• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.842-851
• /
• 1996

Median filter(MF) has often been applied to color or gray images as a noise fiilter in image processing . Application of MF to binary images was tried in this study. For binary images, MF not only can remove noise but can also work as an indicator showing the dominant color in a region which is called window . Fro example, MF can be used to categorize clusters and to detect interested parts of an object. In other words, MF can also be used to remove unnecessary parts. The function of MF can be intensified by introducing a thresholding value, which is determined by the size of the interested part of an object. This improved MF for binary images is called the modified median filter(MMF), and its applicability to grade produce will be discussed in this paper.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.4
• /
• pp.1846-1863
• /
• 2016

High dynamic range (HDR) images can present the perfect real scene and rich color information. A commonly encountered problem in practical applications is how to well visualize HDR images on standard display devices. In this paper, we propose a multi-scale decomposition method using guided filtering for HDR image tone mapping. In our algorithm, HDR images are directly decomposed into three layers：base layer, coarse scale detail layer and fine detail layer. We propose an effective function to compress the base layer and the coarse scale detail layer. An adaptive function is also proposed for detail adjustment. Experimental results show that the proposed algorithm effectively accomplishes dynamic range compression and maintains good global contrast as well as local contrast. It also presents more image details and keeps high color saturation.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.36 no.2
• /
• pp.43-52
• /
• 2020

With the advent of the Fourth Industrial Revolution, people need healing. Research in neuroarchitecture shows that people feel happy and stable when working with nature, and patients heal quickly. Therefore, This study aims to quantitatively analyze the colors that help psychological healing in the painting images depicting nature by setting 'Natural Colors' of Biophilic Design as the subject of research. So the purpose of this study was to measure Biophilic Color and to develop Biophilic Color Palette. We extracted Biophilic colors using Impressionist Monet's Landscape painting. After extracting colors using Photoshop Color Picker, we converted RGB color code to NCS color code and Munsell color code. The results of this study were as follows; The ratio of Y was high in the GY-series and YR-series. This is due to the characteristic of impressionism that expresses the change of color by light in close relationship with light. Y is universally considered to be pleasant, representing happiness, sunshine and optimism. Therefore, it is possible to create an environment that helps psychological healing by utilizing the Y-series color palette. Average Blackness was 28. Average Chromaticness was 34.61. The significance of this study is to propose a biophilic color palette that is useful for psychological healing by quantifying the color code of biophilic colors depicted and expressed with adjective images and idiomatic color names. Quantitative and empirical studies on healing colors are needed continuously and should be actively utilized in healing environment planning.

• Korean Journal of Remote Sensing
• /
• v.8 no.1
• /
• pp.59-69
• /
• 1992

The IMAPRO sotfware package was mainly focused to provide an algorithm which is capable of displaying various color composite images on IBM PC, VGA(Video Graphic Array) card with no special hardware. It displays the false color images using a low-cost eight-bit place refresh buffer. This produces similar quality to the one obtained from image board with three eight-bit plane. Also, it provides user friendly menu driven method for the user who are not familier with technical knowladge of image processing. It may prove useful for universities, institute and private company where expensive hardware is not available.

• Journal of Fashion Business
• /
• v.8 no.3
• /
• pp.49-58
• /
• 2004

In the modern society, already a popular and public part of fashion, hair coloring has the effect of optical illusion on image. This study therefor aims to reveal the effects of varied and fashionable hair coloring on the body images. This is a combination of an actual examination and an experimental study. In order to know the effects of hair colors on body image, 230 female collegians residing in Busan were given a questionnaire on the reality of hair dyeing. Based on the actual research, one subject was selected and stimuli were manufactured. The analysis and examination of the effects of hair dyeing have produced the following conclusions. (1) As a result of dispersion analysis about the image effect according to hair colors, a meaningful difference is recognized in the item and indicates that hair color variation influences the image effect. (2) As a result, extracting the factors that hair colors can influence the image, 3 factors were extracted. The first factor is an intellectual image, the second factor is an active image, and the third factor is a comfortable image. (3) Image effect in hair colors are as same next. Red and Orange color clearly indicate the image of 'charismatic', 'lively', 'positive', 'active', 'light' and 'gorgeous'. Blue and Green color indicates the image of 'unfriendly', 'hard', 'cold' and 'uneasy'. White color indicates the image of 'unfriendly', 'charismatic', 'gorgeous' and 'impure' then Black color has images of 'friendly', 'intellectual', 'indignified' and 'pure'. In other words, the result indicates rather a different tendency comparison with the general color image.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.7 no.2
• /
• pp.106-110
• /
• 2014

This paper proposed the face recognition method which can be effectively applied to the robot's vision system. The proposed algorithm is recognition using hue extraction and feature point. hue extraction was using difference of skin color, pupil color, lips color. Features information were extraction from eye, nose and mouth using feature parameters of the difference between the feature point, distance ratio, angle, area. Feature parameters fuzzified data with the data generated by membership function, then evaluate the degree of similarity was the face recognition. The result of experiment are conducted with frontal color images of face as input images the received recognition rate of 96%.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.816-819
• /
• 2006

One of the most difficult parameters to measure in the sea is current speed and direction. Recently, efforts are being made to estimate the ocean current vectors by utilizing sequential satellite imageries. In this study, we attempted to estimated sea surface current vector (sscv) by using satellite ocean color imageries of SeaWifs around the Korean Peninsula. This ocean color image data has 1-day sampling interval and spatial resolution of 1x1 km. Maximum cross-correlation method is employed which is aimed to detect similar patterns between sequential images. The estimated current vectors are compared to the surface geostrophic current vectors obtained from altimeter of sea level height data. In utilizing the color imagery data, some limitations and drawbacks exist so that in warm water region where phytoplankton concentration is relatively lower than in cold water region, estimation of sscv is poor and unreliable. On the other hand, two current vector fields agree reasonably well in the Korean South Sea region where high concentration of chlorophyll-a and weak tide is observed. In the future, with ocean color images of shorter sampling interval by COMS satellite, the algorithm and methodology developed in the study would be useful in providing the information for the ocean current around Korean Peninsula.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.11
• /
• pp.5583-5604
• /
• 2016

In this paper, we present a novel image operator to extract textual information in natural scene images. First, a powerful refiner called the Stroke Color Extension, which extends the widely used Stroke Width Transform by incorporating color information of strokes, is proposed to achieve significantly enhanced performance on intra-character connection and non-character removal. Second, a character classifier is trained by using gradient features. The classifier not only eliminates non-character components but also remains a large number of characters. Third, an effective extractor called the Character Color Transform combines color information of characters and geometry features. It is used to extract potential characters which are not correctly extracted in previous steps. Fourth, a Convolutional Neural Network model is used to verify text candidates, improving the performance of text detection. The proposed technique is tested on two public datasets, i.e., ICDAR2011 dataset and ICDAR2013 dataset. The experimental results show that our approach achieves state-of-the-art performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.5
• /
• pp.2326-2345
• /
• 2016

For the compression of color images, a common bitmap usually is generated to replace the three individual bitmaps that originate from block truncation coding (BTC) of the R, G and B channels. However, common bitmaps generated by some traditional schemes are not the best possible because they do not consider the minimized distortion of the entire color image. In this paper, we propose a near-optimized common bitmap scheme for BTC using Binary Ant Colony Optimization (BACO), producing a BACO-BTC scheme. First, the color image is compressed by the BTC algorithm to get three individual bitmaps, and three pairs of quantization values for the R, G, and B channels. Second, a near-optimized common bitmap is generated with minimized distortion of the entire color image based on the idea of BACO. Finally, the color image is reconstructed easily by the corresponding quantization values according to the common bitmap. The experimental results confirmed that reconstructed image of the proposed scheme has better visual quality and less computational complexity than the referenced schemes.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.6 no.4
• /
• pp.840-866
• /
• 2014

Visibility in underwater images is usually poor because of the attenuation of light in the water that causes low contrast and color variation. In this paper, a new approach for underwater image quality improvement is presented. The proposed method aims to improve underwater image contrast, increase image details, and reduce noise by applying a new method of using contrast stretching to produce two different images with different contrasts. The proposed method integrates the modification of the image histogram in two main color models, RGB and HSV. The histograms of the color channel in the RGB color model are modified and remapped to follow the Rayleigh distribution within certain ranges. The image is then converted to the HSV color model, and the S and V components are modified within a certain limit. Qualitative and quantitative analyses indicate that the proposed method outperforms other state-of-the-art methods in terms of contrast, details, and noise reduction. The image color also shows much improvement.