• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.11
• /
• pp.5436-5458
• /
• 2017

Automatic Video Surveillance System (AVSS) has become important to computer vision researchers as crime has increased in the twenty-first century. As a new branch of AVSS, baggage detection has a wide area of security applications. Some of them are, detecting baggage in baggage restricted super shop, detecting unclaimed baggage in public space etc. However, in this paper, a detection & classification framework of baggage is proposed. Initially, background subtraction is performed instead of sliding window approach to speed up the system and HSI model is used to deal with different illumination conditions. Then, a model is introduced to overcome shadow effect. Then, occlusion of objects is detected using proposed mirroring algorithm to track individual objects. Extraction of rotational signal descriptor (SP-RSD-HOG) with support plane from Region of Interest (ROI) add rotation invariance nature in HOG. Finally, dynamic human body parameter setting approach enables the system to detect & classify single or multiple pieces of carried baggage even if some portions of human are absent. In baggage detection, a strong classifier is generated by boosting similarity measure based multi layer Support Vector Machine (SVM)s into HOG based SVM. This boosting technique has been used to deal with various texture patterns of baggage. Experimental results have discovered the system satisfactorily accurate and faster comparative to other alternatives.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.10B
• /
• pp.1111-1116
• /
• 2009

In this paper, we discuss distortion-tolerant pattern recognition using computational integral imaging reconstruction. Three-dimensional object information is captured by the integral imaging pick-up process. The captured information is numerically reconstructed at arbitrary depth-levels by averaging the corresponding pixels. We apply Fisher linear discriminant analysis combined with principal component analysis to computationally reconstructed images for the distortion-tolerant recognition. Fisher linear discriminant analysis maximizes the discrimination capability between classes and principal component analysis reduces the dimensionality with the minimum mean squared errors between the original and the restored images. The presented methods provide the promising results for the classification of out-of-plane rotated objects.

• The korean journal of orthodontics
• /
• v.30 no.6 s.83
• /
• pp.687-698
• /
• 2000

The purpose of this study was to evaluate the changes of skeletodental patterns during Class II treatment and its retention period. Forty two patients of Class II malocclusion, which was treated with nonextraction or first premolar-extraction were selected and their lateral cephalograms were examined in this study. Various skeletodental changes in lateral cephalograms of pre-treatment, post-treatment and retention were measured by superimposition in reference to the cranial base for jaws, the palatal plane for maxillary teeth, and mandibular plane for mandibular teeth. The data were analyzed by paired t-test. In this study, occlusal plane showed the significant anterior downward steepening after active treatment, and remained during retention period. In the nonextraction group, maxillary incisors were retracted and extruded during treatment. Maxillary molars were extended, and mandibular molar were uprighted, with no mesial movement. In the extraction group, both maxillary and mandibular incisors were retracted and extruded. Maxillary molars were extruded and moved mesially, and mandibular molars were extruded and moved mesially with no mesial tilting. During retention period in both groups, there were tendencies of labial tipping of maxillary incisor, and mesial tipping of maxillary and mandibular molar. But the changes were not significant and most of teeth showed no change in vortical and horizontal direction.

• The korean journal of orthodontics
• /
• v.16 no.1
• /
• pp.167-177
• /
• 1986

This study was undertaken to compare the main differences and its effects of the 4 first bicuspid extraction on the face and dental arch of the class II div 1 malocclusion. The subjects consisted of twenty two class II div 1 malocclusion, four males, eighteen females, were 14 Years 2 Months old at the stan of the treatment 16 Year 3 Months old at the end of the treatment. (mean age) Twenty one variables were observed by comparing the statistical data of the pretreatment records with postteratment records, which were consited of eight varibles on the study model digitation, thirteen variables on the tracing of the lateral cephalogram. The following results were obtained. 1. No significant change was observed in the intercanine width. 2. Intercuspal widths of the 1st. premolar and 2nd. premolar were decreased. 3. Change of the overjet was dependant upon upper anterior rather than lower anterior. 4. No significant changes were observed in facial plane angle and ANB angle. 5. Uprighting of the lower 1st. molar had an effect on the increase of the facial height.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.7
• /
• pp.53-61
• /
• 1998

In this paper, we propose an efficient multi-view images coding algorithm to find the optimal depth and texture from the set of multi-view images. The proposed algorithm consists of two consecutive steps, i) the depth estraction step, and ii) the texture extraction step, comparedwith the traditional algorithem which finds the depth and texture concurrently. The X-Y plane of the normalized object space is divided into traingular paatches and the Z value of the node is determined in the first step and then the texture of the each patch is extracted in the second step. In the depth extraction step, the depth of the node is determined by applying the block based disparity compensation method to the windowed area centered at the node. In the second step, the texture of the traingular patches is extracted from the multi-view images by applying the affine transformation based disparity compensation method to the traingular pateches with the depth extracted from the first step. Experimental results show that the SNR(Singnal-to- Noise Ratio) of images enconded by our algorithm is better than that of images encoded by the traditional algorithm by the amount about 4dB for for the test sets of multi-view images called dragon, kid, city and santa.

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.155-170
• /
• 2020

Passive ranging is a critical part of machine vision measurement. Most of passive ranging methods based on machine vision use binocular technology which need strict hardware conditions and lack of universality. To measure the distance of an object placed on horizontal plane, we present a passive ranging method based on monocular vision system by smartphone. Experimental results show that given the same abscissas, the ordinatesis of the image points linearly related to their actual imaging angles. According to this principle, we first establish a depth extraction model by assuming a linear function and substituting the actual imaging angles and ordinates of the special conjugate points into the linear function. The vertical distance of the target object to the optical axis is then calculated according to imaging principle of camera, and the passive ranging can be derived by depth and vertical distance to the optical axis of target object. Experimental results show that ranging by this method has a higher accuracy compare with others based on binocular vision system. The mean relative error of the depth measurement is 0.937% when the distance is within 3 m. When it is 3-10 m, the mean relative error is 1.71%. Compared with other methods based on monocular vision system, the method does not need to calibrate before ranging and avoids the error caused by data fitting.

• The korean journal of orthodontics
• /
• v.46 no.3
• /
• pp.163-170
• /
• 2016

Objective: The aims of this study were to investigate a simple method for assessing anterior-posterior jaw relationships via cone-beam computed tomography (CBCT) images taken in the natural head position (NHP) relative to the nasion true vertical plane (NTVP), and measure normative data in Korean adults with normal profiles. Methods: Subjects were selected from patients presenting for third molar extraction and evaluated as having normal profiles by three examiners. The CBCT images of 80 subjects (39 males, 41 females) were taken in the NHP according to Solow and Tallgren's method. Linear measurements of the A-point, B-point, and Pog were calculated relative to the NTVP. Student's t -test was used to assess sexual differences in these measurements. Results: The mean linear measurements of the A-point, B-point, and Pog relative to the NTVP were 0.18 mm (standard deviation [SD], 4.77 mm), -4.00 mm (SD, 6.62 mm), and -2.49 mm (SD, 7.14 mm) respectively in Korean males, and 1.48 mm (SD, 4.21 mm), -4.07 mm (SD, 6.70 mm) and -2.91 mm (SD, 7.25 mm) in Korean females respectively. There were no statistically significant differences between Korean males and females (p < 0.05). Conclusions: Three-dimensional CBCT analysis using the NTVP is a simple and reliable method for assessing anterior-posterior skeletal relationships.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2010.03a
• /
• pp.16-16
• /
• 2010

GaN-based light-emitting diodes (LEDs) are attracting great interest as candidates for next-generation solid-state lighting, because of their long lifetime, small size, high efficacy, and low energy consumption. However, for general illumination applications, the external quantum efficiency of LEDs, determined by the internal quantum efficiency (IQE) and the light extraction efficiency, must be further increased. The IQE is determined by crystal quality and epitaxial layer structure and high value of IQE more than 70% for blue LEDs have been already reported. However, there is much room for improvement of light extraction efficiency because most of the generated photons from active layer remain inside LEDs by total internal reflection at the interface of semiconductor with air due to the high refractive index difference between LEDs epilayer (for GaN, n=2.5) and air (n=1). The light confining in LEDs will be reabsorbed by the metal electrode or active layer, reducing the efficacy of LEDs. Here, we present the first demonstration of enhanced light extraction by forming a MgO nano-pyramids structure on the surface of vertical-LEDs. The MgO nano-pyramids structure was successfully fabricated at room temperature using conventional electron-beam evaporation without any additional process. The nano-sized pyramids of MgO are formed on the surface during growth due to anisotropic characteristics between (111) and (200) plane of MgO. The ZnO layer with quarter-wavelength in thickness is inserted between GaN and MgO layers to increase the critical angle for total internal reflection, because the refractive index of ZnO (n=1.94) could be matched between GaN (n=2.5) and MgO (n=1.73). The MgO nano-pyramids structure and ZnO refractive-index modulation layer enhanced the light extraction efficiency ofV-LEDs with by 49%, comparing with the V-LEDs with a flat n-GaN surface. The angular-dependent emission intensity shows the enhanced light extraction through the side walls of V-LEDs as well as through the top surface of the n-GaN, because of the increase in critical angle for total internal reflection as well as light scattering at the MgO nano-pyramids surface.

• The korean journal of orthodontics
• /
• v.34 no.2 s.103
• /
• pp.109-119
• /
• 2004

This study aimed at investigating the skeletal, dentoalveolar, and soft tissue changes of Class III malocclusion cases treated by second molar extraction. The lateral cephalograms of 15 subjects with moderate Class III malocclusion by average ANB $-1.4^{\circ}\;and\;IMPA\;85^{\circ}$ were traced and the computerized superimposition of average craniofacial change was made. The data was gathered and statistically analyzed. The results were as follows: 1 Lower anterior facial height/anterior facial height increased by 0.6%(P<0.01), mandibular plane increased by $1.5^{\circ}$(P<0.05). 2. There was a slightly downward & backward rotation of the mandible. 3. Lower first molar tipped distally by 4.nm(P<0.001), lower anterior teeth lingually tipped by $3.2^{\circ}$(P<0.05). 4. Retracted lower lip improved facial profile. This study may suggest that second molar extraction could be effective for a moderate Class III malocclusion to make distalization of the lower first molar easier and avoid severe lingual tipping of the lower incisor, if the lower third molar has a normal shape, good direction of eruption and adequate time for lower second molar extraction

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.127-130
• /
• 2007

The increased availability of portable, low-cost, high resolution video devices has resulted in a rapid growth of the applications for video sequences. These video devices can be mounted in handhold unit, mobile unit and airborne platforms like maned or unmaned helicopter, plane, airship, etc. A core technique in use of video sequences is to align neighborhood video frames to each other or to reference images. For video sequences registration, we extracted interested points from aerial video sequences using Harris, $F{\square}rstner$, and KLT operators and implemented image matching using these points. As the result, we analysed image matching results for each operators and evaluated accuracy of aerial video registration.