• Journal of Korea Society of Digital Industry and Information Management
• /
• v.7 no.4
• /
• pp.133-139
• /
• 2011

In this paper, we propose a hybrid filter for noise reduction. The proposed method adjusts rational filtering direction according to an edge in the image using median filtered data. Rational filter modulates the coefficients of a linear lowpass filter to limit its action in presence of image details. By the ratio of polynomials in the input variables, rational filter reduces noise adaptively. Median filter is widely used to reduce impulse noise, but removes some details for highly corrupted images. Also, desirable details are removed when the window size is large. Our proposed algorithm combines rational filter and median filter. Thus, proposed method not only preserves edge, but also reduces noise in uniform region. Experimental results show that our proposed method has better quality than those by existing median and rational filtering methods.

• Journal of Welding and Joining
• /
• v.27 no.6
• /
• pp.9-16
• /
• 2009

In this paper, the coaxial monitoring system to capture image of weld pool was developed in laser-arc hybrid welding. In order to obtain the reliable image, green laser was used as a illumination system and measuring components such as band pass filter, ND (Neutral Density) filter and shutter speed was designed and optimized. Using this monitoring system, weld pool images were captured according to laser power, welding speed, welding current and interspace between laser and arc through the experiment. ANOVA (Analysis of Variation) was carried out to identify the influence of process variables on bead widths extracted from captured images of monitoring system. Welding speed and current were major factor to affect weld pool.

• Nuclear Engineering and Technology
• /
• v.53 no.7
• /
• pp.2371-2376
• /
• 2021

As the γ-ray energy increases, a reconstructed image becomes noisy and blurred due to the penetration of the γ-ray through the coded mask. Therefore, the thickness of the coded mask was increased for high energy regions, resulting in severely decreased the performance of the detection efficiency due to self-collimation by the mask. In order to overcome the limitation, a modified uniformly redundant array γ-ray imaging system using dual anti-mask method was developed, and its performance was compared and evaluated in high-energy radiation region. In the dual anti-mask method, the two shadow images, including the subtraction of background events, can simultaneously contribute to the reconstructed image. Moreover, the reconstructed images using each shadow image were integrated using a hybrid update maximum likelihood expectation maximization (h-MLEM). Using the quantitative evaluation method, the performance of the dual anti-mask method was compared with the previously developed collimation methods. As the shadow image which was subtracted the background events leads to a higher-quality reconstructed image, the reconstructed image of the dual anti-mask method showed high performance among the three collimation methods. Finally, the quantitative evaluation method proves that the performance of the dual anti-mask method was better than that of the previously reconstruction methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1778-1797
• /
• 2021

Document image binarization is an important pre-processing step in document analysis and archiving. The state-of-the-art models for document image binarization are variants of encoder-decoder architectures, such as FCN (fully convolutional network) and U-Net. Despite their success, they still suffer from three limitations: (1) reduced feature map resolution due to consecutive strided pooling or convolutions, (2) multiple scales of target objects, and (3) reduced localization accuracy due to the built-in invariance of deep convolutional neural networks (DCNNs). To overcome these three challenges, we propose an improved semantic segmentation model, referred to as DP-LinkNet, which adopts the D-LinkNet architecture as its backbone, with the proposed hybrid dilated convolution (HDC) and spatial pyramid pooling (SPP) modules between the encoder and the decoder. Extensive experiments are conducted on recent document image binarization competition (DIBCO) and handwritten document image binarization competition (H-DIBCO) benchmark datasets. Results show that our proposed DP-LinkNet outperforms other state-of-the-art techniques by a large margin. Our implementation and the pre-trained models are available at https://github.com/beargolden/DP-LinkNet.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.129-143
• /
• 2023

In the era of big data, the field of artificial intelligence is showing remarkable growth, and in particular, the image classification learning methods by deep learning are becoming an important area. Various studies have been actively conducted to further improve the performance of CNNs, which have been widely used in image classification, among which a representative method is the Convolutional Recurrent Neural Network (CRNN) algorithm. The CRNN algorithm consists of a combination of CNN for image classification and RNNs for recognizing time series elements. However, since the inputs used in the RNN area of CRNN are the flatten values extracted by applying the convolution and pooling technique to the image, pixel values in the same phase in the image appear in different order. And this makes it difficult to properly learn the sequence of arrangements in the image intended by the RNN. Therefore, this study aims to improve image classification performance by proposing a novel hybrid method of CNN and RNN applying the concepts of encoder and decoder. In this study, the effectiveness of the new hybrid method was verified through various experiments. This study has academic implications in that it broadens the applicability of encoder and decoder concepts, and the proposed method has advantages in terms of model learning time and infrastructure construction costs as it does not significantly increase complexity compared to conventional hybrid methods. In addition, this study has practical implications in that it presents the possibility of improving the quality of services provided in various fields that require accurate image classification.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.482-485
• /
• 2004

We fabricated a hybrid bulk/fully depleted silicon on insulator (FDSOI) complementary metal oxide semiconductor (CMOS) active pixel image sensor. The active pixel is comprised of reset and source follower transistors on the SOI seed wafer, while the pinned photodiode and readout gate and floating diffusion are fabricated on the SOI handle wafer after the removal of the buried oxide. The source of dark current is eliminated by hybrid bulk/FDSOI pixel structure between localized oxidation of silicon (LOCOS) and photodiode(PD). By using the low noise hybrid pixel structure, dark currents qm be suppressed significantly. The pinned photodiode can also be optimized for quantum efficiency and reduce the noise of dark current. The spectral response of the pinned photodiode on the SOI handle wafer is very flat between 400 nm and 700 nm and the dark current that is higher than desired is about 10 nA/cm2 at a $V_{DD}$ of 2 V.

• Proceedings of the Korean Society of Laser Processing Conference
• /
• 2006.11a
• /
• pp.123-127
• /
• 2006

Hybrid type microscope with a Scanning Confocal Microscope (SCM) and a shear-force Atomic Force Microscope (AFM) is suggested and preliminarily studied. A image of $120{\times}120{\mu}m^2$ is obtained within 1 second by SCM because scan speed of a X-axis and Y-axis are 1kHz and 1Hz, respectively. Shear-force AFM is able to correctly measure the hight and width of sample with a resolution 8nm. However, the scan speed is slow and it is difficult to distinguish a surface composed of different kinds of materials. We have carried out the measurement of total image of a sample by SCM and an exact analysis of each image by shear-force AFM.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.9B
• /
• pp.1616-1623
• /
• 1999

This paper describes error resilient coding scheme is added in WLL system and its application for robust low-bit rate still image transmission over power controlled W-CDA system Rayleigh fading channels. The baseline JPEG compressing methods are uses in image coding over wireless channel. The channel uses Reed-Solomon(RS) outer codes concatenated with convolutional inner codes, and truncated type I hybrid ARQ protocol based on the selective repeat strategy and the RS error detection capability. Simulation results are proved for the statistics of the frame-error bursts of the proposed system in comparison with conventional WLL system. it gains the 2 dB of the Eb/No in same BER.

• Korean Journal of Remote Sensing
• /
• v.18 no.2
• /
• pp.107-116
• /
• 2002

A hybrid image segmentation algorithm is proposed which integrates edge-based and region-based techniques through the watershed algorithm. First, by using mean curvature diffusion coupled to min/max flow, noise is eliminated and thin edges are preserved. After images are segmented by watershed algorithm, the segmented regions are combined with neighbor regions. Region adjacency graph (RAG) is employed to analyze the relationship among the segmented regions. The graph nodes and edge costs in RAG correspond to segmented regions and dissimilarities between two adjacent regions respectively. After the most similar pair of regions is determined by searching minimum cost RAG edge, regions are merged and the RAG is updated. The proposed method efficiently reduces noise and provides one-pixel wide, closed contours.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2007.11a
• /
• pp.379-380
• /
• 2007