• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1368-1370
• /
• 1996

The Information of Edges which takes small area comparing with the total image is very important in DNA images as well as general images. DNA image is the object should be managed by computing and it's demanding information is less than general images, but the accuracy is more important In a huge DNA image processing system such as DNA Information Bank, the performance depends on the size of image. In this paper, we extract the edge information and make it as a binary image. To reduce the size of the original image, it was applied by JPEG image compression method. The compressed image is combined with edge information when they are restored. As a result, Both the image compression ratio and restoration quality are optimized without the loss of critical information.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.29-38
• /
• 2022

Although image compression is one of the essential technologies to transmit image data on a variety of surveillance and mobile healthcare applications, it causes unnecessary compression artifacts such as blocking and ringing artifacts by the lossy compression in the limited network bandwidth. Recently, image restoration methods using convolutional neural network (CNN) show the significant improvement of image quality from the compressed images. In this paper, we propose Image Denoising Convolutional Neural Networks (IDCNN) to reduce the compression artifacts for the purpose of improving the performance of object classification. In order to evaluate the classification accuracy, we used the ImageNet test dataset consisting of 50,000 natural images and measured the classification performance in terms of Top-1 and Top-5 accuracy. Experimental results show that the proposed IDCNN can improve Top-1 and Top-5 accuracy as high as 2.46% and 2.42%, respectively.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.450-453
• /
• 2002

In this paper a Phase-based virtual image encryption and decryption techniques based on a joint transform correlator (JTC) are proposed. In this method, an encrypted image is obtained by multiplying a phase-encoded virtual image that contains no information from the decrypted image with a random phase. Even if this encryption process converts a virtual image into a white-noise-like image, the unauthorized users can permit a counterfeiting of the encrypted image by analyzing the random phase mask using some phase-contrast technique. However, they cannot reconstruct the required image because the virtual image protects the original image from counterfeiting and unauthorized access. The proposed encryption technique does not suffer from strong auto-correlation terms appearing in the output plane. In addition, the reconstructed data can be directly transmitted to a digital system for real-time processing. Based on computer simulations, the proposed encryption technique and decoding system were demonstrated as adequate for optical security applications.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.39-42
• /
• 2000

In our study, by observing and analyzing normal liver in abdominal CT image, we estimated gray value range and generated binary image. In the binary image, we achieved the number of hole which is located between pixels. Depending on the ratio, we processed the input image to 4 kinds of mesh images to remove the noise part that has the different ratio. With the Union image of 4 kinds of mesh images, we generated the template representing general outline of liver and subtracted from the binary image so the we can represent the organ boundary to be minute. With results of proposed method, processing time is reduced compared with existing method and we compared the result image to manual image of medical specialists.

• Current Optics and Photonics
• /
• v.4 no.4
• /
• pp.302-309
• /
• 2020

An image encryption scheme based on the quick response (QR) code as a data container has aroused wide interest due to the lossless recovery of the decrypted image. In this paper, we apply this method to multi-image encryption. However, since the decrypted image is affected by crosstalk noise, the number of multi-image encryptions is severely limited. To solve this problem, we analyzed the performance of QR code as a data container, and processed the decrypted QR code using the proposed method, so that the number of multi-image encryptions is effectively increased. Finally, we implemented a large image (256 × 256) encryption and decryption.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.551-552
• /
• 2021

In this paper, we present a multi-class image scene classification method based on transformation learning. ImageNet classifies multiple classes of natural scene images by relying on pre-trained network models on large image datasets. In the experiment, we obtained excellent results by classifying the optimized ResNet model on Kaggle's Intel Image Classification data set.

• Journal of the Optical Society of Korea
• /
• v.6 no.4
• /
• pp.156-160
• /
• 2002

In this paper, we propose an improved optical security system using three phase-encoded images and the principle of interference. This optical system based on a Mach-Zehnder interferometer consists of one phase-encoded virtual image to be encrypted and two phase-encoded images, en-crypting image and decrypting image, where every pixel in the three images has a phase value of '0'and'$\pi$'. The proposed encryption is performed by the multiplication of an encrypting image and a phase-encoded virtual image which dose not contain any information from the decrypted im-age. Therefore, even if the unauthorized users steal and analyze the encrypted image, they cannot reconstruct the required image. This virtual image protects the original image from counterfeiting and unauthorized access. The decryption of the original image is simply performed by interfering between a reference wave and a direct pixel-to-pixel mapping image of the en crypted image with a decrypting image. Computer simulations confirmed the effectiveness of the proposed optical technique for optical security applications.

• Journal of Korean Library and Information Science Society
• /
• v.38 no.1
• /
• pp.89-106
• /
• 2007

This is to present the information and direction about color scheme image and adjective image in designing web page, by analysing the color image of our country's National University library's web page which is being operated now. The analysis method is to find the RGB of objective site through color emotion standard and to abstract the color chip. It is divided by color scheme image and adjective image. The scope of research is 41 National University libraries registered in National University Libraries Association. The result is that white and grey color of background and colors like light blue and green are main. In case of adjective image, nimble image and clear image was many. next is orderly bellowing image. and elegant image.

• Journal of information and communication convergence engineering
• /
• v.8 no.2
• /
• pp.185-190
• /
• 2010

In this paper we propose the CBIR algorithm which is based on a novel image block method that combined both color and edge feature. The main drawback of global histogram representation is dependent of the color without spatial or shape information, a new image block method that divided the image to 8 related blocks which contained more information of the image is utilized to extract image feature. Based on these 8 blocks, histogram equalization and edge detection techniques are also used for image retrieval. The experimental results show that the proposed image block method has better ability of characterizing the image contents than traditional block method and can perform the retrieval system efficiently.

• Journal of the Semiconductor & Display Technology
• /
• v.15 no.1
• /
• pp.33-35
• /
• 2016

This paper proposes a method utilizing image compression and transmission method for image segmentation in order to reduce the time required in the process of analyzing the image information that has in the image compression process. Many studies of existing with respect to the image segmentation are being studied as a way to split a lot of a particular part in the image. We divide full image into the N equal parts. And it is compressed using the field coding. This will reduce the time-consuming than using the conventional method.