• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.2
• /
• pp.98-106
• /
• 2016

Remote sensing is an efficient technology for observing and monitoring the land surfaces inaccessible to humans. This research proposes a methodology for improving the accuracy of the land cover classification using the Landsat-8 operational land imager(OLI) image. The proposed methodology consists of the following steps. First, the normalized difference vegetation index(NDVI) and normalized difference water index(NDWI) images are generated from the given Landsat-8 OLI image. Then, a new image is generated by adding both NDVI and NDWI images to the original Landsat-8 OLI image using the layer-stacking method. Finally, the maximum likelihood classification(MLC), and support vector machine(SVM) methods are separately applied to the original Landsat-8 OLI image and new image to identify the five classes namely water, forest, cropland, bare soil, and artificial structure. The comparison of the results shows that the utilization of the layer-stacking method improves the accuracy of the land cover classification by 8% for the MLC method and by 1.6% for the SVM method. This research proposes a methodology for improving the accuracy of the land cover classification by using the layer-stacking method.

• Journal of the Korean Society of Costume
• /
• v.59 no.1
• /
• pp.14-28
• /
• 2009

Exoticism, by definition, is 'the charm of the unfamiliar', usually because of associations with a distant country. In the western-centric world, exoticism implies non-western or oriental style. The purpose of this study was to identify Koreans' perception of "Exoticism", and to compare the perception of exotic fashion image according to gender and education differences. Empirical study was composed of two parts focusing on gender and education effects respectively. For the first part, data were collected by self-administered questionnaires distributed to 280 respondents at 2 universities and 2 high schools during August and September 2005. The sample was consisted of 140 male and 140 female. A measurement, including 24 image adjectives to evaluate 16 fashion stimuli, was developed. Data were analyzed by descriptive statistics, correlations, t-test, and MDS. There was no difference in the perception of exotic fashion image according to gender. Both gender groups perceived exotic image as western image and non-exotic image as oriental image. Thus it could be said that Koreans perceive western-based fashion as foreign and exotic. This finding implies the relativity of "Exoticism." In the second part, the measurement and the analysis methods were the same with the first part. The respondents were consisted of 70 fashion majored female students and 70 non-fashion majored female students. There was considerable difference between fashion and non-fashion major groups in their perception of exotic fashion image. Whereas non-fashion major group perceived exotic image as western image and non-exotic image as oriental image, fashion major group perceived exotic image as both western and oriental image. This result suggested that fashion major group have western-centered conception as well as general perception character of Korean.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.14 no.6
• /
• pp.6-11
• /
• 2000

The Purpose of this study was to investigate the Color Image according of Language and Nonlanguage stimulant. 185 university students were selected in this experimental study. The result of this study were as follow:It was classified into the sense of activity, warmth, refinement and weight by Factors Analysis. There was significant difference between Language and Nonlanguage stimulant. Namely, the evaluation of color image by Nonlanguage stimulant was expressed strong. In particular, Red and Yellow were not shown the difference of evaluation by the stimulant. But Blue and Green were shown the difference of evaluation.

• Journal of the Semiconductor & Display Technology
• /
• v.10 no.4
• /
• pp.95-100
• /
• 2011

This paper proposes a new method of vehicle brake lights detection and recognition using an R-filtering. Firstly, the proposed method processes the R-filtering with the first input image and then with the second one in order to detect brake lights. Secondly, the method counts the number of red pixels and computes the mean value in each R-filtered image. The difference rates between the numbers of the red pixels and between the mean values of two images are defined in this paper. Through the analysis of the difference rates, it can recognize whether brake lights are turned on or off, and whether the vehicle ahead is being approached or not. The proposed method is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiment results show that the proposed algorithm is quite successful.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.421-422
• /
• 2006

Using the still image through the camera reports which the moving object tracking system. Moving object direction detected to compare the two difference images. And base block set at moving object. Matching area set current difference image. The edge image of prior frame and current frame implement the moving object tracking system to block matching.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.7
• /
• pp.1677-1684
• /
• 1996

The theory of optimal stack filtering has been used in difference of estimates(DoE) approach to the detection of intensity edges in noisy image. In this approach, stack filters are applied to a noisy image to obtain local estimates of the dilated and eroded versions of the noise-free image. Thresholding the difference between these two estimates produces the estimated edge map. In this paper, the DoE approach is modified by imposing a symmetry condition of the data used to train the two stack filers. Under this condition, the stack filters obtained are duals of each other. Only one filter must therefore be trained;the other is simply its dual. They also produce statistially unbiased estimates. This new technique is called the symmetric Difference of Estimates (SDoE) approach.

• ETRI Journal
• /
• v.34 no.3
• /
• pp.410-420
• /
• 2012

A series of reversible watermarking technologies have been proposed to increase embedding capacity and the quality of the watermarked image simultaneously. The major skills include difference expansion, histogram shifting, and optimizing embedding order. In this paper, an accurate predictor is proposed to enhance the difference expansion. An efficient sorter is also suggested to find a more desirable embedding order. The payload is differently distributed into two sub-images, split like a chessboard pattern, for better watermarked image quality. Simulation results of the accurate prediction and sorter based on the payload balancing method yield generally better performance over previous methods. The gap is wide, in particular, in low payload for natural images. The peak signal-to-noise ratio improvement is around 2 dB in low payload ranges.

• Journal of Korea Multimedia Society
• /
• v.8 no.3
• /
• pp.379-388
• /
• 2005

Image steganography Is a secret communication scheme to transmit a secret message, which is embedded into an image. The original image and the embedded image are called the cover image and the stego image, respectively. In other words, a sender embeds a secret message into a cover image and transmits a stego image to a receiver, while the receiver takes the stego image, extracts the message from it, and reads the message. General requirements for steganography are great capacity of secret messages, imperceptibility of stego images, and confidentiality between a sender and a receiver. In this paper, we propose a method for being satisfied with three requirements. In order to hide a secret message into a cover image safely, we use a difference value of two consecutive pixels and a secret quantization range. The former is used for the imperceptibility and the latter for the confidentiality. Furthermore, the number of insertion bits is changed according to the difference value for the imperceptibility. Through experiments, we have shown that our method is more good quality of stego images than many other related methods and increases the amount o( message insertion by performing dual insertion processing for some pixels.

• Journal of the Korean Society of Costume
• /
• v.61 no.6
• /
• pp.101-112
• /
• 2011

The purpose of this study was to investigate the relationships among clothing image, make-up image, and hair image. The Data were collected from 306 women living in Gyeongnam province in June, 2009. Statistical analysis used in this study were frequency, F-test, t-test, Duncan test, factor analysis, Cronbach's ${\alpha}$, correlation coefficient, and multiple regression. The results of this study were as follows.: Three factors of clothing image were titled as elegance, youth, and visibility. Three factors of make-up image were titled as modern, romanticism, and mediocrity. Four factors of hair image were titled as attraction, individuality, gentleness, and cuteness. The clothing image, make-up image, and hair image according to the demographic characteristic of women showed significant difference. The clothing image resulted in correlation with the make-up image and hair image. The clothing image had a influence on the make-up image and hair image.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.655-658
• /
• 1998

This paper proposes a moving image compression algorithm using subband coding that divides and processes the differential image of each moving image frame into subband frequency. This method decomposes the original image with each subband and performs DCT. The moving blocks are detected from each of wubband using threshold value which is select from the variance of difference between frames. then they are performed SBDCT and huffman coding in order to reduce the data. As the result of simulation, we confirmed that this method improved the blocking effect of reconstructed image in low bit rate.