• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.11
• /
• pp.2273-2276
• /
• 2009

As parents are interested in music education for infants in these days, they require systems to help these infants to actively play music. In this paper, we propose a keyboard solo system using a real time hand recognition method. In order to enable the infants to use the system easily, the proposed system plays some sounds whenever the infants move their fingers on a paper piano. For the purpose of minimizing cost to play music, the proposed system utilizes a general PC with only a paper piano, a web camera, and a speaker. With the aim of precisely and efficiently recognizing both a hand and each key on keyboard, the proposed system divides a recognition step into a hand recognition step and a keyboard recognition step. Also, the hand recognition step considers only skin color, and the keyboard recognition step considers only black and white without other colors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.9
• /
• pp.1987-1992
• /
• 2010

This paper deals with the method of using the three dimensional characteristic information to classify the front environment in travelling by using the images captured by a CCD camera equipped on a mobile robot. The images detected by the three dimensional characteristic information is divided into the part of obstacles, the part of corners, and th part of doorways in a corridor. In designing the travelling path of a mobile robot, these three situations are used as an important information in the obstacle avoidance and optimal path computing. So, this paper proposes the method of deciding the travelling direction of a mobile robot with using input images based upon the suggested algorithm by preprocessing, and verified the validity of the image information which are detected as obstacles by the analysis through neural network.

• Journal of Convergence for Information Technology
• /
• v.10 no.10
• /
• pp.123-127
• /
• 2020

In order to obtain the overall fire line information of medium and large forest fires at night, the ground control system was developed to determine whether forest fires occurred through real-time video clips and to calculate the location of the forest fires determined using the location of drones, angle information of video cameras, and altitude information on the map to reduce the time required for regular video matches obtained after the completion of the mission. To verify the reliability of the developed function, the error distance of the aiming position information of the flight altitude star and the image camera was measured, and the location information within the reliable range was displayed on the map. As the function developed in this paper allows real-time identification of multiple locations of forest fires, it is expected that overall fire line information for the establishment of forest fire extinguishing measures will be obtained more quickly.

• Journal of the Korean Wood Science and Technology
• /
• v.45 no.6
• /
• pp.797-808
• /
• 2017

Automatic wood species identification systems have enabled fast and accurate identification of wood species outside of specialized laboratories with well-trained experts on wood species identification. Conventional automatic wood species identification systems consist of two major parts: a feature extractor and a classifier. Feature extractors require hand-engineering to obtain optimal features to quantify the content of an image. A Convolutional Neural Network (CNN), which is one of the Deep Learning methods, trained for wood species can extract intrinsic feature representations and classify them correctly. It usually outperforms classifiers built on top of extracted features with a hand-tuning process. We developed an automatic wood species identification system utilizing CNN models such as LeNet, MiniVGGNet, and their variants. A smartphone camera was used for obtaining macroscopic images of rough sawn surfaces from cross sections of woods. Five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch) were under classification by the CNN models. The highest and most stable CNN model was LeNet3 that is two additional layers added to the original LeNet architecture. The accuracy of species identification by LeNet3 architecture for the five Korean softwood species was 99.3%. The result showed the automatic wood species identification system is sufficiently fast and accurate as well as small to be deployed to a mobile device such as a smartphone.

• Korean Journal of Optics and Photonics
• /
• v.19 no.2
• /
• pp.95-102
• /
• 2008

An advantage of parallax barrier displays is that they can also display 2D and 3D contents and can be automatically switched between the two types. But, as the viewer changes position, different views of the scene will be directed by the barrier to the visual system. Moving horizontally beyond a certain point will produce "image flipping" of the different views of the scene. These limitations make unavoidable the use of another autostereoscopic display solutions like eye tracking or increasing the number of views. In this paper, a method of the moving parallax barrier design is introduced to supplement a disadvantage of the fixed parallax barrier that provides observation at specific locations. For making the moving parallax barrier, the cross connector with 640 lines FPC is designed. A commercially available web camera is utilized to implement eye-tracking system and shows the experimental result.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.26 no.6
• /
• pp.606-612
• /
• 2000

This study was performed to investigate the average anthropometric value of normal Korean men and women and to compare the preceding literatures. Additionally, average Korean profilogram was made to serve as a template for diagnosis of facial form. Eighty five Korean subjects(41 men, 44 women) aged between 21 to 26 were selected by members of the author's department on the basis of intact dentition and Class I occlusion without facial asymmetry. Frontal and lateral photographs were taken under standardized condition with digital camera. The image was magnified and adjusted according to the FH plane of cephalometric radiographs and digitized using personal computer. To compare the Western beauty, 25 esthetically pleasing female was selected to measure various angle and distance of the face. 1. It was possible to calculate the mean coordinate value of Korean normal samples which enables the direct visualization and comparison with the use of template. The method in this study was easy to applicate under the Microsoft $Windows^{(R)}$ bases. 2. Maxillary vertical hypoplasia, upper and lower lip protrusion was characteristics of Korean norms and relatively narrow alar base distance, less conspicuous nasal projection was observed. As the vermilion exposure and upper lip length was more than western norm, chin looks shorter than western. To compare the Korean and Western esthetically pleasing profile, facial convexity and nose was less conspicuous in Korean women.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.3
• /
• pp.127-137
• /
• 2018

Recently, UAVs and Drones have been used for various applications. In particular, in the field of surveying, there are studies on the technology for monitoring the terrain based on the high resolution image data obtained by using the UAV-equipped digital camera or various sensors, or for generating high resolution orthoimage, DSM, and DEM. In this study, we analyzed the accuracy of GCP(Ground control point) matching using UAV and VRS-GPS. First, we used VRS-GPS to pre-empt the ground reference point, and then imaged at a base altitude of 150m using UAV. To obtain DSM and orthographic images of 646 images, RMSE was analyzed using pix4d mapper version As a result, even if the number of GCP matches is more than five, the error range of the national basic map(scale : 1/5,000) production work regulations is observed, and it is judged that the digital map revision and gauging work can be utilized sufficiently.

• Journal of Digital Convergence
• /
• v.16 no.3
• /
• pp.303-309
• /
• 2018

Computer vision technology is a component inspection to obtain a video image from the camera to the machine to perform the capabilities of the human eye with a field of artificial intelligence, and then analyzed by the algorithm to determine to determine the good and bad of production parts It is widely applied. Shape inspection method was used as how to identify the location of the start point and the end point of the search range, measure the height to the line scan method, in such a manner as to determine the presence or absence of the bolt tabs average brightness of the inspection area in a circular scan type value And the degree of similarity was calculated. The total time it takes to test in the test performance tests of two types of bolts tab enables test 300 min, and demonstrated the accuracy and efficiency of the inspection on the production line represented a complete inspection accuracy.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.7
• /
• pp.167-174
• /
• 2013

Various smart phone applications have been widely developed and an intelligent service to take a picture for the visually handicapped is needed. By using an auditory service and/or other's help, the blind capture an image with their cameras for keeping a record or exchanging the information with another people. However, they are difficult to take the wanted picture because they are unable to grasp the visual contents in the viewfinder. This paper presents a novel guiding system for the blind people to take a picture with the smart phone. The proposed method identifies a person in the picture and determines the presence of eye blinks and blurring. The system provides a guiding information such as camera directions, which are transferred into the blind user with auditory service.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.7 no.4
• /
• pp.163-172
• /
• 2012

A driver assistance system is critical to improve a convenience and stability of vehicle driving. Several systems have been already commercialized such as adaptive cruise control system and forward collision warning system. Efficient vehicle detection is very important to improve such driver assistance systems. Most existing vehicle detection systems are based on a radar system, which measures distance between a host and leading (or oncoming) vehicles under various weather conditions. However, it requires high deployment cost and complexity overload when there are many vehicles. A camera based vehicle detection technique is also good alternative method because of low cost and simple implementation. In general, night time vehicle detection is more complicated than day time vehicle detection, because it is much more difficult to distinguish the vehicle's features such as outline and color under the dim environment. This paper proposes a method to detect vehicles at night time using analysis of a captured color space with reduction of reflection and other light sources in images. Four colors spaces, namely RGB, YCbCr, normalized RGB and Ruta-RGB, are compared each other and evaluated. A suboptimal threshold value is determined by Otsu algorithm and applied to extract candidates of taillights of leading vehicles. Statistical features such as mean, variance, skewness, kurtosis, and entropy are extracted from the candidate regions and used as feature vector for SVM(Support Vector Machine) classifier. According to our simulation results, the proposed statistical feature based SVM provides relatively high performances of leading vehicle detection with various distances in variable nighttime environments.