• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.10
• /
• pp.1234-1243
• /
• 1988

In this paper, a target tracking algorithm using the centroid of moving edges is presented. It aims to avoid the difficulty of image segmentation in case of extracting the centroid from only one frame. The proposed algorithm can more easily segment the target than the conventional one in images with complex background. Moreover, it can track the target well when the target is occluded by an object. The result of applying it to a real-time target tracker is shown to be comparatively good.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.474-478
• /
• 1999

Genetic algorithm is an efficient search method using principles of natural selection and population genetics. In conventional genetic algorithms, however, the size of gene pool should be increased to insure a convergency. Therefore, many memory spaces and much computation time were needed. Also, since child chromosomes were generated by chromosome crossover and gene mutation, the algorithms have a complex structure. Thus, in this paper, a compact stereo matching algorithm using a population-based incremental teaming based on probability vector is proposed to reduce these problems. The PBIL method is modified for matching environment. Since the Proposed algorithm uses a probability vector and eliminates gene pool, chromosome crossover, and gene mutation, the matching algorithm is simple and the computation load is considerably reduced. Even if the characteristics of images are changed, stable outputs are obtained without the modification of the matching algorithm.

• Journal of Digital Contents Society
• /
• v.6 no.1
• /
• pp.35-39
• /
• 2005

It is significantly important problem in computer what is estimating 3D information from 2D images. However, most of the related works have been interested in the analysis of the changes of 2D image, so that, they need much time to solve the complex equation and expensive device. In this paper, we first actively project the pattern of the sinusoidal wave into the object. Then, we measure the change of the phase from the distortion occurring according to the shape of the object, and we use the change of the phase in order to estimate the depth information. This is our proposal.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.7
• /
• pp.2496-2511
• /
• 2014

Face recognition is considered a complex biometrics in the field of image processing mainly due to the constraints imposed by variation in the appearance of facial images. These variations in appearance are affected by differences in expressions and/or occlusions (sunglasses, scarf etc.). This paper discusses incremental Kernel Fisher Discriminate Analysis on sub-classes for dealing with partial occlusions and variant expressions. This framework focuses on the division of classes into fixed size sub-classes for effective feature extraction. For this purpose, it modifies the traditional Linear Discriminant Analysis into incremental approach in the kernel space. Experiments are performed on AR, ORL, Yale B and MIT-CBCL face databases. The results show a significant improvement in face recognition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.7
• /
• pp.3284-3306
• /
• 2018

This study proposes a method to develop an authoring system(GeoMaTree) for diverse trees that constitute a virtual landscape. The GeoMaTree system enables the simple, intuitive production of an efficient structure, and supports real-time processing. The core of the proposed system is a procedural modeling based on a mathematical model and an application that supports digital content creation on diverse platforms. The procedural modeling allows users to control the complex pattern of branch propagation through an intuitive process. The application is a multi-resolution 3D model that supports appropriate optimization for a tree structure. The application and a compatible function, with commercial tools for supporting the creation of realistic synthetic images and virtual landscapes, are implemented, and the proposed system is applied to a variety of 3D image content.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.365-367
• /
• 2008

A digital city model represents a 3D environment of a city with various city object information such as 3D building model, road, and land cover. Usually, at least two satellite images with some image overlap are necessary and a complex satellite-related computation needs to be carried out to create a city model. This is an expensive technique, because it requires many resources and excessive computational cost. The authors propose a methodology to create a digital city model including 3D building model and land cover information from a single high resolution satellite image. The approach consists of image pan-sharpening, shadow recovery, building occlusion restoration, building model extraction, and land cover classification. We create a digital city model using a single KOMPSAT-2 image and review the result.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2403-2406
• /
• 2003

When viewing images, the relative luminance of the surround has a profound impact on the apparent contrast of the image. The dark surround causes the image elements to appear lighter than those viewed in an illuminated surround. For this reason, it is worthwhile to briefly review the general results of brightness sealing under a various viewing condition. Two of the most often cited parers on the topic of brightness scaling are Stevens-stevens and Bartleson-Breneman's function. There are, however, significant differences between the perceptual functions for simple-field and complex-field viewing. In this paper, we research the relationship between Steven's power law and Bartleson-Breneman's function. We present an appropriate brightness perception function due to TV system viewing conditions. Highlight luminance peak and absolute brightness threshold value in various adaptation levels are obtained from the proposed brightness function . Also, the luminance value of black level to produce the same contrast ratio with variety of display highlight luminance peak is obtained from the proposed brightness function.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.1
• /
• pp.122-129
• /
• 1998

For generation and analysis of the multi-sensory image, we propose a new three dimensional (3D) modeling method considering an iternal heat source. We represent the heat conduction process within th object as an equivalent thermal circuit. Therefore, without a complex computation, our modeling approach can obtain thermal features of the object. By using the faceted model, the proposed method can express the accurate visual signatures of the object. Comparing the estimates datum with the obtained surface temperatures, we have demonstrated that the proposed method can provide a precise thermal features. The thermal images by out model is applicable to simulate a tracking loop of an IR missile.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.15-17
• /
• 2006

This paper presents a new global intensity compensation method for extracting moving object in a visual surveillance system by compensating time variant intensity changes of background region. The method that compensates a little changes of intensity due to time variant illumination change and automatic gain control of camera is called global intensity compensation. The proposed method expresses global intensity change with a mapping table to describe complex form of intensity change while the previous method models this global intensity change with a simple function as a straight line. The proposed method builds the mapping table by calculating the cross histogram between two images and then by selecting an initial point for generating the mapping table by using Hough transform applied to the cross histogram image. Then starting from the initial point, the mapping table is generated according to the proposed algorithm based on the assumption that reflects the characteristic of global intensity change. Experimental results show that the proposed method makes the compensation error much smaller than the previous GIC method

• Journal of Korean Neurosurgical Society
• /
• v.51 no.4
• /
• pp.219-221
• /
• 2012

A 20-month-old boy presented with a intraparenchymal mass in the right frontoparietal area manifesting as complex partial seizure, secondary generalization and left hemiparesis. Magnetic resonance images (MRI) of the brain showed inhomogeneously enhancing mass in the right frontoparietal area which has irregular margin and perilesional edema. Based on the radiological findings, a preoperative diagnosis was an intraaxial tumor, such as pilocytic astrocytoma or dysembryoplastic neuroepithelial tumor. The patient underwent a surgery including frontal craniotomy. The tumor had a partially extreme adherence to the surrounding brain tissue but it showed no dural attachment. Gross-total resection of the tumor was achieved. Postoperative follow-up computed tomography scans showed no residual tumor. The pathological findings confirmed the tumor as a WHO grade I meningioma, transitional type. Nine months after the surgery, follow-up brain MRI showed no recurrence of the tumor, porencephaly in site where the tumor was resected; the patient's symptoms had fully recovered. We report the case of a meningioma in a 20-month-old boy.