• Journal of Korea Society of Industrial Information Systems
• /
• v.8 no.2
• /
• pp.30-37
• /
• 2003

To effectively control a vast amount of postal packages, we need the automatic system for extracting the address region from CCD scanner images. In this paper, we propose a address region extraction algorithm in the standard postal label. We used geometric characteristics of the underlying address regions and defined several criteria for fast detection of address regions. As a result, we accomplished a successful detection and classification of the postal package labels in real time.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.20 no.1
• /
• pp.1-14
• /
• 2017

A land cover map provides basic information to help understand the current state of a region, but its utilization in the ecological research field has deteriorated due to limited temporal and spatial resolutions. The purpose of this study was to investigate the possibility of using a land cover map with data based on high resolution images acquired by UAV. Using the UAV, 10.5 cm orthoimages were obtained from the $2.5km^2$ study area, and land cover maps were obtained from object-based and pixel-based classification for comparison and analysis. From accuracy verification, classification accuracy was shown to be high, with a Kappa of 0.77 for the pixel-based classification and a Kappa of 0.82 for the object-based classification. The overall area ratios were similar, and good classification results were found in grasslands and wetlands. The optimal image segmentation weights for object-based classification were Scale=150, Shape=0.5, Compactness=0.5, and Color=1. Scale was the most influential factor in the weight selection process. Compared with the pixel-based classification, the object-based classification provides results that are easy to read because there is a clear boundary between objects. Compared with the land cover map from the Ministry of Environment (subdivision), it was effective for natural areas (forests, grasslands, wetlands, etc.) but not developed areas (roads, buildings, etc.). The application of an object-based classification method for land cover using UAV images can contribute to the field of ecological research with its advantages of rapidly updated data, good accuracy, and economical efficiency.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.23 no.1
• /
• pp.97-103
• /
• 2009

The status and the property of a tongue are the important indicators to diagnose one's health like physiological and clinicopathological changes of inner organs. However, the tongue diagnosis is affected by examination circumstances like a light source, patient's posture, and doctor's condition. To develop an automatic tongue diagnosis system for an objective and standardized diagnosis, classifying tongue coating is inevitable but difficult since the features like color and texture of the tongue coatings and substance have little difference, especially in the neighborhood on the tongue surface. The proposed method has two procedures; the first is to acquire the color table to classify tongue coatings and substance by automatically separating coating regions marked by oriental medical doctors, decomposing the color components of the region into hue, saturation and brightness and obtaining the 2nd order discriminant with statistical data of hue and saturation corresponding to each kind of tongue coatings, and the other is to apply the tongue region in an input image to the color table, resulting in separating the regions of tongue coatings and classifying them automatically. As a result, kinds of tongue coatings and substance were segmented from a face image corresponding to regions marked by oriental medical doctors and the color table for classification took hue and saturation values as inputs and produced the classification of the values into white coating, yellow coating and substance in a digital tongue diagnosis system. The coating regions classified by the proposed method were almost the same to the marked regions. The exactness of classification was 83%, which is the degree of correspondence between what Oriental medical doctors diagnosed and what the proposed method classified. Since the classified regions provide effective information, the proposed method can be used to make an objective and standardized diagnosis and applied to an ubiquitous healthcare system. Therefore, the method will be able to be widely used in Oriental medicine.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.1256-1259
• /
• 2002

In this paper, we have proposed license plate recognition system for multi-national vehicle license plate using geometric features along with hybrid and seven segment pattern vectors. In the proposed system, we suggested to find horizontal and vertical relation after going through preparation process with inputted real-time license plate image of Korea and Japan, and then to classify license plate with using characteristic and geometric information of license plates. It classifies the extracted license plate images into letters and numbers, such as local name, local number, classification character and license consecutive numbers, and recognize license plate of Korea and Japan by applying hybrid and seven segments pattern vectors to classified letter and number region. License plate extraction step of the proposed system uses width and length information along with relative rate of Korean and Japanese license plate. Moreover, it exactly segmentation by letters with using each letter and number position information within license plate region, and recognizes Korean and Japanese license plates by applying hybrid and seven segment pattern vectors, containing characteristics related to letter size and movement within segmented letter area. As the result of testing the proposed system in real experiment, it recognized regardless of external lighting conditions as well as classifying license plates by nations, Korea and Japan. We have developed a system, recognizing regardless of inputted structural character of vehicle licenses and external environment.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.9
• /
• pp.21-28
• /
• 2009

Color polarity classification is a process to determine whether the color of text is bright or dark and it is prerequisite task for text extraction. In this paper we propose a color polarity method to extract text region. Based on the observation for the text and background regions, the proposed method uses the ratios of sizes and standard deviations of bright and dark regions. At first, we employ Otsu's method for binarization for gray scale input region. The two largest segments among the bright and the dark regions are selected and the ratio of their sizes is defined as the first measure for color polarity classification. Again, we select the segments that have the smallest standard deviation of the distance from the center among two groups of regions and evaluate the ratio of their standard deviation as the second measure. We use these two ratio features to determine the text color polarity. The proposed method robustly classify color polarity of the text. which has shown by experimental result for the various font and size.

• Journal of the Korean Society for information Management
• /
• v.19 no.4
• /
• pp.53-76
• /
• 2002

This study compares and analyzes the classes in the major special areas in the sociology, called “branch sociology,” included in the Korean Decimal Classification 4th edition and Dewey Decimal Classification 21st edition. Especially it analyzes the related classes of specified areas (branch sociology) of sociology including those of arts and sports, sciences, languages, society, region, etc. class by class. In this analysis two systems show many differences in the classes included and in the locations of some classes. This analysis can be useful for the future revision of KDC.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.541-543
• /
• 2022

In recent years, retinal disorders have become a serious health concern. Retinal disorders develop slowly and without obvious signs. To avoid vision deterioration, early detection and treatment are critical. Optical coherence tomography (OCT) is a non-invasive and non-contact medical imaging technique used to acquire informative and high-resolution image of retinal area and underlying layers. Disease signs are difficult to detect because OCT images have many areas which are not related to any disease. In this paper, we present a deep learning-based method to perform multi-label classification on a long-tailed OCT dataset. Our method first extracts the region of interest and then performs the classification task. We achieve 98% accuracy, 92% sensitivity, and 99% specificity on our private OCT dataset. Using the heatmap generated from trained convolutional neural network, our method is more robust and explainable than previous approaches because it focuses on areas that contain disease signs.

• Journal of KIISE:Software and Applications
• /
• v.31 no.12
• /
• pp.1684-1690
• /
• 2004

This paper presents a method for classifier selection that uses distribution information of the training samples in a small region surrounding a sample. The conventional DCS-LA(Dynamic Classifier Selection - Local Accuracy) selects a classifier dynamically by comparing the local accuracy of each classifier at the test time, which inevitably requires long classification time. On the other hand, in the proposed approach, the best classifier in a local region is stored in the FSA(Feature Space Attribute) table during the training time, and the test is done by just referring to the table. Therefore, this approach enables fast classification because classification is not needed during test. Two feature space attributes are used entropy and density of k training samples around each sample. Each sample in the feature space is mapped into a point in the attribute space made by two attributes. The attribute space is divided into regular rectangular cells in which the local accuracy of each classifier is appended. The cells with associated local accuracy comprise the FSA table. During test, when a test sample is applied, the cell to which the test sample belongs is determined first by calculating the two attributes, and then, the most accurate classifier is chosen from the FSA table. To show the effectiveness of the proposed algorithm, it is compared with the conventional DCS -LA using the Elena database. The experiments show that the accuracy of the proposed algorithm is almost same as DCS-LA, but the classification time is about four times faster than that.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.153-156
• /
• 2005

Skin region detection in images is an important process in many computer vision applications targeting humans such as hand gesture recognition and face identification. It usually starts at a pixel-level, and involves a pre-process of color spae transformation followed by a classification process. A color space transformation is assumed to increase separability between skin classes and other classes, to increase similarity among different skin tones, and to bring a robust performance under varying imaging conditions, without any complicated analysis. In this paper, we examine if the color space transformation actually brings those benefits to the problem of skin region detection on a set of human hand images with different postures, backgrounds, people, and illuminations. Our experimental results indicate that color space transfomation affects the skin detection performance. Although the performance depends on camera and surround conditions, normalized [R, G, B] color space may be a good choice in general.

• Journal of Advanced Navigation Technology
• /
• v.15 no.1
• /
• pp.140-146
• /
• 2011

In this paper, we propose a fast object classification method based on texture and color information for video surveillance. We take the advantage of local patches by extracting SURF and color histogram from images. SURF gives intensity content information and color information strengthens distinctiveness by providing links to patch content. We achieve the advantages of fast computation of SURF as well as color cues of objects. We use Bag of Word models to generate global descriptors of a region of interest (ROI) or an image using the local features, and Na$\ddot{i}$ve Bayes model for classifying the global descriptor. In this paper, we also investigate discriminative descriptor named Scale Invariant Feature Transform (SIFT). Our experiment result for 4 classes of the objects shows 95.75% of classification rate.