http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Indra Imanuel (검색결과 3 건)
- 무료
- 기관 내 무료
- 유료
-
Demosaicing based Image Compression with Channel-wise Decoder
Indra Imanuel,이석호 한국인터넷방송통신학회 2023 International Journal of Internet, Broadcasting an Vol.15 No.4
In this paper, we propose an image compression scheme which uses a demosaicking network and a channel-wise decoder in the decoding network. For the demosaicing network, we use as the input a colored mosaiced pattern rather than the well-known Bayer pattern. The use of a colored mosaiced pattern results in the mosaiced image containing a greater amount of information pertaining to the original image. Therefore, it contributes to result in a better color reconstruction. The channel-wise decoder is composed of multiple decoders where each decoder is responsible for each channel in the color image, i.e., the R, G, and B channels. The encoder and decoder are both implemented by wavelet based auto-encoders for better performance. Experimental results verify that the separated channel-wise decoders and the colored mosaic pattern produce a better reconstructed color image than a single decoder. When combining the colored CFA with the multi-decoder, the PSNR metric exhibits an increase of over 2dB for three-times compression and approximately 0.6dB for twelve-times compression compared to the Bayer CFA with a single decoder. Therefore, the compression rate is also increased with the proposed method than with the method using a single decoder on the Bayer patterned mosaic image.
-
Denoising Diffusion Null-space Model and Colorization based Image Compression
Indra Imanuel,Dae-Ki Kang,Suk-Ho Lee The Institute of Internet 2024 International Journal of Internet, Broadcasting an Vol.16 No.2
Image compression-decompression methods have become increasingly crucial in modern times, facilitating the transfer of high-quality images while minimizing file size and internet traffic. Historically, early image compression relied on rudimentary codecs, aiming to compress and decompress data with minimal loss of image quality. Recently, a novel compression framework leveraging colorization techniques has emerged. These methods, originally developed for infusing grayscale images with color, have found application in image compression, leading to colorization-based coding. Within this framework, the encoder plays a crucial role in automatically extracting representative pixels-referred to as color seeds-and transmitting them to the decoder. The decoder, utilizing colorization methods, reconstructs color information for the remaining pixels based on the transmitted data. In this paper, we propose a novel approach to image compression, wherein we decompose the compression task into grayscale image compression and colorization tasks. Unlike conventional colorization-based coding, our method focuses on the colorization process rather than the extraction of color seeds. Moreover, we employ the Denoising Diffusion Null-Space Model (DDNM) for colorization, ensuring high-quality color restoration and contributing to superior compression rates. Experimental results demonstrate that our method achieves higher-quality decompressed images compared to standard JPEG and JPEG2000 compression schemes, particularly in high compression rate scenarios.
-
인드라 임마누엘(Indra Imanuel),이석호(Suk-ho Lee) 한국정보통신학회 2021 한국정보통신학회 여성 ICT 학술대회 논문집 Vol.2021 No.8
이미지 초해상도(Superresolution)에 대한 최근 연구는 GAN(Generative Adversarial Network)을 사용하여 저해상도 영상의 입력에 대응하는 고해상도 이미지를 생성하는 연구가 주를 이루고 있다. 그런데 이와 같이 GAN을 이용하여 생성된 초해상도 영상은 선명하지만 내용면에서는 저해사도 영상의 원래 내용과는 다른 출력이 나오는 경우가 많다. 특히 학습할 때 사용한 데이터셋과 성격이 다른 저해상도 영상을 입력으로 줄 때 이러한 현상이 심화가 된다. 또한 기존의 GAN들은 많은 판별신경망을 사용하여 학습 시 시간과 컴퓨팅 자원을 많이 소비하는 반면에 본 논문에서 제안한 방법은 판별 신경망의 개수를 줄임으로써 학습이 더 빠르고 효율적으로 진행이 될 수 있도록 하고 있다. 제안한 방법을 사용함으로써 학습한 데이터셋과 성질이 다른 저해상도 영상이 압력으로 들어와도 내용면에서 같은 고해상도 영상이 산출되는 것을 실험을 통해 확인할 수 있다. Recent work in image superresolution has been mainly done using Generative Adversarial Network (GANs) to generate high-resolution images that correspond to inputs from low-resolution images. However, while super-resolution images generated using GAN are clear, output is often different from the original contents of low-resolution images. In particular, this phenomenon intensifies when low-resolution images with different characteristics are given as inputs from the datasets used in learning. Moreover, while exiting GANs use a large amount of discriminative neural network to consume time and computing resources during training, the method proposed in this paper reduces the number of discriminative neural networks, enabling learning to proceed faster and more efficiently. By using the proposed method, it can be confirmed through experiments that the same high-resolution image is produced in terms of content even if a low-resolution image with different properties from the learned dataset enters the input.
ScienceON
eArticle연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
