• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.4
• /
• pp.2757-2763
• /
• 2015

p-Snake is an energy minimizing algorithm that applies an additional prototype energy to the existing Active Contour Model and is used to extract the contour line in the area where the edge information is unclear. In this paper suggested the creation of a prototype energy field that applies a variable prototype expressed as a combination of circle and straight line primitives, and a fudge function, to improve p-Snake's contour extraction performance. The prototype was defined based on the parts codes entered and the appropriate initial contour was extracted in each primitive zones acquired from the pre-processing process. Then, the primitives variably adjusted to create the prototype and the contour probability based on the distance to the prototype was calculated through the fuzzy function to create the prototype energy field. This was applied to p-Snake to extract the contour from 100 images acquired from various small parts and compared its similarity with the prototype to find that p-Snake made with the adaptive prototype was about 4.6% more precise than the existing Snake method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.17 no.1
• /
• pp.32-39
• /
• 2016

Intelligent Transport Systems (Intelligent Transportation System: ITS) is a system for inducing a flow of ideal car for using the most advanced technology, it is determined the status of the road, and take appropriate action. In order to be measured at various time points, and is managed, the information about the traffic situation is used image using a computer mainly. The image processing using a computer, it is an easy way to collect parameters of the various traffic in real time, technology has developed more and more. Vehicle detection of transport parameters of intelligent transportation system is a very important technology basically. Therefore, technology detection method using car background images and the contour line extraction method using an edge is used, however, problems have been raised on the accuracy of the detection rate.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.930-938
• /
• 2007

Captions which appear in images include information that relates to the images. In order to obtain the information carried by captions, the methods for text extraction from images have been developed. However, most existing methods can be applied to captions with fixed height of stroke's width. We propose a method which can be applied to various caption size. Our method is based on connected components. And then the edge pixels are detected and grouped into connected components. We analyze the properties of connected components and build a neural network which discriminates connected components which include captions from ones which do not. Experimental data is collected from broadcast programs such as news, documentaries, and show programs which include various height caption. Experimental result is evaluated by two criteria : recall and precision. Recall is the ratio of the identified captions in all the captions in images and the precision is the ratio of the captions in the objects identified as captions. The experiment shows that the proposed method can efficiently extract captions various in size.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.2
• /
• 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 Digital Convergence
• /
• v.18 no.3
• /
• pp.189-194
• /
• 2020

Recently, various clustering techniques have been studied to efficiently handle data generated by heterogeneous IoT devices. However, existing clustering techniques are not suitable for mobile IoT devices because they focus on statically dividing networks. This paper proposes a probabilistic deep learning-based dynamic clustering model for collecting and analyzing information on IoT devices using edge networks. The proposed model establishes a subnet by applying the frequency of the attribute values collected probabilistically to deep learning. The established subnets are used to group information extracted from seeds into hierarchical structures and improve the speed and accuracy of dynamic clustering for IoT devices. The performance evaluation results showed that the proposed model had an average 13.8 percent improvement in data processing time compared to the existing model, and the server's overhead was 10.5 percent lower on average than the existing model. The accuracy of extracting IoT information from servers has improved by 8.7% on average from previous models.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.2
• /
• 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 Oral Medicine and Pain
• /
• v.26 no.2
• /
• pp.147-156
• /
• 2001

The purpose of this study was to identify the difference of vertical movement of mandible according to Angle's molar relationship and by skeletal factors affect to vertical movement of mandible. 172(age ranged from 20 to 30) subjects who go to college within territory of Kwangju city without any experience of temporomandibular disorder, extraction and orthodontic treatment. were selected for this study. The subjects were classified into class I(male:30, female:49), class II(male:18, female:24) and class III(male:18, female:33) according to Angle's molar relationship. The distance was measured between incisal edge of maxillary and mandibular central incisor and between bottom of central fossa of maxillary and mandibular 1st molar with ruler. The arch length and width were measured on the diagnostic cast. Cephalometrics were taken and then traced. Landmarks were identified and analyzed. 1. Maximal interincisal opening of male is larger than that of female in class I, class II and class III. Among each group maximal interincisal distance is the largest in class III. Maximal intermolar distance of male is superior to that of female in class I, class II, and class III, but there is no siginficant difference among them. 2. On maximal opening movement of Angle's classification class I and class II, total mandibular length, mandibular ramal length, madibular inferior border length and upper arch width were important variables and facial length, upper arch length and lower arch length had negative relationship to that. On maximal opening movement of Angle's class III, the upper arch length, the lower arch length and anterior facial length were important variables especially when compared with class I and II, and upper arch width had negative relationship. These results suggest that maximal opening movement is affected by facial morphology in all classes, but each group is affected by different facial skeletal variables. Accordingly, facioskeletal variables might be considered as diagnosis and treatment to improve the amount of mouth opening.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.8B
• /
• pp.1549-1557
• /
• 1999

In this paper, we propose a face recognition algorithm based on the differential image method-DCT This algorithm uses neural networks which is flexible for noise. Using the same condition (same luminous intensity and same distance from the fixed CCD camera to human face), we have captured two images. One doesn't contain human face. The other contains human face. Differential image method is used to separate the second image into face region and background region. After that, we have extracted square area from the face region, which is based on the edge distribution. This square region is used as the characteristics region of human face. It contains the eye bows, the eyes, the nose, and the mouth. After executing DCT for this square region, we have extracted the feature vectors. The feature vectors were normalized and used as the input vectors of the neural network. Simulation results show 100% recognition rate when face images were learned and 92.25% recognition rate when face images weren't learned for 30 persons.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.12B
• /
• pp.2359-2368
• /
• 1999

In this paper we propose a 2D FLIR image-based 3D target recognition system which performs group-to-ground vehicle recognition using the target contour and its degree of reliability extracted from FLIR image. First we extract target from background in FLIR image. Then we define contour points of the extracted target which have high edge gradient magnitude and brightness value as reliable contour point and make reliable contour by grouping all reliable contour points. After that we extract corresponding reliable contours from model contour image and perform comparison between scene and model features which are calculated by DST(discrete sine transform) of reliable contours. Experiment shows that the proposed algorithm work well and even in case of imperfect target extraction it showed better performance then conventional 2D contour-based matching algorithms.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.5
• /
• pp.331-337
• /
• 2020

The study is underway with the goal of developing an app that will replace vernier calipers using a smartphone's high-performance camera. The specifications of the camera mounted on recent smart phones have evolved so that usually has a 12 Mpixels of image sensor and its size of the pixel is 1.4㎛ and the size of the image sensor is 1 / 2.55 in. The proposed algorithm will apply to develop a precision measuring application that will compete with the Vernier calipers. Most existing applications cannot guarantee an accuracy in scale because the scale of the ruler displayed on the image is unclear or the size of the measurement object varies depending on the distance between the camera and the measurement object. In addition, another accurate measuring tools using lasers are also available, but they are limited because they are expensive. Therefore, if easy-to-carry and precise applications are developed, it is possible to substitute existing measurement tools. The proposed correction algorithm is an algorithm that automatically corrects the distorted source image using the shape and size information of the known template. The e-calipers are applications that display the distance when the area to be measured is specified in the corrected image.