• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.163-165
• /
• 2019

The task of image denoising is gaining popularity in the computer vision research field. Its main objective of restoring the sharp image from given noisy input is demanded in all image processing procedure. In this work, we treat the process of residual hair removal on faces images similar to the task of image denoising. In particular, our method removes the residual hair that presents on the frontal or profile face images and in-paints it with the relevant skin color. To achieve this objective, we employ a deep neural network that able to perform both tasks in one time. Furthermore, simple technic of residual hair color augmentation is introduced to increase the number of training data. This approach is beneficial for improving the robustness of the network. Finally, we show that the experimental results demonstrate the superiority of our network in both quantitative and qualitative performances.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.12A
• /
• pp.2092-2099
• /
• 2001

In the three-dimensional image system using stereoscopic images, efficient coding schemes which can get rid of redundancy between the left and right images are usually used. In this paper, we propose an efficient coding method by using relationship between a reference image and residual image. In the proposed algorithm, zero-tree method which guaranty a good quality in low bit rate is used for encoding the residual image. Zero-tree algorithm gives good coding performance, but it has computational complexity so that we used ADLS method to reduce time for the disparity estimation. Using the wavelet based zero-tree method, it is shown that high quality of image in the limited band-width can be preserved through computer simulation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4426-4442
• /
• 2020

Since scene segmentation is becoming a hot topic in the field of autonomous driving and medical image analysis, researchers are actively trying new methods to improve segmentation accuracy. At present, the main issues in image semantic segmentation are intra-class inconsistency and inter-class indistinction. From our analysis, the lack of global information as well as macroscopic discrimination on the object are the two main reasons. In this paper, we propose a Densely connected residual Attention network (DA-Res2Net) which consists of a dense residual network and channel attention guidance module to deal with these problems and improve the accuracy of image segmentation. Specifically, in order to make the extracted features equipped with stronger multi-scale characteristics, a densely connected residual network is proposed as a feature extractor. Furthermore, to improve the representativeness of each channel feature, we design a Channel-Attention-Guide module to make the model focusing on the high-level semantic features and low-level location features simultaneously. Experimental results show that the method achieves significant performance on various datasets. Compared to other state-of-the-art methods, the proposed method reaches the mean IOU accuracy of 83.2% on PASCAL VOC 2012 and 79.7% on Cityscapes dataset, respectively.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2007.05a
• /
• pp.241-245
• /
• 2007

The residual stress in axial stress in the axial direction of the steel filaments has been measured by using a method based on the combination of the focused ion beam (FIB) and high resolution strain mapping program (VIC-2D). That is, the residual stress was calculated from the measured displacement field before and after the introduction of a slot along the steel filaments. The displacement was obtained by the digital correlation analysis of high-resolution scanning electron micrographs, while the slot was introduced by FIB milling with low energy beam. The present measurement revealed that the residual stress within 8% of the magnitude was persistent in the steel filaments fabricated.

• Journal of the Society of Naval Architects of Korea
• /
• v.50 no.2
• /
• pp.104-110
• /
• 2013

In this paper, the design procedure and results for 'Residual Life Prediction System Considering Corrosion and Coating' are explained, which is one module of 'Life-cycle Management System of Ship and Offshore Plant's' Operation. This 'Residual Life Prediction System' has two main functions; one is residual life prediction function based on probability processing using corrosion measurement data of ship's major structural members, and another is rust rate prediction function based on visual image processing of inspection photos. The analysis of system user requirements and functions are introduced, and the structure and environment of the developed system are explained.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.102-105
• /
• 2019

In the classical single-image super-resolution (SISR) reconstruction method using convolutional neural networks, the extracted features are not fully utilized, and the training time is too long. Aiming at the above problems, we proposed an improved SISR method based on a residual network. Our proposed method uses a feature fusion technology based on improved residual blocks. The advantage of this method is the ability to fully and effectively utilize the features extracted from the shallow layers. In addition, we can see that the feature fusion can adaptively preserve the information from current and previous residual blocks and stabilize the training for deeper network. And we use the global residual learning to make network training easier. The experimental results show that the proposed method gets better performance than classic reconstruction methods.

• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.633-642
• /
• 2019

Recently, the convolution neural network (CNN) model at a single image super-resolution (SISR) have been very successful. The residual learning method can improve training stability and network performance in CNN. In this paper, we propose a SISR using recursive residual network architecture by introducing dense skip connections for learning nonlinear mapping from low-resolution input image to high-resolution target image. The proposed SISR method adopts a method of the recursive residual learning to mitigate the difficulty of the deep network training and remove unnecessary modules for easier to optimize in CNN layers because of the concise and compact recursive network via dense skip connection method. The proposed method not only alleviates the vanishing-gradient problem of a very deep network, but also get the outstanding performance with low complexity of neural network, which allows the neural network to perform training, thereby exhibiting improved performance of SISR method.

• The Journal of Korea Robotics Society
• /
• v.13 no.1
• /
• pp.1-7
• /
• 2018

The image-to-image translation is one of the deep learning applications using image data. In this paper, we aim at improving the performance of object transfiguration which transforms a specific object in an image into another specific object. For object transfiguration, it is required to transform only the target object and maintain background images. In the existing results, however, it is observed that other parts in the image are also transformed. In this paper, we have focused on the structure of artificial neural networks that are frequently used in the existing methods and have improved the performance by adding constraints to the exiting structure. We also propose the advanced structure that combines the existing structures to maintain their advantages and complement their drawbacks. The effectiveness of the proposed methods are shown in experimental results.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.2
• /
• pp.47-53
• /
• 2010

This paper proposed Residual Image detection and Color Info using the face detection technique. The proposed technique was fast processing speed and high rate of face detection on the video. In addition, this technique is to detection error rate reduced through the calibration tasks for tilted face image. The first process is to extract target image from the transmitted video images. Next, extracted image processed by window rotated algorithm for detection of tilted face image. Feature extraction for face detection was used for AdaBoost algorithm.

• Journal of the Korean Society of Radiology
• /
• v.16 no.3
• /
• pp.295-302
• /
• 2022

Sparse-view computed tomography (CT) imaging technique is able to reduce radiation dose, ensure the uniformity of image characteristics among projections and suppress noise. However, the reconstructed images obtained by the sparse-view CT imaging technique suffer from severe artifacts, resulting in the distortion of image quality and internal structures. In this study, we proposed a convolutional neural network (CNN) with wavelet transformation and residual learning for reducing artifacts in sparse-view CT image, and the performance of the trained model was quantitatively analyzed. The CNN consisted of wavelet transformation, convolutional and inverse wavelet transformation layers, and input and output images were configured as sparse-view CT images and residual images, respectively. For training the CNN, the loss function was calculated by using mean squared error (MSE), and the Adam function was used as an optimizer. Result images were obtained by subtracting the residual images, which were predicted by the trained model, from sparse-view CT images. The quantitative accuracy of the result images were measured in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The results showed that the trained model is able to improve the spatial resolution of the result images as well as reduce artifacts in sparse-view CT images effectively. Also, the trained model increased the PSNR and SSIM by 8.18% and 19.71% in comparison to the imaging model trained without wavelet transformation and residual learning, respectively. Therefore, the imaging model proposed in this study can restore the image quality of sparse-view CT image by reducing artifacts, improving spatial resolution and quantitative accuracy.