• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4326-4344
• /
• 2021

The SinGAN is one of generative adversarial networks that can be trained on a single nature image. It has poor ability to learn more global features from nature image, and losses much local detail information when it generates arbitrary size image sample. To solve the problem, a non-linear function is firstly proposed to control downsampling ratio that is ratio between the size of current image and the size of next downsampled image, to increase the ratio with increase of the number of downsampling. This makes the low-resolution images obtained by downsampling have higher proportion in all downsampled images. The low-resolution images usually contain much global information. Therefore, it can help the model to learn more global feature information from downsampled images. Secondly, the attention mechanism is introduced to the generative network to increase the weight of effective image information. This can make the network learn more local details. Besides, in order to make the output image more natural, the TVLoss function is introduced to the loss function of SinGAN, to reduce the difference between adjacent pixels and smear phenomenon for the output image. A large number of experimental results show that our proposed model has better performance than other methods in generating random samples with fixed size and arbitrary size, image harmonization and editing.

• Journal of Korea Multimedia Society
• /
• v.18 no.11
• /
• pp.1332-1341
• /
• 2015

This paper proposes a novel reversible secret sharing scheme using AES algorithm in encrypted images. In the proposed scheme, a role of the dealer is divided into an image provider and a data hider. The image provider encrypts the cover image with a shared secret key and sends it to the dealer. The dealer embeds the secret data into the encrypted image and transmits encrypted shadow images to the corresponding participants. We utilize Galois polynomial arithmetic operation over 2⁸ and the coefficient of the higher-order term is fixed to one in order to prevent the overflow. In experimental results, we demonstrate that the PSNR is sustained close to 44dB and the embedding capacity is 524,288 bits.

• ETRI Journal
• /
• v.42 no.2
• /
• pp.258-271
• /
• 2020

A correlation exists between luminance samples and chrominance samples of a color image. It is beneficial to exploit such interchannel redundancy for color image compression. We propose an algorithm that predicts chrominance components Cb and Cr from the luminance component Y. The prediction model is trained by supervised learning with Laplacian-regularized least squares to minimize the total prediction error. Kernel principal component analysis mapping, which reduces computational complexity, is implemented on the same point set at both the encoder and decoder to ensure that predictions are identical at both the ends without signaling extra location information. In addition, chrominance subsampling and entropy coding for model parameters are adopted to further reduce the bit rate. Finally, luminance information and model parameters are stored for image reconstruction. Experimental results show the performance superiority of the proposed algorithm over its predecessor and JPEG, and even over JPEG-XR. The compensation version with the chrominance difference of the proposed algorithm performs close to and even better than JPEG2000 in some cases.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1597-1610
• /
• 2022

At present, the main method of high-speed train chassis detection is using computer vision technology to extract keypoints from two related chassis images firstly, then matching these keypoints to find the pixel-level correspondence between these two images, finally, detection and other steps are performed. The quality and accuracy of image matching are very important for subsequent defect detection. Current traditional matching methods are difficult to meet the actual requirements for the generalization of complex scenes such as weather, illumination, and seasonal changes. Therefore, it is of great significance to study the high-speed train image matching method based on deep learning. This paper establishes a high-speed train chassis image matching dataset, including random perspective changes and optical distortion, to simulate the changes in the actual working environment of the high-speed rail system as much as possible. This work designs a convolutional neural network to intensively extract keypoints, so as to alleviate the problems of current methods. With multi-level features, on the one hand, the network restores low-level details, thereby improving the localization accuracy of keypoints, on the other hand, the network can generate robust keypoint descriptors. Detailed experiments show the huge improvement of the proposed network over traditional methods.

• International Journal of Computer Science & Network Security
• /
• v.23 no.10
• /
• pp.129-134
• /
• 2023

The greatest challenge of this century is the protection of stored and transmitted data over the network. This paper provides a new hybrid algorithm designed based on combination algorithms, in the proposed algorithm combined with Hill and the Advanced Encryption Standard Algorithms, to increase the efficiency of color image encryption and increase the sensitivity of the key to protect the RGB image from Keyes attackers. The proposed algorithm has proven its efficiency in encryption of color images with high security and countering attacks. The strength and efficiency of combination the Hill Chipper and Advanced Encryption Standard Algorithms tested by statical analysis for RGB images histogram and correlation of RGB images before and after encryption using hill cipher and proposed algorithm and also analysis of the secret key and key space to protect the RGB image from Brute force attack. The result of combining Hill and Advanced Encryption Standard Algorithm achieved the ability to cope statistically

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.12
• /
• pp.219-228
• /
• 2012

In this paper, we propose a paper keyboard piano implementation using the finger movement detection with the 3D image data from a kinect. Keyboard pattern and keyboard depth information are extracted from the color image and depth image to detect the touch event on the paper keyboard and to identify the touched key. Hand region detection error is unavoidable when using the simple comparison method between input depth image and background depth image, and this error is critical in key touch detection. Skin color is used to minimize the error. And finger tips are detected using contour detection with area limit and convex hull. Finally decision of key touch is carried out with the keyboard pattern information at the finger tip position. The experimental results showed that the proposed method can detect key touch with high accuracy. Paper keyboard piano can be utilized for the easy and convenient interface for the beginner to learn playing piano with the PC-based learning software.

• Current Optics and Photonics
• /
• v.8 no.3
• /
• pp.215-224
• /
• 2024

In medium- and long-range optical imaging systems, atmospheric turbulence causes blurring and distortion of images, resulting in loss of image information. An image-restoration method based on an adaptive feature-fusion multi-input-multi-output (MIMO) dense U-shaped network (Unet) is proposed, to restore a single image degraded by atmospheric turbulence. The network's model is based on the MIMO-Unet framework and incorporates patch-embedding shallow-convolution modules. These modules help in extracting shallow features of images and facilitate the processing of the multi-input dense encoding modules that follow. The combination of these modules improves the model's ability to analyze and extract features effectively. An asymmetric feature-fusion module is utilized to combine encoded features at varying scales, facilitating the feature reconstruction of the subsequent multi-output decoding modules for restoration of turbulence-degraded images. Based on experimental results, the adaptive feature-fusion MIMO dense U-shaped network outperforms traditional restoration methods, CMFNet network models, and standard MIMO-Unet network models, in terms of image-quality restoration. It effectively minimizes geometric deformation and blurring of images.

• Korean Journal of Optics and Photonics
• /
• v.15 no.2
• /
• pp.114-122
• /
• 2004

In this paper, we proposed an optical encryption and decryption technique that uses a nail bed pattern as a key-code. Since the technique uses a nail bed pattern that is a biometric signal of an encryptor, the technique is robust about a fake key or illegal use of a key. In addition to this, the encrypted image contains the biometric information of the encryptor. This makes the proposed technique also be applied to authentication.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2009.10a
• /
• pp.510-512
• /
• 2009

A volumetric 3D display system based on a rotating two dimensional color LED array is set up. It has a cylinder display space ${\Phi}800{\times}640mm3$ which is composed of 256 slices of pictures in one 3D image with each slice $320{\times}256$ LED pixels. The volumetric image has 4 gray scales and 64 colors. The main structure and working principle of the system is described in detail.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.3
• /
• pp.532-543
• /
• 2003

In this paper, we proposed structure of a reversible discrete-time cellular neural network (DTCNN) for labeling digital images to protect copylight. First, we present the concept and the structure of reversible DTCNN, which can be used to generate 2D binary pseudo-random images sequences. We presented some, output examples of different kinds of reversible DTCNNs to show their complex behaviors. Then both the original image and the copyright label, which is often another binary image, are used to generate a binary random key image. The key image is then used to scramble the original image. Since the reversibility of a reversible DTCNN, the same reversible DTCNN can recover the copyright label from a labeled image. Due to the high speed of a DTCNN chip, our method can be used to label image sequences, e.g., video sequences, in real time. Computer simulation results are presented.