• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.1
• /
• pp.19-29
• /
• 2003

This paper presents a novel hybrid classifier for face recognition with artificially generated virtual training samples. We utilize both the nearest neighbor approach in feature angle space and a connectionist model to obtain a synergy effect by combining the results of two heterogeneous classifiers. First, a classifier called the nearest feature angle (NFA), based on angular information, finds the most similar feature to the query from a given training set. Second, a classifier has been developed based on the recall of stored frontal projection of the query feature. It uses a frontal recall network (FRN) that finds the most similar frontal one among the stored frontal feature set. For FRN, we used an ensemble neural network consisting of multiple multiplayer perceptrons (MLPs), each of which is trained independently to enhance generalization capability. Further, both classifiers used the virtual training set generated adaptively, according to the spatial distribution of each person's training samples. Finally, the results of the two classifiers are combined to comprise the best matching class, and a corresponding similarit measure is used to make the final decision. The proposed classifier achieved an average classification rate of 96.33% against a large group of different test sets of images, and its average error rate is 61.5% that of the nearest feature line (NFL) method, and achieves a more robust classification performance.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.2
• /
• pp.69-81
• /
• 2011

The soil moisture data of the National Aeronautics and Space Administration(NASA) and the Vrije Universiteit Amsterdam(VUA) in collaboration with NASA, retrieved from Advanced Microwave Scanning Radiometer-Earth observing system(AMSR-E) brightness temperature, were collected to evaluate the applicability of the remote sensed soil moisture in South Korea. The averages of the soil moisture by in-situ sensors, by NASA and by VUA-NASA are approximately 0.218, 0.119, and $0.402m^3/m^3$, respectively. This indicates that the soil moisture of NASA was underestimated and that of VUA-NASA was overestimated. The soil moisture products of VUA-NASA showed a better relationship with the in-situ data than that of NASA data. However, there are still limitations of C-band soil moisture measurements. To improve the applicability of satellite soil moisture measurements, bias correction and other post processings are essential using in-situ soil moisture measurements at various surface conditions.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.38 no.2
• /
• pp.125-131
• /
• 2020

In this study, the author comparatively analyzed the effects and applicability of drifts, one of planting design methods based on the principle of visual harmony, to look into the definition and characteristics in planing techniques with examples of drifts in gardens designed by Gerturde Jekyll and Piet Oudolf. Sites chosen for the case studies included Jekyll's Upton grey and Hestercomb garden and Oudolf's At Scampston Hall and Trentham Estate Garden. The results showed that Jekyll set layers for vertical and horizontal structures by using plants of different height to make flowers look like floating with their stems unseen and appear in turn over time. Assemble planting of groups was used to conceal rigid, irregular lines so that the plants are recognized as mass with smoother horizontal lines. Clearly visible, repeated drifts creates a sense of unity. Oudolf, in combining grass and perennial plants, used one-to-one correspondence or expansion to express drifts. Grass serves roles as a connecting material inserted when changing space or making transitions of images. Blocks in single species are repeatedly crossed to set scenes, and overlapping and mixing makes them more lively.

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.919-927
• /
• 2019

In this paper, we propose an accurate camera calibration method for acquiring multiview stereoscopic images. Generally, camera calibration is performed by using checkerboard structured patterns. The checkerboard pattern simplifies feature point extraction process and utilizes previously recognized lattice structure, which results in the accurate estimation of relations between the point on 2-dimensional image and the point on 3-dimensional space. Since estimation accuracy of camera parameters is dependent on feature matching, accurate detection of checkerboard corner is crucial. Therefore, in this paper, we propose the method that performs accurate camera calibration method through accurate detection of checkerboard corners. Proposed method detects checkerboard corner candidates by utilizing 1-dimensional gaussian filters with succeeding corner refinement process to remove outliers from corner candidates and accurately detect checkerboard corners in sub-pixel unit. In order to verify the proposed method, we check reprojection errors and camera location estimation results to confirm camera intrinsic parameters and extrinsic parameters estimation accuracy.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.1
• /
• pp.58-63
• /
• 2020

This paper proposes the method for improving the localization accuracy of the mobile robot based on the stereo camera. To restore the position information from stereo images obtained by the stereo camera, the corresponding point which corresponds to one pixel on the left image should be found on the right image. For this, there is the general method to search for corresponding point by calculating the similarity of pixel with pixels on the epipolar line. However, there are some disadvantages because all pixels on the epipolar line should be calculated and the similarity is calculated by only pixel value like RGB color space. To make up for this weak point, this paper implements the method to search for the corresponding point simply by calculating the gap of x-coordinate when the feature points, which are extracted by feature extraction and matched by feature matching method, are a pair and located on the same y-coordinate on the left/right image. In addition, the proposed method tries to preserve the number of feature points as much as possible by finding the corresponding points through the conventional algorithm in case of unmatched features. Because the number of the feature points has effect on the accuracy of the localization. The position of the mobile robot is compensated based on 3-D coordinates of the features which are restored by the feature points and corresponding points. As experimental results, by the proposed method, the number of the feature points are increased for compensating the position and the position of the mobile robot can be compensated more than only feature extraction.

• Journal of KIISE
• /
• v.42 no.5
• /
• pp.642-651
• /
• 2015

A vanishing point is a point where parallel lines converge, and they become evident when a camera's lenses are used to project 3D space onto a 2D image plane. Vanishing point detection is the use of the information contained within an image to detect the vanishing point, and can be utilized to infer the relative distance between certain points in the image or for understanding the geometry of a 3D scene. Since parallel lines generally exist for the artificial structures within images, line-detection-based vanishing point-detection techniques aim to find the point where the parallel lines of artificial structures converge. To detect parallel lines in an image, we detect edge pixels through edge detection and then find the lines by using the Hough transform. However, the various textures and noise in an image can hamper the line-detection process so that not all of the lines converging toward the vanishing point are obvious. To overcome this difficulty, it is necessary to assign a different weight to each line according to the degree of possibility that the line passes through the vanishing point. While previous research studies assigned equal weight or adopted a simple weighting calculation, in this paper, we are proposing a new method of assigning weights to lines after noticing that the lines that pass through vanishing points typically belong to artificial structures. Experimental results show that our proposed method reduces the vanishing point-estimation error rate by 65% when compared to existing methods.

• Restorative Dentistry and Endodontics
• /
• v.34 no.3
• /
• pp.208-214
• /
• 2009

The purpose of this study was to compare the dye leakage of MTA (mineral trioxide aggregate) apical plug produced by two orthograde placement techniques (hand condensation technique and ultrasonically assisted hand condensation technique). To simulate straight canal, 60 transparent acrylic blocks with straight canal were fabricated. These transparent acrylic blocks were divided into 2 groups (Group C; hand condensation technique (HC) and Group U; ultrasonically assisted hand condensation technique (UAHC)) of 30 blocks with each MTA application method. Each group was divided into 2 subgroups (n=15) with different canal size of #70 (subgroup C70 and subgroup U70) and #120 (subgroup C120 and subgroup U120). After apical plug was created, a wet paper point was placed over the MTA plug and specimen was kept in a humid condition at room temperature to allow MTA to set. After 24 hours, remaining canal space was backfilled using Obtura II. All specimens were transferred to floral form socked by 0.2% rhodamine B solution and stored in 100% humidity at room temperature. After 48 hours, resin block specimens were washed and scanned using a scanner. The maximum length of micro leakage was measured from the scanned images of four surfaces of each resin block using Photoshop 6.0. Statistical analysis was performed with Mann-Whitney U test. Group U of UAHC had significantly lower leakage than Group C of HC in #70-size canal (subgroup U70) (p<0.05).

• The KIPS Transactions:PartB
• /
• v.10B no.1
• /
• pp.95-102
• /
• 2003

In surveillance video system, there are many classes of images and some spatial regions are more important than other regions. The conventional compression method in this system have been compressed there full frames without classfying them depend on their important parts. To improve the accuracy of the image coding and deliver effective compression for the surveillance video system, it was necessary to separate the regions according to their importance. In this paper, we propose a new effective surveillance video image compression method. The proposed scheme defines importance based three-level region of interest block in a frame, such as background, motion object block, and the feature object block. A captured video image frame can be separated to these three different levels of block regions. And depends on the priority, each block can be modified and compressed in different resolution, compression ratio and qualify factor. Therefore, in surveillance video system, this algorithm not only reduces the image processing time and space, but also guarantees the Important image data in high quality to acquire the system's goal.

• Tunnel and Underground Space
• /
• v.26 no.3
• /
• pp.220-234
• /
• 2016

Sprayable waterproofing membrane has been considered as a substitute for a sheet waterproofing membrane in a variety of underground excavation works. However, fundamental properties of sprayble waterproofing membrane have not been fully given yet. In this study, a new two-component sprayable waterproofing membrane prototype was developed. In addition, its physico-mechanical properties were measured and compared with those of two kinds of thin spray-on liners where constitutive materials and construction methods are very close to each other. From direct tensile tests, the sprayable waterproofing membrane with elongations at break between 250% and 300% showed much higher ductility than TSLs. However, the sprayable waterproofing membrane had a limitation as a support member since its bond strength and loading capacity was lower than those of TSLs. From three-dimensional X-ray CT images, the porosity of the sprayable waterproofing membrane was estimated to be 26.13%. However, most of pores which might have been generated during membrane curing were not observed to be interconnected but isolated.

• Korean Journal of Remote Sensing
• /
• v.20 no.4
• /
• pp.261-274
• /
• 2004

The feature extraction using remotely sensed imagery has been recognized one of the important tasks in remote sensing applications. As the high-resolution imagery are widely used to the engineering purposes, need of more accurate feature information also is increasing. Especially, in case of the automatic extraction of linear feature such as road using mid or low-resolution imagery, several techniques was developed and applied in the mean time. But quantitatively comparative analysis of techniques and case studies for high-resolution imagery is rare. In this study, we implemented a computer program to perform and compare GDPA (Gradient Direction Profile Analysis) algorithm and Hough transformation. Also the results of applying two techniques to some images were compared with road centerline layers and boundary layers of digital map and presented. For quantitative comparison, the ranking method using commission error and omission error was used. As results, Hough transform had high accuracy over 20% on the average. As for execution speed, GDPA shows main advantage over Hough transform. But the accuracy was not remarkable difference between GDPA and Hough transform, when the noise removal was app]ied to the result of GDPA. In conclusion, it is expected that GDPA have more advantage than Hough transform in the application side.