• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.2
• /
• pp.19-25
• /
• 2018

A scientific and systematic approach for digitally representing colours is essential for improving image quality. Therefore, there is a need for objectively analysing such approaches. Studies regarding display systems, which can reflect human visual characteristics in the digital media environment, and associated international standards at the forefront, have already caused significant impact. Colour is one of the most important factors employed for evaluating the overall image quality of displays. The proposed study focusses on colour properties which are based on the characteristics of the human peripheral vision area, with the primary objective of reproducing digital colours which can simulate human visual characteristics in the digital media environment. The proposed study aims at identifying digital colour characteristics which can vary according to the level of background lightness and the size of colour stimuli. Based on the evaluation results obtained through psychophysical experiments, a method has been proposed for determining peripheral vision characteristics which vary according to the increasing size of a colour stimulus, thereby digitally reproducing them on displays.

• Journal of Biosystems Engineering
• /
• v.36 no.1
• /
• pp.48-57
• /
• 2011

The computer vision system was designed and constructed to measure the weight of a dairy cattle. Its development involved the functions of image capture, image preprocessing, image algorithm, and control integrated into one program. The experiments were conducted with the model dairy cattle and the real dairy cattle by two ways. First experiment with the model dairy cattle was conducted by using the indoor vision experimental system, which was built to measure the model dairy cattle in the laboratory. Second experiment with real dairy cattle was conducted by using the outdoor vision experimental system, which was built for measuring 229 heads of cows in the cattle facilities. This vision system proved to a reliable system by conducting their performance test with 15 heads of real cow in the cattle facilities. Indirect weight measuring with four methods were conducted by using the image processing system, which was the same system for measuring of body parameters. Error value of transform equation using chest girth was 30%. This error was seen as the cause of accumulated error by manually measurement. So it was not appropriate to estimate cow weight by using the transform equation, which was calculated from pixel values of the chest girth. Measurement of cow weight by multiple regression equation from top and side view images has relatively less error value, 5%. When cow weight was measured indirectly by image surface area from the pixel of top and side view images, maximum error value was 11.7%. When measured cow weight by image volume, maximum error weight was 57 kg. Generally, weight error was within 30 kg but maximum error 10.7%. Volume transform method, out of 4 measuring weight methods, was minimum error weight 21.8 kg.

• Korean Journal of Construction Engineering and Management
• /
• v.11 no.4
• /
• pp.68-79
• /
• 2010

During the last two decades, several tele-operated and machine-vision-assisted systems have been developed in construction and maintenance area such as pavement crack sealing, sewer pipe rehabilitation, and excavation. In developing such tele-operated and machine-vision-assisted systems, trajectory plans are very important tasks for optimal motions of robots whether their environments are structured or unstructured. This paper presents an optimal trajectory planning algorithm used for a machine-vision-assisted automatic pavement crack sealing system. In this paper, the performance of the proposed optimal trajectory planning algorithm is compared with the greedy trajectory plans which are used in previously developed pavement crack sealing systems. The comparison is based on computational cost versus overall gains in crack sealing efficiency. Finally, it is concluded that the proposed algorithm plays an important role in productivity improvement of the automatic pavement crack sealing system developed.

• Child Health Nursing Research
• /
• v.8 no.2
• /
• pp.164-173
• /
• 2002

The vision disturbances of school-age children has been recognized as and important school health problem. The purpose of this study is to describe the current status of the visual health and to explore the related factors for the decrease in visual acuity in the elementary school age children. The study subjects were 697 children (Boys: 338, Girls: 359) of 4th to 6th grade in two school in urban area. The visual acuity data of the school health examination in 1999 and 2000 were utilized for analysis. The questionnaire for children and parents was used for survey. The findings were as follows. 1. The prevalance rate of the children with the visual acuity less than 0.7 on the left eye were 26.84％ ( Grade 4), 31.30％ (Grade 5), and 38.39％ (Grade 6). The rate on the right eye were 28.31％ (Grade4), 30.37％ (Grade 5), and 37.92％ (Grade 6). There was a significant difference in the rate of the visual acuity less than 0.7 according to grade (p<.01). 2.The rate of visual acuity decrease was 40.12％. 3. The factors related to the decrease in the visual acuity were grade, sex, genetic factor, posture, and the awareness of the visual acuity. There was more decrease in the visual acuity when the children were in higher grade (O.R= 1.06), girls (O.R=2.29). Children having parents with better vision (Father: O.R=1.26; Mother O.R= 1.25) showed better vision. On the other hand, when the children have siblings with glasses, there was more decrease in the visual acuity (O.R=2.31). Students with good posture during study (sitting on the chair) and watching TV to the lower direction showed less decrease in the visual acuity. Also, when the students know their visual acuity, the rate of decrease were lower. The variables which odds ratio were statistically significant were sex (p<.01), siblings with glasses (p <.01), and awareness of visual acuity (p<.01).

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.9-14
• /
• 2018

The vision system is a device for acquiring images and analyzing and discriminating inspection areas. Demand for use in the automation process has increased, and the introduction of a vision-based inspection system has emerged as a very important issue. These vision systems are used for everyday life and used as inspection equipment in production processes. Image processing technology is actively being studied. However, there is little research on the area definition for extracting objects such as character recognition or semiconductor packages. In this paper, define a region of interest and perform edge extraction to prevent the user from judging noise as an edge. We propose a noise-robust alignment correction model that can extract the edge of a region to be inspected using the distribution of edges in a specific region even if noise exists in the image. Through the proposed model, it is expected that the product production efficiency will be improved if it is applied to production field such as character recognition of tire or inspection of semiconductor packages.

• Smart Media Journal
• /
• v.11 no.4
• /
• pp.30-37
• /
• 2022

Disease threatens plant growth and recognizing the type of disease is essential to making a remedy. In recent years, deep learning has witnessed a significant improvement for this task, however, a large volume of labeled images is one of the requirements to get decent performance. But annotated images are difficult and expensive to obtain in the agricultural field. Therefore, designing an efficient and effective strategy is one of the challenges in this area with few labeled data. Transfer learning, assuming taking knowledge from a source domain to a target domain, is borrowed to address this issue and observed comparable results. However, current transfer learning strategies can be regarded as a supervised method as it hypothesizes that there are many labeled images in a source domain. In contrast, unsupervised transfer learning, using only images in a source domain, gives more convenience as collecting images is much easier than annotating. In this paper, we leverage unsupervised transfer learning to perform plant disease recognition, by which we achieve a better performance than supervised transfer learning in many cases. Besides, a vision transformer with a bigger model capacity than convolution is utilized to have a better-pretrained feature space. With the vision transformer-based unsupervised transfer learning, we achieve better results than current works in two datasets. Especially, we obtain 97.3% accuracy with only 30 training images for each class in the Plant Village dataset. We hope that our work can encourage the community to pay attention to vision transformer-based unsupervised transfer learning in the agricultural field when with few labeled images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.6
• /
• pp.1183-1188
• /
• 2016

Kinect sensor version 2 is a kind of camera released by Microsoft as a computer vision and a natural user interface for game consoles like Xbox one. It allows acquiring color images, depth images, audio input and skeletal data with a high frame rate. In this paper, using depth image, we present a surveillance system of a certain area within Kinect's field of view. With computer vision library(Emgu CV), if an object is detected in the target area, it is tracked and kinect camera takes RGB image to send it in database server. Therefore, a mobile application on android platform was developed in order to notify the user that Kinect has sensed strange motion in the target region and display the RGB image of the scene. User gets the notification in real-time to react in the best way in the case of valuable things in monitored area or other cases related to a reserved zone.

• Journal of Advanced Navigation Technology
• /
• v.14 no.4
• /
• pp.553-561
• /
• 2010

This paper proposed the face tracking method which can be effectively applied to the robot's vision system. The proposed algorithm tracks the facial areas after detecting the area of video motion. Movement detection of video images is done by using median filter and erosion and dilation operation as a method for removing noise, after getting the different images using two continual frames. To extract the skin color from the moving area, the color information of sample images is used. The skin color region and the background area are separated by evaluating the similarity by generating membership functions by using MIN-MAX values as fuzzy data. For the face candidate region, the eyes are detected from C channel of color space CMY, and the mouth from Q channel of color space YIQ. The face region is tracked seeking the features of the eyes and the mouth detected from knowledge-base. Experiment includes 1,500 frames of the video images from 10 subjects, 150 frames per subject. The result shows 95.7% of detection rate (the motion areas of 1,435 frames are detected) and 97.6% of good face tracking result (1,401 faces are tracked).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.8
• /
• pp.1737-1744
• /
• 2010

The Image sensor needs various image processing to improve image quality. ISP(Image Signal Processor) performs various image processing. Conventional vision cameras have own software ISP functions and perform in PC instead of using commercial ISP chips. However these methods have problems such as large computation for image processing. In this paper, we proposed ISP that significantly reduced chip area by efficient sharing of hardware and software. Large operation blocks are designed to hardware for high performances, and we used hardware simultaneously with software considering the size of the hardware. The implemented ISP can process VGA(640*4800) images and has 91450 gate sizes in 0.35um process.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.191-199
• /
• 2021

This study aims to present the need to supplement the driver's license renewal test for elderly drivers. In Korea, the proportion of elderly drivers is increasing as the elderly population increases rapidly. Overall the traffic accident rate is decreasing but the traffic accident and death rate from traffic accidents are increasing in older drivers. In this study the assessments and education conducted when renewing the driver's license for elderly drivers conducted in Korea were conducted to find out the necessary tests compared to the current situation of foreign countries. Although it is appropriate to evaluate the three key functional areas of vision, cognition, motor and somatosensory, we currently evaluate visual acurity in vison area. While MMSE-K and Clock drawing tests are not recognizable for mild cognitive impairment in cognitive areas. The motor and somato sensory function to perform driving are not evaluated at all. Therefore for safe driving of older drivers, the test to be conducted during renewal of the driver's license will need to supplement that the visual field and contrast sensitivity in vision area, cognitive function from mild cognitive impairments, and the endurance, functional range of motion and proprioception in motor function area.