• Journal of the Korean Institute of Intelligent Systems
• /
• 제18권2호
• /
• pp.169-174
• /
• 2008

Recently, biometric systems are of interest for the reliable security system. Iris recognition technology is one of the biometric system with the highest reliability. Various iris recognition methods have been proposed for automatic personal identification and verification. These methods require accurate iris segmentation for successful processing because the iris is a small part of an acquired image. The iris boundaries have been parametrically modeled and subsequently detected by circles or parabolic arcs. Since the iris boundaries have a wide range of edge contrast and irregular border shapes, the assumption that they can be fit to circles or parabolic arcs is not always valid. In some cases, the shape of a dilated pupil is slightly different from a constricted one. This is especially true when the pupil has an irregular shape. This is why this research is important. This paper addresses how to accurately detect iris boundaries for improved iris recognition, which is robust to noises.

• Journal of the Society of Naval Architects of Korea
• /
• 제42권6호
• /
• pp.619-630
• /
• 2005

A two-frame PIV (Particle Image Velocimetry) technique is used to investigate the wake characteristics behind a marine propeller with 4 blades at high Reynolds number. For each of 9 different blade phases from $ 0^{\circ} $ to $ 80^{\circ} $, one hundred and fifty instantaneous velocity fields are measured. They are ensemble averaged to study the spatial evolution of the propeller wake in the region ranging from the trailing edge to one propeller diameter (D) downstream location. The phase-averaged mean velocity shows that the trailing vorticity is related to radial velocity jump, and the viscous wake is affected by boundary layers developed on the blade surfaces and centrifugal force. Both Galilean decomposition method and vortex identification method using swirling strength calculation are very useful for the study of vortex behaviors En the propeller wake legion. The slipstream contraction occurs in the near-wake region up to about X/D : 0.53 downstream. Thereafter, unstable oscillation occurs because of the reduction of interaction between the tip vortex and the wake sheet behind the maximum contraction point.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• 제36S권1호
• /
• pp.104-114
• /
• 1999

This paper proposes an efficient method for the automatic generation of personalized 3D face model from color image sequence. To detect a robust facial region in a complex background, moving color detection technique based on he facial color distribution has been suggested. Color distribution and edge position information in the detected face region are used to extract the exact 31 facial feature points of the facial description parameter(FDP) proposed by MPEG-4 SNHC(Synthetic-Natural Hybrid Coding) adhoc group. Extracted feature points are then applied to the corresponding vertex points of the 3D generic face model composed of 1038 triangular mesh points. The personalized 3D face model can be generated automatically in less then 2 seconds on Pentium PC.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• 제46권2호
• /
• pp.44-51
• /
• 2009

Text understand in natural images has become an active research field in the past few decades. In this paper, we present an automatic recognition system in Korean signboards with a complex background. The proposed algorithm includes detection, binarization and extraction of text for the recognition of shop names. First, we utilize an elaborate detection algorithm to detect possible text region based on edge histogram of vertical and horizontal direction. And detected text region is segmented by clustering method. Second, the text is divided into individual characters based on connected components whose center of mass lie below the center line, which are recognized by using a minimum distance classifier. A shape-based statistical feature is adopted, which is adequate for Korean character recognition. The system has been implemented in a mobile phone and is demonstrated to show acceptable performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제18권12호
• /
• pp.2953-2960
• /
• 2014

In the field of image recognition, circle detection is one of the most widely used techniques. Conventional algorithms are mainly based on Hough transform, which is the most straightforward algorithm for detecting circles and for providing enough robust algorithm. However, it suffers from large memory requirements and high computational loads, and sometimes tends to detect incorrect circles. This paper proposes an optimal circle detection and approximation method which is applicable for inspecting fiber optic connector endface. The proposed method finds initial center coordinates and radius based on the initial edge lines. Then, by introducing the simplified K-means algorithm, the proposed method investigates a substitute-circle by minimizing the area of non-overlapped regions. Through extensive simulations, it is shown that the proposed method can improve the error rate by as much as 67% and also can reduce the computing time by as much as 80%, compared to the Hough transform provided by the OpenCV library.

• Korean Journal of Agricultural Science
• /
• 제47권2호
• /
• pp.205-217
• /
• 2020

In this study, a deep learning-based tillage boundary detection method for autonomous tillage by a tractor was developed, which consisted of image cropping, object classification, area segmentation, and boundary detection methods. Full HD (1920 × 1080) images were obtained using a RGB camera installed on the hood of a tractor and were cropped to 112 × 112 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the path boundary was detected using a probability map, which was generated by the integration of softmax outputs. The results show that the F1-score of the classification was approximately 0.91, and it had a similar performance as the deep learning-based classification task in the agriculture field. The path boundary was determined with edge detection and the Hough transform, and it was compared to the actual path boundary. The average lateral error was approximately 11.4 cm, and the average angle error was approximately 8.9°. The proposed technique can perform as well as other approaches; however, it only needs low cost memory to execute the process unlike other deep learning-based approaches. It is possible that an autonomous farm robot can be easily developed with this proposed technique using a simple hardware configuration.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국해양정보통신학회 2005년도 추계종합학술대회
• /
• pp.981-984
• /
• 2005

Recently, filtering methods for attenuating noise while preserving image details are in progress actively. And SM(standard median) fille. showed a great performance for noise removal in impulse noise environment but, it caused edge cancellation error So, variable methods that modified SM(standard median)filter have been proposed, and CWM(center weighted median) filter is representative. Also, there are several methods to improve the efficiency based on min/max operation in term of preserving detail and filtering speed. In this paper, we managed a pixel corrupted by impulsive noise using min/max value of the surrounding band enclosing a pixel, and compared the efficiency with exiting methods in the simulation.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• 제16권3호
• /
• pp.41-48
• /
• 2012

Objectives: The aims of this study are to design a optimized mechanical structure of digital tongue imaging system (DTIS) equipped with LEDs in aspects of object distance and camera angle of coverage. Methods and Results: We tried to find optimized object distance while recording a rectangular object of common tongue size. In case object distance is 22 cm or less, edge of the rectangle was not taken beyond the shooting range. In contrast, if object distance is 40 cm or more, the rectangle image was too small. Therefore when considering the variation of subjects, we selected distance of 35-40 cm as appropriate object distance for the DTIS. We also tried to find optimized angle between camera view axis and horizontal line. We photographed from the side of the face of 7 adults with exposed tongue. We drew an exposed tongue lines to connect the tongue tip points and the tongue root points by using the photos acquired from the side faces. And then we calculated the tongue exposure angles between the vertical line and the exposed tongue lines. Mean tongue exposure angle was $28.3^{\circ}$ when tongue was lightly exposed and $13.3^{\circ}$ when maximally. So we determined $73^{\circ}$ as appropriate slope angle of part in contact with face of the DTIS and by considering that the standard variation was great, we designed control gears to adjust the slope of the camera view axis and to regulate the object distance. Conclusions: We designed a optimized mechanical structure in object distance and slope angle of part in contact with face of the DTIS.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제29권11C호
• /
• pp.1518-1526
• /
• 2004

In this paper, an algorithm using wavelet transform for detecting a cut that is a radical scene transition point, and fade and dissolve that are gradual scene transition points is proposed. The conventional methods using wavelet transform for this purpose is using features in both spatial and frequency domain. But in the proposed algorithm, the color space of an input image is converted to YUV and then luminance component Y is transformed in frequency domain using 2-level lifting. Then, the histogram of only low frequency subband that may contain some spatial domain features is compared with the previous one. Edges obtained from other higher bands can be divided into global, semi-global and local regions and the histogram of each edge region is compared. The experimental results show the performance improvement of about 17% in recall and 18% in precision and also show a good performance in fade and dissolve detection.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제13권10호
• /
• pp.1997-2003
• /
• 2009

Methods for effective musical score recognition and efficient editing of musical scores are demanded because functions of computers for researches on musical activities become more and more important parts in recent days. In the conventional methods for handling musical scores manually, there are weak points such as incorrect score symbols in input process and requirement of much time to adjust the incorrect symbols. And also there is another weak point that the scores edited by each application program can be remodified by a specific application program only. In this paper, we proposed a method for automatic musical score recognition of printed musical scores in order to make up for the weak points. In the proposed method, staffs in a scanned score image are eliminated by horizontal histogram, noises are removed by 4 directional edge tracking algorithm, and then musical score symbols are extracted by using Grassfire algorithm. The extracted symbols are recognized by hierarchical ART2 algorithm. In order to evaluate the performance of the proposed method, we used 100 musical scores for experiment. In the experiment, we verified that the proposed method using hierarchical ART2 algorithm is efficient.