• 반도체디스플레이기술학회지
• /
• 제20권1호
• /
• pp.64-69
• /
• 2021

In this paper, a method for improving the defect classification performance in low contrast, ununiformity and featureless steel plate surfaces has been studied based on deep convolution neural network and transfer-learning neural network. The steel plate surface images have low contrast, ununiformity, and featureless, so that the contrast between defect and defect-free regions are not discriminated. These characteristics make it difficult to extract the feature of the surface defect image. A classifier based on a deep convolution neural network is constructed to extract features automatically for effective classification of images with these characteristics. As results of the experiment, AlexNet-based transfer-learning classifier showed excellent classification performance of 99.43% with less than 160 seconds of training time. The proposed classification system showed excellent classification performance for low contrast, ununiformity, and featureless surface images.

• 반도체디스플레이기술학회지
• /
• 제20권4호
• /
• pp.182-186
• /
• 2021

Tone mapping operator is designed to reproduce visibility of real-world scenes such as HDR images on limited dynamic range display devices. This paper presents and implements compare and to estimate some tone mapping algorithms commonly used. The evaluation is performed by applying tone mapping operators on 7 HDR images, and by presenting the results with subjective estimation. Reinhard tone mapping algorithm is the best in the visual experimental results. The goal of this work is to discuss what is visible of high dynamic range on a normal display device and to determine to which better algorithm is. This work motivates us to make more progress through the new proposal of tone mapping operator on future work.

• 반도체디스플레이기술학회지
• /
• 제22권3호
• /
• pp.149-154
• /
• 2023

This paper presents a novel approach to multi-focus image fusion using light field cameras. The proposed neural network, LFFCNN (Light Field Focus Convolutional Neural Network), is composed of three main modules: feature extraction, feature fusion, and feature reconstruction. Specifically, the feature extraction module incorporates SPP (Spatial Pyramid Pooling) to effectively handle images of various scales. Experimental results demonstrate that the proposed model not only effectively fuses a single All-in-Focus image from images with multi focus images but also offers more efficient and robust focus fusion compared to existing methods.

• 반도체디스플레이기술학회지
• /
• 제19권3호
• /
• pp.1-6
• /
• 2020

In this paper, a method for improving the defect classification performance in steel plate surface has been studied, based on DWT(discrete wavelet transform) and SVM(support vector machine). Surface images of the steel plate have low contrast, uneven, and featureless, so that the contrast between defect and defect-free regions is not discriminated. These characteristics make it difficult to extract the feature of the surface defect image. In order to improve the characteristics of these images, a synthetic images based on discrete wavelet transform are modeled. Using the synthetic images, edge-based features are extracted and also geometrical features are computed. SVM was configured in order to classify defect images using extracted features. As results of the experiment, the support vector machine based classifier showed good classification performance of 94.3%. The proposed classifier is expected to contribute to the key element of inspection process in smart factory.

• 반도체디스플레이기술학회지
• /
• 제15권3호
• /
• pp.18-23
• /
• 2016

QFN (Quad Flat No-leads Package) is one of the SMD (Surface Mount Device). Since there is no lead in QFN, there are many defects on solder. Therefore, we propose an efficient mechanism for QFN solder defect detection at this paper. For this, we employ Convolutional Neural Network (CNN) of the Machine Learning algorithm. QFN solder's color multi-layer images are used to train CNN. Since these images are 3-channel color images, they have a problem with applying to CNN. To solve this problem, we used each 1-channel grayscale image (Red, Green, Blue) that was separated from 3-channel color images. We were able to detect QFN solder defects by using this CNN. In this paper, it is shown that the CNN is superior to the conventional multi-layer neural networks in detecting QFN solder defects. Later, further research is needed to detect other QFN.

• 반도체디스플레이기술학회지
• /
• 제23권2호
• /
• pp.135-142
• /
• 2024

Cu-Cu bonding, one of the key technologies in advanced packaging, enhances semiconductor chip performance, miniaturization, and energy efficiency by facilitating rapid data transfer and low power consumption. However, the quality of the interface bonding can significantly impact overall bond quality, necessitating strategies to quickly detect and classify in-process defects. This study presents a methodology for detecting defects in wafer junction areas from Scanning Acoustic Microscopy images using a ResNet-50 based deep learning model. Additionally, the use of the defect map is proposed to rapidly inspect and categorize defects occurring during the Cu-Cu bonding process, thereby improving yield and productivity in semiconductor manufacturing.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2000년도 제1회 학술대회 논문집
• /
• pp.231-234
• /
• 2000

Vertically aligned carbon nanotubes were synthesized on Ni-coated Si substrates using microwave plasma-enhanced chemical vapor deposition. The grain size of Ni thin films was varied with the RF power density during the RF magnetron sputtering process. It was found that the diameter, growth rate, and density of carbon nanotubes could be controlled systematically by the grain size of Ni thin films. With decreasing the grain size of Ni thin films, the diameter of the nanotubes decreased, whereas the growth rate and density increased. High-resolution transmission electron microscope images clearly demonstrated synthesized nanotubes to be multiwalled. The number of graphitized wall decreased with decreasing the diameter. Field emission properties will be further presented.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2004년도 Asia Display / IMID 04
• /
• pp.669-672
• /
• 2004

The thin-film passivation technology using the poly-para-xylylene (parylene) was applied to polymer electroluminescent devices. The fabricated device shows a good luminescent characteristic of maximum 11640 cd/$m^2$. The measured lifetime was reached up to 28 hours, which means the effectiveness of the passivation. Applying the parylene thin-film passivation technique, 10${\times}$10 passive matrix display system was implemented and obtained some still images.

• 반도체디스플레이기술학회지
• /
• 제5권2호
• /
• pp.19-25
• /
• 2006

This paper focuses on lossy medical image compression methods for medical images that operate on three-dimensional(3-D) irreversible integer wavelet transform. We offer an application of unbalanced tree structure algorithm to medical images, using a 3-D unbalanced wavelet decomposition and a 3-D unbalanced spatial dependence tree. The wavelet decomposition is accomplished with integer wavelet filters implemented with the lifting method. We have tested our encoder on volumetric medical images using different integer filters and coding unit sizes. The coding unit sizes of 16 slices save considerable dynamic memory(RAM) and coding delay from full sequence coding units used in previous works. If we allow the formation of trees of different lengths, then we can accomodate more transaxial scales than three. The encoder and decoder can then keep track of the length of the tree in which each pixel resides through the sequence of decompositions. Results show that, even with these small coding units, our algorithm with certain filters performs as well and better in lossy coding than previous coding systems using 3-D integer unbalanced wavelet transforms on volumetric medical images.

• 반도체디스플레이기술학회지
• /
• 제17권4호
• /
• pp.1-5
• /
• 2018

Atomic force microscopy (AFM) simulation for Si (001) surface defects was conducted by using density functional theory (DFT). Three major defects on the Si (001) surface are difficult to analyze due to external noises that are always present in the images obtained by AFM. Noise-free surface defects obtained by simulation can help identify the real surface defects on AFM images. The surface defects were first optimized by using a DFT code. The AFM tip was designed by using five carbon atoms and positioned on the surface to calculate the system's energy. Forces between tip and surface were calculated from the energy data and converted into an AFM image. The simulated AFM images are noise-free and, therefore, can help evaluate the real surface defects present on the measured AFM images.