• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.225-229
• /
• 2020

Recently, convolutional neural network (CNN) have been showed outstanding performance in the field of image recognition, image processing and computer vision, etc. In this paper, we propose a CNN-based image rotation correction algorithm as a solution to image rotation problem, which is one of the factors that reduce the recognition rate in image recognition system using CNN. In this paper, we trained our deep learning model with Leeds Sports Pose dataset to extract the information of the rotated angle, which is randomly set in specific range. The trained model is evaluated with mean absolute error (MAE) value over 100 test data images, and it is obtained 4.5951.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.220-223
• /
• 2004

Automatic image registration is an essential element of remote sensing because remote sensing system generates enormous amount of data, which are multiple observations of the same features at different times and by different sensor. The general process of automatic image registration includes three steps: 1) The extraction of features to be used in the matching process, 2) the feature matching strategy and accurate matching process, 3) the resampling of the data based on the correspondence computed from matched feature. For step 2) and 3), we have developed an algorithms for automated registration of satellite images with RANSAC(Random Sample Consensus) in success. However, for step 1), There still remains human operation to generate GCP Chips, which is time consuming, laborious and expensive process. The main idea of this research is that we are able to automatically generate GCP chips with comer detection algorithms without GPS survey and human interventions if we have systematic corrected satellite image within adaptable positional accuracy. In this research, we use SUSAN(Smallest Univalue Segment Assimilating Nucleus) algorithm in order to detect the comer. SUSAN algorithm is known as the best robust algorithms for comer detection in the field of compute vision. However, there are so many comers in high-resolution images so that we need to reduce the comer points from SUSAN algorithms to overcome redundancy. In experiment, we automatically generate GCP chips from IKONOS images with geo level using SUSAN algorithms. Then we extract reference coordinate from IKONOS images and DEM data and filter the comer points using texture analysis. At last, we apply automatically collected GCP chips by proposed method and the GCP by operator to in-house automatic precision correction algorithms. The compared result will be presented to show the GCP quality.

• Journal of Digital Contents Society
• /
• v.16 no.2
• /
• pp.179-187
• /
• 2015

Spread of smartphone creates various contents. Among many contents, AR application using Location Based Service(LBS) is needed widely. In this paper, we propose error correction algorithm for location-based Augmented Reality(AR) system using computer vision technology in android environment. This method that detects the early features with SURF(Speeded Up Robust Features) algorithm to minimize the mismatch and to reduce the operations, and tracks the detected, and applies it in mobile environment. We use the GPS data to retrieve the location information, and use the gyro sensor and G-sensor to get the pose estimation and direction information. However, the cumulative errors of location information cause the mismatch that and an object is not fixed, and we can not accept it the complete AR technology. Because AR needs many operations, implementation in mobile environment has many difficulties. The proposed approach minimizes the performance degradation in mobile environments, and are relatively simple to implement, and a variety of existing systems can be useful in a mobile environment.

• Journal of Korean Clinical Health Science
• /
• v.7 no.2
• /
• pp.1337-1344
• /
• 2019

Purpose. This study was the analyze the refractive status of presbyopia in Korea. Methods. The subjects was from November 2018 to October 2019, two hundred thirty four subjects( 117 male subjects, 117 female subjects; from 40-year old to 88-year old ) were performed in refraction test using the Auto-Refraction(Speed -K model, Japan). The myopia, hyperopia, astigmatism, and anisometropia were defined as spherical equivalent(SE)≤-0.50 diopters, SE ≥+1.00 D, cylinder error ≥0.75 D and SE difference≥1.00 D between binocular eyes, respectively. Results. The refractive status by spherical equivalent among all subjects was myopia 61.43%, astigmatism 86.86%, emmetropia 19.18%, anisometropia 12.07%, and hyperopia 18.54. The prevalence of myopia and astigmatism were much more common in male. However, The hyperopia and astigmatism were much more common in female. The prevalence of spherical equivalent was much common from -0.50 diopter to -5.00 diopter. On the other hand, the prevalence of astigmatism and myopia was much more than hyperopia in all subjects. There was a statistical significance between OD and OS of the female and male in the spherical equivalent power(p<.000). However, there was not statical significant between female and male of OD and OS in the spherical equivalent power(p<.070). On the other hand, The prevalence of againest axis in astigmatism was more common in all subjects. In ADD power for the near vision correction, the female was much more diopter than male. Conclusions. These results suggested that the analysis of the refractive status on the presbyopia in Korea can give the useful diagnosis data for the correction of visual acuity at near distance.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.45 no.5
• /
• pp.417-428
• /
• 2017

In this paper, we describe the architectural design, unit component hardware design and core software design(Helmet Pose Tracking Software and Terrain Elevation Data Correction Software) of IHDS(Intelligent Helmet Display System), and describe the results of unit test and integration test. According to the trend of the latest helmet display system, the specifications which includes 3D map display, FLIR(Forward Looking Infra-Red) display, hybrid helmet pose tracking, visor reflection type of binocular optical system, NVC(Night Vision Camera) display, lightweight composite helmet shell were applied to the design. Especially, we proposed unique design concepts such as the automatic correction of altitude error of 3D map data, high precision image registration, multi-color lighting optical system, transmissive image emitting surface using diffraction optical element, tracking camera minimizing latency time of helmet pose estimation and air pockets for helmet fixation on head. After completing the prototype of all system components, unit tests and system integration tests were performed to verify the functions and performance.

• Journal of Korean Ophthalmic Optics Society
• /
• v.5 no.1
• /
• pp.107-116
• /
• 2000

This study is of investigation of refraction error, spectacles and contact lenses wearing state, visual acuity test, ophthalmologic common sense and vision care, using questionnaire study for 850 male and female high school students in Kunsan and Chongup City, Cheolla North Province. The results are as follows: 1. Among the 823 answerers, emmetropia is 18%, myopia is 55.1%, and hyperopia is 7%, respectively. 2. Among the 837 answerers, 381 students(45.5%) wear spectacles or contact lenses. Among the 381 students who wear spectacles or contact lenses, 78% wear only spectacles, 4% wear only contact lenses and 18% wears spectacles sometimes or contact lenses sometimes. 3. The places where the answerers had visual acuity test to wear spectacles or contact lenses are optical shop(64.7%), hospital(28.3%), unchecked(4.2%) and the others(2.7%). The places where the answerers had visual acuity test to change their spectacles or contact lenses are optical shop(82%), hospital(28.3%), unchecked(6.6%) and the others(1.9%). 4. As for the period of visual acuity test, from 6 months to one year is 54.1%, within 6 months is 9.2%, from one year to two years is 29.5%, and more than two years is 7.2%. 5. The contact lens wearers purchased their contact lenses at optical shops(94%) and at hospital(6%). 6. The reasons why they like wearing contact lenses are their appearance(51.2%), convenience in physical excercise(23.l%), lighter weight than spectacles(9.8%) and the others(15.7%). 7. As for the spectacles frame they like, plastic frame is 24.4%, gold or silver plated frame is 43.4%, coloured frame is 32.1%. 8. As for the considerations in choosing spectacles frame, their design is 37%, their quality is 36%, their price is 14.7% and their brand is 12.5%. 9. As for the period for changing spectacles, 10.5% is within 6 months, 57.3% is 6months to 1 year, 22.4% is 1 year to 2 months and 9.6% is more than 2 years. 10. There is a false fact, in Korea, that even though one has his poor eyesight, not wearing custom is helpful for the eyesight recovery. As for their conviction of the false fact, 10.5% of the answerers have 100% conviction, 22.5% of them have 22.5% conviction, 49.5% of them have 50% conviction and 17.5% of them don't have any conviction. 11. 48.5% of the answerers are interested in their vision care while 51.5% of them are not interested at all. As for the way of vision care, the vision-care way to keep enough distant when they are watching TV, when they are using computers and when they are reading, is 49% while the vision-care way such as hypogastric breathing or eye massage is 11%. And alimentotherapy is 4% and the rest who are not interested in vision care is 36%. 12. When they come to an age, the students who want vision correction operation are 45.9% while the students who do not want it are 27%. The students who do not have any idea about the operation are 27.1%

• Journal of Korean Ophthalmic Optics Society
• /
• v.15 no.2
• /
• pp.137-144
• /
• 2010

Purpose: This study was to evaluate the clinical performance of 1-Day disposable toric soft contact lenses (TSCL) and to compare the visual performance with glasses and TSCL. Methods: In a two-week investigation of 'prism ballast' designed TSCL, occular refractions in 15 (30 eyes) healthy subjects were within the range of -2.75 D TO -8.00 D spherical power and -0.75 DC to -2.25 DC cylinderical power (with-the-rule). Subjects were assessed the clinical performance (orientation, centration, movement, tightness, rotation recovery, symptoms) of TSCL and compared binocular vision and contrast sensitivity with corrected glasses and TSCL at initial and two-week follow-up visits. Results: The prism-ballast design TSCL achieved better orientation, rotation recovery and symptoms over 2 week period. There was no statistically significant difference between spectacles and TSCL with respect to measuring binocular vision and contrast sensitivity. Conclusions: The clinical performance was good with prism-ballast design toric soft contact lenses. Evaluation of binocular vision and contrast sensitivity did not show the differences between spectacles and TSCL correction. This study suggests that TSCL wearers can be achieved similar visual performance for spectacles wearers.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.2
• /
• pp.1414-1419
• /
• 2015

A method for detecting a skin region on the image is generally used to detect the color information. However, If saturation lowered, skin detection is difficult because hue information of the pixels is lost. So in this paper, we propose a method of correcting color of lower saturation of skin region images by the lighting. Color correction process of this method is saturation image acquisition and low-saturation region classification, segmentation, and the saturation of the split in the low saturation region extraction and color values, the color correction sequence. This method extracts the low saturation regions in the image and extract the color and saturation in the region and the surrounding region to produce a color similar to the original color. Therefore, the method of extracting the low saturation region should be correctly preceding. Because more accurate segmentation in the process of obtaining a low saturation regions, we use a multi-threshold method proposed Otsu in Hue values of the HSV color space, and create a binary image. Our experimental results for 170 portrait images show a possibility that the proposed method could be used efficiently preprocessing of skin color detection method, because the detection result of proposed method is 5.8% higher than not used it.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.3
• /
• pp.219-226
• /
• 2013

A distortion correction technique is presented to enhance the 3D scanning performance of a micro-size camera-projector system. Recently, several types of micro-size digital projectors and cameras are available. However, there have been few effort to develop a micro-size 3D scanning system. We develop a micro-sized 3D scanning system which is based on the structured light technique. Three images of phase-shifted sinusoidal patterns are projected, captured, and analyzed by the system to reconstruct 3D shapes of very small objects. To overcome inherent optical imperfection of the micro 3D sensor, we correct the vignetting and blooming effects which cause distortions in the phase image. Error analysis and 3D scanning results on small real objects are presented to show the performance of the developed 3D scanning system.

• Korean Journal of Remote Sensing
• /
• v.30 no.3
• /
• pp.367-373
• /
• 2014

Albedo is one of the critical parameters for understanding global climate change and energy/water balance. In this study, we used red and NIR reflectance from Satellite Pour I'Obervation de la Terre (SPOT)/Vegetation (VGT) S1 product. The product is preprocessed for users that they are atmospherically corrected using Simple Method Atmospheric Correction (SMAC) by Vision on Technology (VITO) for calculating broadband albedo. Roujean's Bi-directional Reflectance Distribution Function (BRDF) model is a semi-empirical method used for BRDF angular integration and inversion. Each kernel of Roujean's model was multi integrated by angle components (i.e., viewing zenith, solar zenith, and relative azimuth angle). Black-sky hemispherical function is integrated by observational angle; whereas, white-sky hemispherical efficient is integrated by incident angle. Estimated spectral albedo of red ($0.61{\sim}0.68{\mu}m$, B2) and near infrared ($0.79{\sim}0.89{\mu}m$, B3) have a good agreement with MODIS albedo products.