• International Journal of Internet, Broadcasting and Communication
• /
• 제16권2호
• /
• pp.22-30
• /
• 2024

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.

• 방송공학회논문지
• /
• 제18권6호
• /
• pp.935-938
• /
• 2013

본 레터논문에서는 컬러라이제이션(Colorization)기반 영상압축방법을 위해 평균이동기반의 영상분할법을 사용하여 컬러라이제이션 행렬을 분할하는 방법을 제안한다. 실험을 통해 제안한 방법을 사용할 경우 계산 속도는 대략 30배 이상 빨라지고, 기존의 역컬러라이제이션 기반의 압축방법에서 생기는 번짐(smearing) 현상도 많이 제거가 되는 것을 볼 수 있었다.

• 한국멀티미디어학회:학술대회논문집
• /
• 한국멀티미디어학회 2012년도 춘계학술발표대회논문집
• /
• pp.40-42
• /
• 2012

Colorization is a method using computer to add color to a black and white image automatically. The input is a grayscale image and some representative pixels (RPs). The RPs contain the color information for the image, and it indicates each region's color information. Colorization-based coding is a novel way for lossy image compression, it decodes a color image to get grayscale image and extracts RPs from the image. Because RPs decides the region's color and we also want small data size for image compression, form this viewpoint the paper proposes a way to get better and fewer RPs based on watershed segmentation. According to the segmentation result we also improve the original chrominance blending colorization method to save decode time and get better reconstruct image.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.38-43
• /
• 2009

The Chinese Ink Painting is an art with long history in Chinese culture. Painters can obtain various kinds of scenery by mixing water and ink properly. These papers provides a colorization technique that can transfer gray scale paintings to color paintings. Various colorization techniques for photorealistic images have good results. But these techniques are uncertainly suitable for Chinese Ink Painting. In our method, users only provide a gray scale Chinese Ink Painting and a similar color Chinese Ink Painting subjectively, system can automatically transfer the color from color painting to gray scale painting. We also provide a method for users to refine the automatically generated result.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.124-127
• /
• 2009

In this paper, we proposed automatically video colorization method with partial color sources in first frame. The input color sources are propagated to other gray pixels with the high correlation between two pixels. To robust again the errors in portion of the weak boundary, we calculate correlation between two pixels using dual-path comparison. Video colorization method should maintain the color connectivity between frames. Accordingly, we define reliability of primarily color by compare the color of neighborhood frames. We perform the color correction by blending neighboring color when the reliability of primarily color is low. We formalize this premise with energy function, and find the color to minimize the energy function. In this way, using property of video, we reduce the error caused by propagation and get result of natural changes between frames. Through simulation results, we show the proposed method derive a natural result more than previous method.

• 대한임베디드공학회논문지
• /
• 제13권6호
• /
• pp.313-319
• /
• 2018

We propose a post-processing algorithm to improve the quality of the RGB image generated by deep learning based colorization from the gray-scale image of an infrared camera. Wavelet fusion is used to generate a new luminance component of the RGB image luminance component from the deep learning model and the luminance component of the infrared camera. PSNR is increased for all experimental images by applying the proposed algorithm to RGB images generated by two deep learning models of SegNet and DCGAN. For the SegNet model, the average PSNR is improved by 1.3906dB at level 1 of the Haar wavelet method. For the DCGAN model, PSNR is improved 0.0759dB on the average at level 5 of the Daubechies wavelet method. It is also confirmed that the edge components are emphasized by the post-processing and the visibility is improved.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제25권2호
• /
• pp.26-38
• /
• 2021

Image coloration refers to adding plausible colors to a grayscale image or video. Image coloration has been used in many modern fields, including restoring old photographs, as well as reducing the time spent painting cartoons. In this paper, a method is proposed for colorizing grayscale images using a convolutional neural network. We propose an encoder-decoder model, adapting FusionNet to our purpose. A proper loss function is defined instead of the MSE loss function to suit the purpose of coloring. The proposed model was verified using the ImageNet dataset. We quantitatively compared several colorization models with ours, using the peak signal-to-noise ratio (PSNR) metric. In addition, to qualitatively evaluate the results, our model was applied to images in the test dataset and compared to images applied to various other models. Finally, we applied our model to a selection of old black and white photographs.

• 한국멀티미디어학회논문지
• /
• 제21권11호
• /
• pp.1271-1278
• /
• 2018

The NDT using ultrasonic is largely divided into A-Scan and C-Scan methods. Since A-Scan method is subject to subjective judgement by trained personnel, C-Scan method has been introduced, which presents the weld area in two dimensions by placing the transducers two dimensionally used in the A-Scan method. Therefore, it is necessary to develop equipment that can provide weld quality without the help of a welding expert and the presentation of effective C-Scan images. Thus, in this paper, the algorithms that express a low resolution 2-dimensional gray image formed by C-Scan method as a high-resolution color C-Scan image and automatically determine the weld quality from the generated C-Scan color image. The high resolution color C-Scan images proposed in this paper allow the exact shape of the weld point to be expressed, and an objective algorithm to use this image to automatically determine weld quality.

• 대한원격탐사학회지
• /
• 제34권6_3호
• /
• pp.1415-1425
• /
• 2018

다목적실용위성 5호는 국내 최초로 영상레이더(SAR)가 탑재된 지구관측위성이다. SAR 영상은 위성에 부착된 안테나로부터 방사된 마이크로파가 물체로부터 반사된 신호를 수신하여 생성된다. SAR는 대기 중의 입자의 크기에 비해 파장이 긴 마이크로파를 사용하기 때문에 구름이나 안개 등을 투과할 수 있으며, 주야간 구분 없이 고해상도의 영상을 얻을 수 있다. 하지만, SAR 영상에는 색상 정보가 부재하는 제한점이 존재한다. 이러한 SAR 영상의 제한점을 극복하기 위해, 도메인 변환을 위해 개발된 딥러닝 모델인 Cycle GAN을 활용하여 SAR 영상에 색상을 대입하는 연구를 수행하였다. Cycle GAN은 unpaired 데이터셋 기반의 무감독 학습으로 인해 학습이 불안정하다. 따라서 Cycle GAN의 학습 불안정성을 해소하고, 색상 구현의 성능을 향상하기 위해 다중 크기 식별자를 적용한 MS Cycle GAN을 제안하였다. MS Cycle GAN과 Cycle GAN의 색상 구현 성능을 비교하기 위하여 두 모델이 Florida 데이터셋을 학습하여 생성한 영상을 정성적 및 정량적으로 비교하였다. 다양한 크기의 식별자가 도입된 MS Cycle GAN은 기존의 Cycle GAN과 비교하여 학습 결과에서 생성자 및 식별자 손실이 대폭 감소되었고, 나뭇잎, 강, 토지 등의 영역 특성에 부합하는 색상이 구현되는 것을 확인하였다.

• 대한전자공학회논문지SP
• /
• 제47권4호
• /
• pp.20-27
• /
• 2010

본 논문에서는 웨이블릿 패킷 변환(WPT) 기반의 컬러화 알고리즘에서 슈도랜덤코드(pseudo-random code) 정보의 삽입을 통해 복원된 컬러 영상에서 채도를 보상하는 방법을 제안한다. 우선 컬러 영상을 흑백 영상으로 변환하는 과정(컬러-그레이변환)에서 RGB 영상을 YCbCr 영상으로 변환한 후, Y 영상에 2레벨 웨이블릿 패킷 변환을 적용하여 정보량이 최소인 부영역(수평의 수직, 수직의 수평 부영역)에 CbCr 영상을 삽입한다. 이때 프린팅 및 스캐닝 과정에서 발생하는 채도 열화를 보상하기 위해 원본 영상 CbCr의 최대값 및 최소값을 슈도랜덤코드 형태로 변환하여 대각의 대각 부영역에 역시 삽입한다. 슈도랜덤코드는 CbCr의 최대값 및 최소값을 흰색 점의 개수로 표현한 영상으로, 컬러 복원 과정(그레이-컬러변환)에서 이를 추출하여 원본의 CbCr 최대값 및 최소값과 복원 영상의 CbCr 최대값 및 최소값과의 비를 가중치로 이용함으로써 채도 보상 알고리즘을 수행한다. 실험을 통해 제안된 방법이 복원된 컬러 영상에서 채도를 향상시킴을 색차와 PSNR 수치로 확인할 수 있었다.