• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.3
• /
• pp.117-122
• /
• 2023

Gaze estimation, which automatically recognizes where a user is currently staring, and object detection based on estimated gaze point, can be a more accurate and efficient way to understand human visual behavior. in this paper, we propose a method to detect the objects within the region of interest around the gaze point. Specifically, after estimating the 3D gaze point, a region of interest based on the estimated gaze point is created to ensure that object detection occurs only within the region of interest. In our experiments, we compared the performance of general object detection, and the proposed object detection based on region of interest, and found that the processing time per frame was 1.4ms and 1.1ms, respectively, indicating that the proposed method was faster in terms of processing speed.

• Journal of Broadcast Engineering
• /
• v.11 no.1 s.30
• /
• pp.80-90
• /
• 2006

A simple 2D gaze tracking method using single camera and Purkinje image is proposed. This method employs single camera with infrared filter to capture one eye and two infrared light sources to make reflection points for estimating corresponding gaze point on the screen from user's eyes. Single camera, infrared light sources and user's head can be slightly moved. Thus, it renders simple and flexible system without using any inconvenient fixed equipments or assuming fixed head. The system also includes a simple and accurate personal calibration procedure. Before using the system, each user only has to stare at two target points for a few seconds so that the system can initiate user's individual factors of estimating algorithm. The proposed system has been developed to work in real-time providing over 10 frames per second with XGA $(1024{\times}768)$ resolution. The test results of nine objects of three subjects show that the system is achieving an average estimation error less than I degree.

• The Journal of Korean Association of Computer Education
• /
• v.5 no.4
• /
• pp.134-145
• /
• 2002

The purpose of this study is to present the functional and technical solutions for text learning of web-based textbook in which each letter has its own focal point. The solutions help learners not to lose the main focus when eye moves to the next letter or line. The text screen of the electronic textbook automatically scrolls the text to up and down or left and right directions which are preassigned by learner. It doesn't need the operation of mouse or keyboard. And learner can change scroll speed and types anytime during scrolling. Automatic text scroll function is a solution for controlling data and screen to reflect the personal favor and ability. It contains the content structure of the text(characteristics, categorizations etc.), the appearance of the text(density, size, font etc.), scroll options(scroll, speed etc.), program control type(ram resident program etc.), and the application of the screen design principles(legibility etc.). To resolve these functional problems, technical 8 phases are provided, which are environment setting, scroll option setting, copy, data analysis, scroll coding, centered focus coding, left and right focus coding, implementation. The learner can focus on text without dispersion because the text focal points stay in the fixed area of screen. 1bey read the text following their preferences for fonts, sizes, line spacing and so on.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.79-86
• /
• 2005

In this paper, we propose a new LINF(Linear Independent Non-negative Factorization) algorithm for real-time face recognition systea This system greatly consists of the two parts: 1) face extraction part; 2) face recognition part. In the face extraction Part we applied subtraction image, the detection of eye and mouth region , and normalization method, and then in the face recognition Part we used LINF in extracted face candidate region images. The existing recognition system using only PCA(Principal Component Analysis) showed low recognition rates, and it was hard in the recognition system using only LDA(Linear Discriminants Analysis) to apply LDA directly when the training set is small. To overcome these shortcomings, we reduced dimension as the matrix that had non-negative value to be different from former eigenfaces and then applied LDA to the matrix in the proposed system We have experimented using self-organized DAIJFace database and ORL database offered by AT(')T laboratory in Cambridge, U.K. to evaluate the performance of the proposed system. The experimental results showed that the proposed method outperformed PCA, LDA, ICA(Independent Component Analysis) and PLMA(PCA-based LDA mixture algorithm) method within the framework of recognition accuracy.

• Journal of Korean Ophthalmic Optics Society
• /
• v.10 no.4
• /
• pp.313-321
• /
• 2005

To know the pollution level concerning the microbes contamination condition in soft contact lenses, 2 experiments were operated with different methods. Firs experiment, we observed lenses surfaces through a scanning electronic microscope after pollution sort contact lenses with the suspensions of Staphylococcus aureus, Pseudomonas aeruginosa and Entrobacter aerogenes which can be major bacteria causing keratitis as wearing on soft contact lenses. As 1 hour after pollution with the soft contact lenses, we observed that many bacteria adhered to the lenses, and the pollution condition got worse with passing time increase(2, 4, 6, 12, and 24 hours, respectively). At 12 hours lapse of polluting soft contact lenses with P. aeruginosa, some bacteria adhered to the lenses. And as 24 hours lapsed after pollution soft lenses with E. aerogenes, bacteria adhered to them, and atypical substance was observed some of the surface of lenses. Second experiment, we observed the microbe pollution condition in soft contact lenses by let 21 people in twenties(men & women), who doesn't eye disorders, wear soft contact lenses during 4 hours. As the result, many kinds of bacterium and fungus were observed, and especially, the bacteria could be identified with their colors and the shapes of colony, so we found that single type, two types, and three types of bacteria adhered to their lenses.

• 한국가시화정보학회:학술대회논문집
• /
• 2002.04a
• /
• pp.51-78
• /
• 2002

A number of research groups worldwide are studying electronic implants that can be mounted on retinal optic nerve/visual cortex to restore vision of patients suffering from retinal degeneration. The implants consist of a neural interface made of biocompatible materials, one or more integrated circuits for stimuli generation, a camera, an image processor, and a telemetric channel. The realization of these classes of neural prosthetic devices is largely due to the explosive development of micro- and nano-electronics technologies in the late $20^{th}$ century and biotechnologies more recently. Animal experiments showed promise and some human experiments are in progress to indicate that recognition of images can be obtained and improved over time. We, at NBS-ERC of SNU, have started our own retinal implant project in 2000. We have selected polyimide as the biomaterial for an epi-retinal stimulator. In-vitro and in-vivo biocompatibility studies have been performed on the electrode arrays. We have obtained good affinity to retinal pigment epithelial cells and no harmful effect. The implant also showed very good stability and safety in rabbit eye for 12 weeks. We have also demonstrated that through proper stimulation of inner retina, meaning vision can be obtained.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.4 no.2
• /
• pp.111-118
• /
• 2011

It is not easy to define a boundary between TV and home computer in these day since developing H/W and S/W of computer technology induces that TV is conflated with computer. Coming digital HD broadcasting forces for replacement of TV at home and the trend of TV is became bigger. The evolved TV is able to replace the computer by connecting to the network and people want to do interactions with contents by using the bidirectional communication. Therefore, it is expected to changing the human lifestyle. It is natural that contents for all members of family are needed, since screen of TV become bigger. It is required that the contents should guarantees the accessability of information to the all of family members and the easy interaction with contents. But, the related basic research is not enough to catch the user's eye to induce flow or presence. Our goal of this study is to analyse effects of experiential space perception on performing interactive digital contents. The result shows that users interacted with contents without any difficulty when they met a same dimension and shape of objects as dimension and shape objects in their experiences or learning.

• Investigative Magnetic Resonance Imaging
• /
• v.16 no.1
• /
• pp.67-75
• /
• 2012

Purpose : We studied enhanced method to view the vessels in the brain using Magnetic Resonance Angiography (MRA). Noticing that Maximum Intensity Projection (MIP) image is often used to evaluate the arteries of the neck and brain, we propose a new method for view brain vessels to stereo image in 3D space with more superior and more correct compared with conventional method. Materials and Methods: We use 3T Siemens Tim Trio MRI scanner with 4 channel head coil and get a 3D MRA brain data by fixing volunteers head and radiating Phase Contrast pulse sequence. MRA brain data is 3D rotated according to the view angle of each eyes. Optimal view angle (projection angle) is determined by the distance between eye and center of the data. Newly acquired MRA data are projected along with the projection line and display only the highest values. Each left and right view MIP image is integrated through anaglyph imaging method and optimal stereoscopic MIP image is acquired. Results: Result image shows that proposed method let enable to view MIP image at any direction of MRA data that is impossible to the conventional method. Moreover, considering disparity and distance from viewer to center of MRA data at spherical coordinates, we can get more realistic stereo image. In conclusion, we can get optimal stereoscopic images according to the position that viewers want to see and distance between viewer and MRA data. Conclusion: Proposed method overcome problems of conventional method that shows only specific projected image (z-axis projection) and give optimal depth information by converting mono MIP image to stereoscopic image considering viewers position. And can display any view of MRA data at spherical coordinates. If the optimization algorithm and parallel processing is applied, it may give useful medical information for diagnosis and treatment planning in real-time.

• Radiation Oncology Journal
• /
• v.27 no.1
• /
• pp.42-48
• /
• 2009

Purpose: The introduction of image guided radiation therapy/four-dimensional radiation therapy (IGRT/4DRT) potentially increases the accumulated dose to patients from imaging and verification processes as compared to conventional practice. It is therefore essential to investigate the level of the imaging dose to patients when IGRT/4DRT devices are installed. The imaging dose level was monitored and was compared with the use of pre-IGRT practice. Materials and Methods: A four-dimensional CT (4DCT) unit (GE, Ultra Light Speed 16), a simulator (Varian Acuity) and Varian IX unit with an on-board imager (OBI) and cone beam CT (CBCT) were installed. The surface doses to a RANDO phantom (The Phantom Laboratory, Salem, NY USA) were measured with the newly installed devices and with pre-existing devices including a single slice CT scanner (GE, Light Speed), a simulator (Varian Ximatron) and L-gram linear accelerator (Varian, 2100C Linac). The surface doses were measured using thermo luminescent dosimeters (TLDs) at eight sites-the brain, eye, thyroid, chest, abdomen, ovary, prostate and pelvis. Results: Compared to imaging with the use of single slice non-gated CT, the use of 4DCT imaging increased the dose to the chest and abdomen approximately ten-fold ($1.74{\pm}0.34$ cGy versus $23.23{\pm}3.67$cGy). Imaging doses with the use of the Acuity simulator were smaller than doses with the use of the Ximatron simulator, which were $0.91{\pm}0.89$ cGy versus $6.77{\pm}3.56$ cGy, respectively. The dose with the use of the electronic portal imaging device (EPID; Varian IX unit) was approximately 50% of the dose with the use of the L-gram linear accelerator ($1.83{\pm}0.36$ cGy versus $3.80{\pm}1.67$ cGy). The dose from the OBI for fluoroscopy and low-dose mode CBCT were $0.97{\pm}0.34$ cGy and $2.3{\pm}0.67$ cGy, respectively. Conclusion: The use of 4DCT is the major source of an increase of the radiation (imaging) dose to patients. OBI and CBCT doses were small, but the accumulated dose associated with everyday verification need to be considered.