landsat imageries and the airborne topographic LiDAR data. Firstly, the river basin boundaries are determined by using the LiDAR data, and the multiple river basin imageries are generated from the multi-temporal Landsat imageries by using the river basin boundaries. Next the classification method is employed to identify the multiple land covers in the generated river basin imageries. Finally, monitoring the land cover changes is implemented by comparing the differences of the same clusters in the multi-temporal river basin imageries.

• Journal of Korean Academy of Nursing
• /
• v.17 no.1
• /
• pp.9-23
• /
• 1987

Nursing service, as the largest user of labor resources, has become concerned about appropriate allocation of staffing resources. Therefore, this project was designed to measure quantitatively the direct nursing care provided to patients and to develop a new patient classification system based on the direct nursing care activities. The initial step in the development of the classification instrument was to identify the content of direct nursing activities. The frequency with which these activities were carried out, the total time spent in carrying them out and the average time for one performance of each of the nursing activities was calculated. The next step was to select the items for the classification instrument taking into account these direct nursing activities. A list of 40 items was prepared. These items were then classified into 8 major categories: personal hygiene, moving ＆ exercise, nutrition & elimination, observation, medication, treatment, collecting specimens and other care activities for severity ill patients. Each item was assigned a value unit based on the average time required by the nursing staff to complete the specific item. The third step was to determine the practicality of the items and value units, so an attempt was made to establish content validity for these items and units by obtaing a consensus from 8 head nurses, representing eight different departments. The 4th step was to conducted a pilot study to establish the score range for the classification boundaries. For this purpose an instrument was designed using the list of items and value units and a prepared classification criteria as a guideline to validate the patient classification. A judgment group consisting of 52 supervisory nurses and head nurses were asked to select the proper patient to fit each classification criteria and to fill out the instrument for each patient. The total value unit and the frequency for each classification group was calculated. According to the frequency distribution, the score range for the classification group was determined as follows : 0~15 for groupI, 16~30 for group II, 31~50 for group III, and above 51 for group IV. Finally a patient classification form was developed.