• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.37 no.9
• /
• pp.823-828
• /
• 2013

To reduce the cost per watt of photovoltaic power, it is important to reduce the cell thickness of crystalline silicon solar cells. As the thickness of the silicon layer is reduced, two distinctive thermal expansion rates between the silicon and the aluminum layer induce bowing in a solar cell. With a thinner silicon layer, the bowing distance grows exponentially. Excessive bowing could damage the silicon wafer. In this study, we tried to measure an irregularly curved silicon solar cell more accurately using a 3D image scanner. For the detailed analysis of the three-dimensional bowing shape, a least square fit was applied to the point data from the scanned image. It has been found that the bowing distance and shape distortion increase with a decrease in the thickness of the silicon layer. An Ag strip on top of the silicon layer can reduce the bowing distance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1761-1777
• /
• 2021

An image with infrared features and visible details is obtained by processing infrared and visible images. In this paper, a fusion method based on Laplacian pyramid and generative adversarial network is proposed to obtain high quality fusion images, termed as Laplacian-GAN. Firstly, the base and detail layers are obtained by decomposing the source images. Secondly, we utilize the Laplacian pyramid-based method to fuse these base layers to obtain more information of the base layer. Thirdly, the detail part is fused by a generative adversarial network. In addition, generative adversarial network avoids the manual design complicated fusion rules. Finally, the fused base layer and fused detail layer are reconstructed to obtain the fused image. Experimental results demonstrate that the proposed method can obtain state-of-the-art fusion performance in both visual quality and objective assessment. In terms of visual observation, the fusion image obtained by Laplacian-GAN algorithm in this paper is clearer in detail. At the same time, in the six metrics of MI, AG, EI, MS_SSIM, Q_abf and SCD, the algorithm presented in this paper has improved by 0.62%, 7.10%, 14.53%, 12.18%, 34.33% and 12.23%, respectively, compared with the best of the other three algorithms.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.5
• /
• pp.406-412
• /
• 2001

In this paper, a new fuzzy single layer learning algorithm is proposed, which shows improved learning time and convergence property than that of the conventional fuzzy single layer perceptron algorithms. First, we investigate the structure of physiological neurons of the nervous system and propose new neuron structures based on fuzzy logic. And by using the proposed fuzzy neuron structures, the model and learning algorithm of Physiological Fuzzy Single Layer Perceptron(P-FSLP) are proposed. For the evaluation of performance of the P-FSLP algorithm, we applied the conventional fuzzy single layer perceptron algorithms and the P-FSLP algorithm to three experiments including Exclusive OR problem, the 3-bit parity bit problem and the recognition of car licence plates, which is an application of image recognition, and evaluated the performance of the algorithms. The experimentation results showed that the proposed P-FSLP algorithm reduces the possibility of local minima more than the conventional fuzzy single layer perceptrons do, and enhances the time and convergence for learning. Furthermore, we found that the P-FSLP algorithm has the great capability for image recognition applications.

• Imaging Science in Dentistry
• /
• v.33 no.1
• /
• pp.43-49
• /
• 2003

Purpose : To evaluate the differences in bone height, bone width, and visibility of posterior spiral tomographic images according to various exposure directions, image layer thickness, and inclination of the mandibular inferior border. Materials and Methods: Six partially and completely edentulous dry mandibles were radiographed using Scanora spiral tomography. Spiral tomography was performed at different exposure directions (dentotangential and maxillotangential projection), image layer thicknesses (2 mm, 4 mm and 8 mm), and at various inclinations to the mandibular border (+ 100, 00 and -10°). The bone height and width was measured using selected tomographic images. The visibility of mandibular canal, crestal bone, and buccal and lingual surfaces were graded as 0, 1, or 2. Results : The bone width at the maxillo-tangential projection was wider than at the dento-tangential projection (p < 0.05). The visibility of buccal and lingual surface at the maxillo-tangential projection was higher than at the dento-tangential projection (p<0.05). Thinner image layer thicknesses resulted in greater visibility of buccal and lingual surfaces (p < 0.05). Bone height was greatest in the -10° group, and at the same time the bone width of the same group was the narrowest (p < 0.05). The visibility of alveolar crest and buccal surface of the + 10° group was the highest, while the visibility of the mandibular canal was greatest in the 00 group. Conclusion: When spiral tomography is performed at the mandibular posterior portion for visualization prior to implant surgery, it is important that the inferior border of mandible be positioned as parallel as possible to the floor. A greater improvement of visibility can be achieved by maintaining a thin image layer thickness when performing spiral tomography.

• Journal of IKEEE
• /
• v.22 no.1
• /
• pp.149-155
• /
• 2018

In this paper, we used ET(Electrical Tomography) for earth resistivity image reconstruction of vertical multi layer underground model. The earth resistivity is analyzed generally as the parallel multi-layer model, however possibly there happens vertical layer model. Here to find the best electrode array in case of vertical layer underground model, Wenner, Schlumberger, and Dipole-dipole electrode arrays, which are well known electrode arrays used in ET, have been tested. And Gauss-Newton algorithm is used in ET inversion. RMS error analysis shows that Wenner electrode array is best in imaging.

• Current Optics and Photonics
• /
• v.2 no.2
• /
• pp.153-164
• /
• 2018

In semiconductor manufacturing, critical dimensions indicate the features of patterns formed by the semiconductor process. The purpose of measuring critical dimensions is to confirm whether patterns are made as intended. The deposition process for an organic light emitting diode (OLED) forms a luminous organic layer on the thin-film transistor electrode. The position of this organic layer greatly affects the luminescent performance of an OLED. Thus, a system for measuring the position of the organic layer from outside of the vacuum chamber in real-time is desired for monitoring the deposition process. Typically, imaging from large stand-off distances results in low spatial resolution because of diffraction blur, and it is difficult to attain an adequate industrial-level measurement. The proposed method offers a new superresolution single-image using a conversion formula between two different optical systems obtained by a deep learning technique. This formula converts an image measured at long distance and with low-resolution optics into one image as if it were measured with high-resolution optics. The performance of this method is evaluated with various samples in terms of spatial resolution and measurement performance.

• Journal of Korea Multimedia Society
• /
• v.2 no.4
• /
• pp.490-495
• /
• 1999

In this paper, a method of improving the learning time and convergence rate is proposed to exploit the advantages of artificial neural networks and fuzzy theory to neuron structure. This method is applied to the XOR Problem, n bit parity problem which is used as the benchmark in neural network structure, and recognition of digit image in the vehicle plate image for practical image application. As a result of the experiments, it does not always guarantee the convergence. However, the network showed improved the teaming time and has the high convergence rate. The proposed network can be extended to an arbitrary layer Though a single layer structure Is considered, the proposed method has a capability of high speed 3earning even on large images.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.4
• /
• pp.487-493
• /
• 1998

Camera calibration is the process of determining the coordinate relationship between a camera image and its real world space. Accurate calibration of a camera is necessary for the applications that involve quantitative measurement of camera images. However, if the camera plane is parallel or near parallel to the calibration board on which 2 dimensional objects are defined(this is called "ill-conditioned"), existing solution procedures are not well applied. In this paper, we propose a neural network-based approach to camera calibration for 2D images formed by a mono-camera or a pair of cameras. Multi-layer perceptrons are developed to transform the coordinates of each image point to the world coordinates. The validity of the approach is tested with data points which cover the whole 2D space concerned. Experimental results for both mono-camera and stereo-camera cases indicate that the proposed approach is comparable to Tsai's method［8］. Especially for the stereo camera case, the approach works better than the Tsai's method as the angle between the camera optical axis and the Z-axis increases. Therefore, we believe the approach could be an alternative solution procedure for the ill -conditioned camera calibration.libration.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.32 no.7
• /
• pp.518-528
• /
• 2008

The effects of surface roughness on a turbulent boundary layer (TBL) were investigated using particle image velocimetry (PIV). The roughness elements used were periodically arranged two-dimensional spanwise rods, and the roughness height was ${\kappa}/{\delta}$. Introduction of the roughness elements increased the wake strength and the turbulent stress not only in the roughness sublayer but also in the outer layer. This indicates the existence of interaction between inner and outer layers for 2D rod-roughened wall. Roughness effects on a turbulence structure near the wall were obtained by PIV measurements. Iso-contours of mean velocities and Reynolds stresses in the roughness sublayer showed a very good agreement with previous DNS results.

• Journal of Korea Multimedia Society
• /
• v.19 no.12
• /
• pp.1951-1959
• /
• 2016

In this paper, we propose a two-scale fusion method for infrared and visible images using saliency and variance. The images are separated into two scales respectively: a base layer of low frequency component and a detailed layer of high frequency component. Then, these are synthesized using weight. The saliencies and the variances of the images are used as the fusion weights for the two-scale images. The proposed method is tested on several image pairs, and its performance is evaluated quantitatively by using objective fusion metrics.