• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.420-438
• /
• 2004

Artificially or naturally contained texts in the natural images have significant and detailed information about the scenes. If we develop a method that can extract and recognize those texts in real-time, the method can be applied to many important applications. In this paper, we suggest a new method that extracts the text areas in the natural images using the low-level image features of color continuity. gray-level variation and color valiance and that verifies the extracted candidate regions by using the high-level text feature such as stroke. And the two level features are combined hierarchically. The color continuity is used since most of the characters in the same text lesion have the same color, and the gray-level variation is used since the text strokes are distinctive in their gray-values to the background. Also, the color variance is used since the text strokes are distinctive in their gray-values to the background, and this value is more sensitive than the gray-level variations. The text level stroke features are extracted using a multi-resolution wavelet transforms on the local image areas and the feature vectors are input to a SVM(Support Vector Machine) classifier for the verification. We have tested the proposed method using various kinds of the natural images and have confirmed that the extraction rates are very high even in complex background images.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.43-53
• /
• 2016

In this study, under the assumption that there may be differences in colour attributes that can be perceived according to the brightness of the background and the size of the colour stimulus, a test was conducted where colour matching was done for stimulus sizes of $10^{\circ}$ and $20^{\circ}$ in terms of peripheral vision by varying the background brightness. The test results showed that depending on the background brightness and the specific combinations of the Munsell colour attributes used as the test stimulus, colours can be perceived differently even if they are the same colours. In addition, in contrast to findings from previous studies on colour perception according to the stimulus size, it was found that even if the size of the colour stimulus is relatively small, colours can be perceived more colourfully or more brightly with changes in the background brightness. Based on the findings of this study, degradation in image quality can be improved, which may occur when the size of the input image is changed at a later time, and also, contributions can be made when it comes to the reproduction of effective sold three-dimensional structures that reflect visual qualities when processing 3D holographic imagery, in addition to 2D imagery.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.4
• /
• pp.43-48
• /
• 2018

This study was conducted to reproduce digital colour based on the lightness of the background and size of the colour stimulus so that colour can be similarly perceived under different conditions. With the evolution of display technologies, display devices of various sizes can now reproduce more accurate colour and enhanced images, thus affecting the overall quality of display images. This study reproduced digital colour by considering the visual characteristics of the digital media environment. To accomplish this, we developed a colour appearance model which distinguishes the properties of foveal and peripheral vision. The proposed model is based on existing research on the lightness of the background and size of the colour stimulus. Based on experimental results, an analysis of variance was performed in order to develop the colour appearance model. The algorithm and modelling were verified based on the proposed model. In addition, to apply this model to display technologies, a practical colour control system and a method for handling complex input images were developed. Through this research, colour conversion errors which might occur when the input image is converted to fit a specific display size are resolved from the perspective of the human visual system. As a result, more accurate colour can be displayed and enhanced images can be reproduced.

• Journal of the Korea Computer Graphics Society
• /
• v.24 no.5
• /
• pp.31-39
• /
• 2018

In this paper, we propose an automated method for the ground-glass nodule(GGN) classification using GGN-Net based on intensity, texture, and shape-enhanced images in chest CT images. First, we propose the utilization of image that enhances the intensity, texture, and shape information so that the input image includes the presence and size information of the solid component in GGN. Second, we propose GGN-Net which integrates and trains feature maps obtained from various input images through multiple convolution modules on the internal network. To evaluate the classification accuracy of the proposed method, we used 90 pure GGNs, 38 part-solid GGNs less than 5mm with solid component, and 23 part-solid GGNs larger than 5mm with solid component. To evaluate the effect of input image, various input image set is composed and classification results were compared. The results showed that the proposed method using the composition of intensity, texture and shape-enhanced images showed the best result with 82.75% accuracy.

• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.308-320
• /
• 2021

Conventional image quality studies have been focused on 'naturalness' and has relied on memory color. Memory colors are mainly formed for familiar objects with prior experience, and the more faithfully these memories are reflected, the more naturalness of the reproduced image quality increases. In particular, the brightness and saturation of memory colors play an important role in increasing the preference of image quality as well as naturalness. Therefore, in the case of existing image quality studies, image quality characteristics were studied focusing on natural objects and people with memory. We extracted representative images of each genre (sports, documentaries, news, entertainment and music, and movies), adjusted the brightness, contrast, and saturation of each image, and conducted an experiment to evaluate perceived quality. Based on situational context, the results of this classification indicated that genres of television content can be divided into two categories: proximate and indirect experiences. Proximate experience best characterizes outdoor sports, dramas, and nature documentaries, where their image qualities have shown to have a strong correlation with brightness and contrast. On the other hand, indirect experience best characterizes news, music shows and SF/action movies. The image quality perception for indirect experiences was shown to be closely related to and optimized by contrast and saturation.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.370-372
• /
• 2006

본 논문에서 제안하는 방법은 영상에서 중심 객체를 추출하기 위해 에지와 색상 정보에서 추출한 특집 지도와 배경의 영향을 줄이기 위친 창조 지도(reference map)를 제안한 것이 특징이다. 특징 지도는 다른 영역과 현저하게 구분되는 영역을 검출하기 위해서 영상의 특징 값(feature)들을 이용해서 구성한 영상이라고 할 수 있다. 그리고 창조 지도는 배경의 영향을 최소화하면서, 객체가 존재할 확률이 높은 부분을 나타내는 지도이다. 제안하는 방법은 밝기 차 정보를 가지고 있는 에지와 YCbCr 컬러모델과 HSV 컬러모델의 색상 성분을 특징 값으로 사용한다. 이들 특징 값을 이용해서 특징 지도를 구성하는 방법으로 영상 내 색상 차에 의해서 나타나는 경계부분을 구하는 방법을 사용한다. 이 방법을 사용하여 에지 지도와 두 개의 색상 지도의 3가지 특징 지도를 생성한다. 다음으로, 영상 배경의 영향을 줄이기 위해 참조 지도를 구한다. 구해진 참조 지도와 특징 지도들을 이용해서 결합 지도(combination map)를 생성한다. 결함 지도로부터 다각형의 객체 후보 영역을 구하고, 객체 후보 영역에 영상분할을 적용하여 중심 객체를 추출한다. 실험에 사용된 영상들은 Corel DB를 사용하였으며, 실험결과로써 precision은 84.3%, recall은 81.3%의 성능을 보인다.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.2
• /
• pp.138.1-138.1
• /
• 2011

천상열차분야지도와 소주천문도는 전통 별자리를 돌에 새긴 한국과 중국의 대표 천문도이다. 이들 천문도는 조선 초기인 1395년과 남송시대인 1247년에 각각 만들어졌다. 비슷한 시기에 만들어진 두 천문도에는 한양(漢陽)과 개봉(開封)의 위도를 기준으로 밤하늘에 보이는 동양의 전통 별자리가 새겨져있다. 본 연구에서는 이들 두 천문도의 별자리를 비교 분석하여 각각의 특징을 찾아내고 이들을 한국과 중국의 전통 별그림과 비교하였다. 천상열차분야지도 별그림의 가장 큰 특징은 밝기에 따라 별의 크기를 다르게 새긴 과학적인 표현법이다. 이 외에도 한국과 중국 석각천문도의 별그림에는 몇 가지 차이점이 있다. 두 천문도에서 보이는 별그림의 차이를 조사한 결과 다르게 그려진 별그림에서 각각의 공통된 특징을 찾아냈다. 두 천문도의 대표적 차이점은 별자리 연결방식과 별의 상대적 위치 차이에 의한 별자리 모양이다. 아울러, 두 천문도에 그려진 서로 다른 별그림을 한국과 중국의 보천가(步天歌)와 신의상법요(新儀象法要)의 별그림과 비교하였다. 한국과 중국의 석각 천문도를 비교한 결과 두 천문도 별그림의 가장 큰 차이점은 천문도 제작의 완성도와 별그림의 유래 그리고 별자리 표현 방식의 차이에서 기인하고 있음을 확인하였다.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.7
• /
• pp.1763-1772
• /
• 1996

The conventional training set selection methods for the satellite image classification usually depend on the manual selection using data from the direct measurements of the ground or the ground map. However this task takes much time and cost, and some feature values vary in wide ranges even if they are in the same class. Such feature values can increase the robustness of the neural net but learning time becomes longer. In this paper,we propose anew training set selection algorithm using a rule-based method. By the technique proposed, the SPOT multispectral Imagery is classified in 3 bands, and the pixels which satisfy the rule are employed as the training sets for the neutralist classifier. The experimental results show faster initial convergence and almost the same or better classification accuracy. We also showed an improvement of the classification accuracy by using texture features and NDV1.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.11C
• /
• pp.1140-1151
• /
• 2003

This paper proposes a face recognition method based on modified Otsu's binarization and Hu moment. Proposed method is robust to brightness, contrast, scale, rotation, and translation changes. As the proposed modified Otsu's binarization computes other thresholds from conventional Otsu's binarization, namely we create two binary images, we can extract higher dimensional feature vector. Here the feature vector has properties of robustness to brightness and contrast changes because the proposed method is based on Otsu's binarization. And our face recognition system is robust to scale, rotation, and translation changes because of using Hu moment. In the perspective of brightness, contrast, scale, rotation, and translation changes, experimental results with Olivetti Research Laboratory (ORL) database and the AR database showed that average recognition rates of conventional well-known principal component analysis (PCA) are 93.2% and 81.4%, respectively. Meanwhile, the proposed method for the same databases has superior performance of the average recognition rates of 93.2% and 81.4%, respectively.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.239-242
• /
• 2006

골다공증은 해면골의 골소주 두께 감소 및 파단에 기인한 전체적인 골질이 저하되는 질병이다. 골다공증을 예방과 조기진단을 하기 위해서는 골밀도를 측정하여야 한다. 보다 나은 이미지를 얻기 위해 Digital X-Ray로 골밀도를 측정하여 영상 처리하기 위한 방법을 제시한다. 먼저 디지털 센서에서 증감지와 렌즈간 거리가 가까워서 증감지의 중심과 주변부의 광 경로차이가 발생하므로 왜곡이 발생하는데 이를 균일화하여야 한다. 그리고 X-Ray장비의 조건에 따라 영상에 많은 차이를 보이므로 영상의 밝기를 보정하는 과정이 필수적이다.