• Journal of Internet of Things and Convergence
• /
• v.5 no.2
• /
• pp.15-20
• /
• 2019

As the machine learning research has developed, the field of translation and image analysis such as optical character recognition has made great progress. However, video translation that combines these two is slower than previous developments. In this paper, we develop an image translator that combines existing OCR technology and translation technology and verify its effectiveness. Before developing, we presented what functions are needed to implement this system and how to implement them, and then tested their performance. With the application program developed through this paper, users can access translation more conveniently, and also can contribute to ensuring the convenience provided in any environment.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.6
• /
• pp.88-94
• /
• 2008

A DCT-based energy-ratio measure for autofocus in digital camera is proposed in this paper. This measure, namely AC2DC1 and AC5DC1, determines the sharpness of an image using a ratio between AC and DC energy in the DCT domain. This method is derived from energy analysis of DCT coefficients. Autofocus score calculation method is used to assess the performance of the proposed measure and to compare it with other measures. Experimental results under various conditions verify the robustness of the proposed focus measure for the Gaussian as well as impulsive noises.

• Journal of Korea Multimedia Society
• /
• v.16 no.1
• /
• pp.29-41
• /
• 2013

The digital camera is impossible to preserve the appearance of a scene containing high dynamic range due to a limitations of the sensing hardware. The Retinex was proposed on the purpose to solve these problems. While the Retinex enhances visibility and color constancy, it sometimes suffers from color distortion, halo effect and reduced global contrast. This paper presents an advanced Retinex algorithm working on the YCbCr color coordinate to reduce the processing time and to improve the global contrast and color. Simulation results show that our algorithm significantly reduces the total processing time, and provide the superior result image by improving the global contrast and color consistency as well as by reducing the halo effect around the boundaries.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.919-926
• /
• 2023

In this paper, we implemented the surveillance camera system capable of day and night shooting. To this end, it is designed to capture clear images even at night using a CMOS image sensor as well as an IR-LED. In addition, a relatively simple motion detection algorithm was proposed through color model separation. Motions can be detected by extracting only the H channel from the color model, dividing the image into blocks, and then applying the block matching method using the average color value between consecutive frames. When motions are detected during filming, an alarm sounds automatically and a day and night motion detection system is implemented that can capture and save the event screen to a PC.

• Science of Emotion and Sensibility
• /
• v.14 no.2
• /
• pp.321-330
• /
• 2011

Images of smoky make up illustrations with different the brightness tones for typical Korean eyes (standard one, small single eyelid and tailed up style) were systematically analyzed using vision-based emotional descriptive language for students majoring makeup and professional group. We identified that various images could be expressed by changing smoky makeup tones on eyes types through analysis of the emotional descriptive language. The smoky make up image recognition of smoky make up illustrations was almost consistent between the students and the professional group, but there was the distinct difference of image perception by two groups for some smoky make up illustrations due to the generation gap as well as their make up expertise and techniques. We suggested the image positioning maps which expressed the emotional reaction felt according to eyes shapes and smoky make up tones. The positioning maps were to provide criteria for various images to be able to express by smoky make up.

• Cartoon and Animation Studies
• /
• s.38
• /
• pp.93-114
• /
• 2015

In the history of animation, which created by Yuri Norstein is one of the best animations in the world. Out of all animations that Yuri Norstein created, is one animation that most people have hard time to understand because unexpected images and complicated structure of this animation get us confused. And also since this animation is based on Yuri Norstein's childhood memories and his own experiences, people who doesn't understand Russian culture and history will be lost. The purpose of this study is to analyze created by Yuri Norstein through the crystal-image in of Deleuze. According to Deleuze, we can see and understand unorganized time through the crystal-image which is the door way understanding and recognizing the time-image. In the there are some of the crystal-image appears. Eternity episode is one of the Crystal-images. In eternity episode we can see a peaceful life as simply continue endlessly. This is also the part that shows subject of animation and time itself accoding to Deleuze. By Yuri Norstein reflects Deleuze's claims that time-image we think and realize through crystal-image is eventually human life and universe.

• 한국HCI학회:학술대회논문집
• /
• 2008.02b
• /
• pp.30-35
• /
• 2008

The purpose of this study is to analyze and define user's emotional satisfaction factors to the PC OS GUI image. The study is to investigate the relationship between PC OS GUI Image and Sensitive Vocabula교 based on user's emotional preference. 47 user preferred sensitive words are collected by the initial survey. Through the similarity test, 47 words are narrowed down to 20 comprehend words. The semantic differential methods is used in the final survey with 5 step questionnaire. From this process, user preferred the GUI design that is vocabularized as Clear, Easy, Safety, Stability. Additionally, the result shows that the image of Clear is related to Safety and the image of Easy is related to Stability. The result of the study could be used in design PC OS GUI as base data.

• Trans-
• /
• v.11
• /
• pp.119-142
• /
• 2021

Video was a cultural practice based on image. The audience longs to experience new things, not everyday things through by video images. There are many components of the image, but among them, color, a visual representation, plays a big role. Since the advent of color films, color has constantly evolved as an important component of visual art and has become an important role in innovative visual art design. According to film history data, filmmakers were interested in color since the film was created in 1895, but in the early stages of film development, film colors were only black and white. Because these two colors no longer satisfy viewers, more natural colors began to emerge from the film as it was colored. However, with the development of historical paintings, the lack of artistic creation and the public's level increased, making people more active in using colors because simple reproduction of natural colors alone does not satisfy people. The colors in the video are both techniques of expression and can be understood by mind and thought. It is also an indication that colors do not just exist, but they work strongly on human psychology. Now people are so motivated by repetitive and unimportant information that they find that the human intuitive system simplifies the information they receive unconsciously that they have certain customs and characteristics when they see things. Color is part of the film language, or color language can express the film's ideological themes or portray vivid characters in the film, and people are receiving more intuitive messages. This study analyzed the basic color components of bisexual lighting, namely, pink, blue, and purple, and analyzed how human psychology is affected through color, combining the scenes from the video. The purpose of this paper is to explore what color language bisexual lighting is expressed using color properties in images and how bisexual lighting interacts with human psychology through color.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.6
• /
• pp.485-491
• /
• 2022

Intravenous injection is the most frequent invasive treatment for inpatients and is widely used for parenteral nutrition administration and blood products, and more than 1 billion procedures are used for peripheral catheter insertion, blood collection, and other IV therapy per year. Intravenous injection is one of the difficult procedures to be performed only by trained nurses with intravenous injection training, and failure can lead to thrombosis and hematoma or nerve damage to the vein. Accordingly, studies on auxiliary equipment capable of visualizing the vein structure of the back of the hand or arm are being published to reduce errors during intravenous injection. This study is a study on the performance difference according to the number of LEDs irradiating the 850nm wavelength band on a vein detector that visualizes the vein during intravenous injection. Four LED PCBs were produced by attaching NIR filters to CCD and CMOS camera lenses irradiated on the skin to acquire images, sharpen the acquired images using image processing algorithms, and project the sharpened images onto the skin. After that, each PCB was attached to the front end of the vein detector to detect the vein image and create a performance comparison questionnaire based on the vein image obtained for performance evaluation. The survey was conducted on 20 nurses working at K Hospital.

• Journal of the Korean Society of Radiology
• /
• v.84 no.1
• /
• pp.240-252
• /
• 2023

Purpose To assess the effect of deep learning image reconstruction (DLIR) for head CT in pediatric patients. Materials and Methods We collected 126 pediatric head CT images, which were reconstructed using filtered back projection, iterative reconstruction using adaptive statistical iterative reconstruction (ASiR)-V, and all three levels of DLIR (TrueFidelity; GE Healthcare). Each image set group was divided into four subgroups according to the patients' ages. Clinical and dose-related data were reviewed. Quantitative parameters, including the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), and qualitative parameters, including noise, gray matter-white matter (GM-WM) differentiation, sharpness, artifact, acceptability, and unfamiliar texture change were evaluated and compared. Results The SNR and CNR of each level in each age group increased among strength levels of DLIR. High-level DLIR showed a significantly improved SNR and CNR (p < 0.05). Sequential reduction of noise, improvement of GM-WM differentiation, and improvement of sharpness was noted among strength levels of DLIR. Those of high-level DLIR showed a similar value as that with ASiR-V. Artifact and acceptability did not show a significant difference among the adapted levels of DLIR. Conclusion Adaptation of high-level DLIR for the pediatric head CT can significantly reduce image noise. Modification is needed while processing artifacts.