• Journal of Broadcast Engineering
• /
• v.4 no.2
• /
• pp.119-126
• /
• 1999

We proposed an algorithm which detects scene changes in video with speediness and accuracy. It is a two-step approach. In the first step, we decide potential scene change segments using the compressed domain data extracted by temporal sampling of MPEG compressed video. In the second step, we determine the exact scene change positions using the pixel values of each frame in those segments by means of combining the intensity and edge changes. In addition we discuss the method to remove false detection generated from camera flash. Integrating the above methods, we introduce a structure that can detect scene changes speedily and accurately.

• Korean Journal of Remote Sensing
• /
• v.28 no.6
• /
• pp.611-622
• /
• 2012

This study proposed two multisensor fusion methods for segment-based image classification utilizing a region-growing segmentation. The proposed algorithms employ a Gaussian-PDF measure and an evidential measure respectively. In remote sensing application, segment-based approaches are used to extract more explicit information on spatial structure compared to pixel-based methods. Data from a single sensor may be insufficient to provide accurate description of a ground scene in image classification. Due to the redundant and complementary nature of multisensor data, a combination of information from multiple sensors can make reduce classification error rate. The Gaussian-PDF method defines a regional measure as the PDF average of pixels belonging to the region, and assigns a region into a class associated with the maximum of regional measure. The evidential fusion method uses two measures of plausibility and belief, which are derived from a mass function of the Beta distribution for the basic probability assignment of every hypothesis about region classes. The proposed methods were applied to the SPOT XS and ENVISAT data, which were acquired over Iksan area of of Korean peninsula. The experiment results showed that the segment-based method of evidential measure is greatly effective on improving the classification via multisensor fusion.

• Journal of Fashion Business
• /
• v.20 no.2
• /
• pp.78-96
• /
• 2016

This study investigated the colors of the costumes and backgrounds of characters in the fantasy film, Alice in Wonderland(2010) by Tim Burton. The methods used were literature studies including related books, articles and internet materials, and positive research with DVD color analysis. Twenty-one scenes were selected by the researcher. Five scenes were selected from novel and film components representing, exposition, complication, crisis, climax, and denouement. After controlled pixel by photoshop program and the represented colors, hues and tones were analyzed. The results were as follows; First, in four characters, Alice's dress colors changed depend on the situation and the passage offered from blue to red, metal light, and blue green. The Mad Hatter's colors were orange with green which signified madness and passion. The Red Queen's red dress and blue make up represented countrified and evil. The White Queen's all white dress and hair, black eyes and vivid red meant purity and nobility. Similar characters' colors were limited. Second, the background colors, especially tones were an important component of the fantasy image. These were different for each type of scene in the film such as exposition, complication, crisis, climax, and denouement.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2005.07a
• /
• pp.781-784
• /
• 2005

We have developed technology to fabricate large-size active matrix organic light-emitting diode (AMOLED) displays with good color purity. Using these innovations, we have developed a 40inch diagonal WXGA AMOLED full color display. Because the TFT circuitry occupies a large portion of the pixel structure, an efficient white emission OLED is essential to integrate the device onto the active matrix backplane. The development of these technologies enables OLED displays to fulfill the requirements for larger size applications such as HDTVs

• Journal of the Semiconductor & Display Technology
• /
• v.16 no.1
• /
• pp.106-111
• /
• 2017

When a substrate with a pixel-defining layer (bank) is coated, there arises capillary force due to surface tension and adhesive forces between a solvent and the bank layer. It brings in a degradation of film thickness and emission uniformities within pixels. With an attempt to suppress it, we have performed fluid flow simulations of capillary arise by varying the contact angle of bank and the bank structure. We have first demonstrated that the fluid flow model can reproduce the capillary phenomenon that was observed experimentally. It has been found that capillary arise can be suppressed using a hydrophobic material for the bank layer. Furthermore, it was suppressed by tilting the sidewalls outwardly (i.e., using a positive photoresistor). We can obtain very uniform films when the slope is $50^{\circ}$ with the contact angle of $40^{\circ}$.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.11 no.4
• /
• pp.89-97
• /
• 2015

In this paper, a method of color image segmentation based on DBSCAN(Density Based Spatial Clustering of Applications with Noise) using compactness of superpixels and texture information is presented. The DBSCAN algorithm can generate clusters in large data sets by looking at the local density of data samples, using only two input parameters which called minimum number of data and distance of neighborhood data. Superpixel algorithms group pixels into perceptually meaningful atomic regions, which can be used to replace the rigid structure of the pixel grid. Each superpixel is consist of pixels with similar features such as luminance, color, textures etc. Superpixels are more efficient than pixels in case of large scale image processing. In this paper, superpixels are generated by SLIC(simple linear iterative clustering) as known popular. Superpixel characteristics are described by compactness, uniformity, boundary precision and recall. The compactness is important features to depict superpixel characteristics. Each superpixel is represented by Lab color spaces, compactness and texture information. DBSCAN clustering method applied to these feature spaces to segment a color image. To evaluate the performance of the proposed method, computer simulation is carried out to several outdoor images. The experimental results show that the proposed algorithm can provide good segmentation results on various images.

• Journal of Ginseng Research
• /
• v.36 no.4
• /
• pp.469-476
• /
• 2012

Raw ginseng root of Panax ginseng is graded according to its shape and the quality of its internal tissue. A variety of grades are sold with prices according to grade. If an inferior raw ginseng is purchased, the consumer experience an economic loss. This research was conducted in order to explore the possibility of developing a noninvasive method for investigating raw ginseng's internal tissue. It has been determined that computed tomography (CT) scanner images agreed with actual cross-sections of raw ginseng. CT images were obtained to assess the internal portions of raw ginseng, and CT scans of raw ginseng were thoroughly measured using the Hounsfield unit (HU) system, since it allows for a more detailed analysis compared to nuclear magnetic resonance imaging. HU is a measure of attenuation used for CT images, with each pixel being assigned a value using a scale on which air is defined as -1000, water as 0 and compact bone as +1000. It takes about one second to process are slice and produce an image of the raw ginseng by a one channel CT scanner. An image good enough to discriminate the internal tissues can be obtained in 1/24 seconds with a one-channel CT scanner. Using this method, images of raw ginseng can be obtained and the characteristics of the internal tissues can be observed in a short time.

• Journal of the Semiconductor & Display Technology
• /
• v.12 no.2
• /
• pp.27-32
• /
• 2013

Shape From Focus (SFF) is a passive optical technique to recover 3D structure of an object that utilizes focus information from 2D images of the object taken at different focus levels. Mostly, SFF methods use a single focus measure to compute image focus quality of each pixel in the image sequence. However, it is difficult to recover accurate 3D shape using a single focus measure, as different focus measures perform differently in diverse conditions. In this paper, a nonlinear Total Variation (TV) based approach is proposed for 3D shape recovery. To improve the result of surface reconstruction, several initial depth maps are obtained using different focus measures and the resultant 3D shape is obtained by diffusing them through TV. The proposed method is tested and evaluated by using image sequences of synthetic and real objects. The results and comparative analysis demonstrate the effectiveness of our method.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.11 no.2
• /
• pp.104-110
• /
• 2011

A CMOS Image Sensor (CIS) mounted on mobile appliances requires low power consumption due to limitations of the battery life cycle. In order to reduce the power consumption of CIS, we propose novel power reduction techniques such as a data flip-flop circuit with leakage current elimination and a low power single slope analog-to-digital (A/D) converter with a sleep-mode comparator. Based on 0.13 ${\mu}m$ CMOS process, the chip satisfies QVGA resolution (320 ${\times}$ 240 pixels) that the cell pitch is 2.25 um and the structure is a 4-Tr active pixel sensor. From the experimental results, the performance of the CIS has a 10-b resolution, the operating speed of the CIS is 16 frame/s, and the power dissipation is 25 mW at a 3.3 V(analog)/1.8 V(digital) power supply. When we compare the proposed CIS with conventional ones, the power consumption was reduced by approximately 22% in the sleep mode, and 20% in the active mode.

• Journal of Korea Game Society
• /
• v.20 no.3
• /
• pp.15-24
• /
• 2020

We present a reinforcement learning-based framework for generating 2D Lego puzzle from input pixel art images. We devise heuristics for a proper Lego puzzle as stability and efficiency. We also design a DQN structure and train it to maximize the heuristics of 2D Lego puzzle. In legorization stage, we complete the layout of Lego puzzle by adding a Lego brick to the input image using the trained DQN. During this process, we devise a region of interest to reduce the computational loads of the legorization. Using this approach, our framework can present a very high resolutional Lego puzzle.