• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• pp.676-684
• /
• 2022

As realistic media are widespread in various image processing areas, image or video compression is one of the key technologies to enable real-time applications with limited network bandwidth. Generally, image or video compression cause the unnecessary compression artifacts, such as blocking artifacts and ringing effects. In this study, we propose a Deep Residual Channel-attention Network, so called DRCAN, which consists of an input layer, a feature extractor and an output layer. Experimental results showed that the proposed DRCAN can reduced the total memory size and the inference time by as low as 47% and 59%, respectively. In addition, DRCAN can achieve a better peak signal-to-noise ratio and structural similarity index measure for compressed images compared to the previous methods.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.112-115
• /
• 2022

The process of deep learning usually needs to deal with massive data which has greatly limited the development of deep learning technologies today. Convolutional Neural Network (CNN) structure is often used to solve image classification problems. However, a large number of images may be required in order to train an image in CNN, which is a heavy burden for existing computer systems to handle. If the image data can be compressed under the premise that the computer hardware system remains unchanged, it is possible to train more datasets in deep learning. However, image compression usually adopts the form of lossy compression, which will lose part of the image information. If the lost information is key information, it may affect learning performance. In this paper, we will analyze the effect of image compression on deep learning performance on CNN-based cat and dog classification. Through the experiment results, we conclude that the compression of images does not have a significant impact on the accuracy of deep learning.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.825-828
• /
• 2022

In this paper, we propose an efficient image size selection method for video-based point cloud compression. The current MPEG video-based point cloud compression reference encoding process configures a threshold on the size of images while converting point cloud data into images. Because the converted image is compressed and restored by the legacy video codec, the size of the image is one of the main components in influencing the compression efficiency. If the image size can be made smaller than the image size determined by the threshold, compression efficiency can be improved. Here, we studied how to improve the compression efficiency by selecting the best-fit image size generated during video-based point cloud compression. Experimental results show that the proposed method can reduce the encoding time by 6 percent without loss of coding performance compared to the test model 15.0 version of video-based point cloud encoder.

• Journal of the Korean Society of Radiology
• /
• v.15 no.3
• /
• pp.281-291
• /
• 2021

This study aimed to measure the quantitative changes in images according to the use of compressed sensing in expressing the slow flow rate in TOF MRA test using magnetic resonance imaging. This study set different blood flow rate sections by using auto-injector and flow phantom and compared changes in the SNR, CNR, SSIM, and RMSE measurements by different CS factors between TOF with CS and TOF without CS. One-way ANOVA was performed to test the effect on the image induced by the increase of the CS factor. The results revealed that TOF MRA with CS significantly decreased scan time without significantly affecting SNR and CNR compared to TOF MRA with CS. On the other hand, the differences in SSIM and RMSE between TOF with CS and TOF without CS increased as the CS factor increased. Therefore, it is necessary to efficiently reduce scan time by adapting the CS technique while considering the appropriate range of the CS factor. Additionally, more studies are needed to evaluate CS factors and the similarity precision of images further.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5C
• /
• pp.496-512
• /
• 2007

In this paper, we propose a novel JPEG-2000 compressed image retrieval system using feature vector extracted through partial entropy decoding. Main idea of the proposed method is to utilize the context information that is generated during entropy encoding/decoding. In the framework of JPEG-2000, the context of a current coefficient is determined depending on the pattern of the significance and/or the sign of its neighbors in three bit-plane coding passes and four coding modes. The contexts provide a model for estimating the probability of each symbol to be coded. And they can efficiently describe texture images which have different pattern because they represent the local property of images. In addition, our system can directly search the images in the JPEG-2000 compressed domain without full decompression. Therefore, our proposed scheme can accelerate the work of retrieving images. We create various distortion and similarity image databases using MIT VisTex texture images for simulation. we evaluate the proposed algorithm comparing with the previous ones. Through simulations, we demonstrate that our method achieves good performance in terms of the retrieval accuracy as well as the computational complexity.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.605-608
• /
• 1999

In this paper, we proposed several scene analysis algorithms. These algorithms using image difference and histogram operate on the sequence of DC coefficient which is extracted from Motion JPEG or MPEG without full-frame decompression. Since DC sequence has the most information of full frame while it has reduced data. Experimental results show less than 1/64 of full frame analysing complexity and exactly analyze scene changes and extract key frames.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10b
• /
• pp.259-261
• /
• 1998

멀티미디어 데이터 중에서도 많은 부문의 응용에 사용되는 이미지 데이터의 내용 기반 검색에 대한 연구가 활발히 이뤄지고 있지만, 기조의 내용 기반 이미지 검색 대부분이 대상으로 삼고 있는 임지 포맷과는 달리 현재 이용되는 대부분의 이미지는 압축된 상태이다. 이미지 압축의 표준으로 사용되는 JPEG 압축 이미지에 대해서 압축 상태에서 특성을 추출하고 이를 검색에 이용하면 기존의 방법에 비해 압축을 해제하는 비용을 줄일 수 있고 블록 정보를 이용하는 장점을 가지게 된다. 본 논문에서는 JPEG 압축 이미지에서 블록 단위의 정보를 가진 특성으로 추출해내고 이를 사용한 이미지 검색 기법을 제안한다.

• ETRI Journal
• /
• v.6 no.1
• /
• pp.10-14
• /
• 1984

A method for image data compression, Called condtional replenishment, using the interframe correlation of image signal hasbeen studied. In this study, only those picture elements between successive frames are transmitted instead of every picture element in each, frame. A real time test simulator that can demonstrate the functions of conditional replenishment coder with condition of noiseless channel has been realized, and the result shows that the transmitting pixels can be compressed to the 25% of original signal retaining good picture quality.

• Journal of The Institute of Information and Telecommunication Facilities Engineering
• /
• v.10 no.2
• /
• pp.80-85
• /
• 2011

In this paper, I propose flexible base point used for a BTC(Block Truncation Coding). Halftoning images are used for printer by reducing the number of pixel depth. During over 20 years, many researches have been studied to apply this techniques to image compression. BTC algorithms are the compression methods using digital halftoning technique about images. In the BTC algorithm, an image block is divided into higher and lower domain compared with the mean of block. then the MAX and MIN representative values are evaluated by calculating the mean of higher and lower domain respectively. At a result, an image block(for example 88 size) is compressed into 64bits pixel representation and 16 bits of the MAX and MIN. And they also have been tried to sustain the image quality high after compression. In this paper, I found that there is some marginal possibility to enhance the image quality by adjusting the base point(generally mean of block) of existing algorithms.

• ETRI Journal
• /
• v.37 no.6
• /
• pp.1251-1258
• /
• 2015

We investigate an image recovery method for sparse-view computed tomography (CT) using an iterative shrinkage algorithm based on a second-order approach. The two-step iterative shrinkage-thresholding (TwIST) algorithm including a total variation regularization technique is elucidated to be more robust than other first-order methods; it enables a perfect restoration of an original image even if given only a few projection views of a parallel-beam geometry. We find that the incoherency of a projection system matrix in CT geometry sufficiently satisfies the exact reconstruction principle even when the matrix itself has a large condition number. Image reconstruction from fan-beam CT can be well carried out, but the retrieval performance is very low when compared to a parallel-beam geometry. This is considered to be due to the matrix complexity of the projection geometry. We also evaluate the image retrieval performance of the TwIST algorithm -sing measured projection data.