scispace - formally typeset
Search or ask a question
Topic

Channel (digital image)

About: Channel (digital image) is a research topic. Over the lifetime, 7211 publications have been published within this topic receiving 69974 citations.


Papers
More filters
01 Jan 1980
TL;DR: In this paper, an approach for exploiting the tradeoffs between source and channel coding in the context of image transmission is described. But this approach does not consider the impact of channel errors.
Abstract: An approach is described for exploiting the tradeoffs between source and channel coding in the context of image transmission. The source encoder employs two-dimensional (2-D) block transform coding using the discrete cosine transform (DCT). This technique has proven to be an efficient and readily implementable source coding technique in the absence of channel errors. In the presence of channel errors, however, the performance degrades rapidly, requiring some form of error-control protection if high quality image reconstruction is to be achieved. This channel coding can be extremely wasteful of channel bandwidth if not applied judiciously. The approach described here provides a rationale for combined source-channel coding which provides improved quality image reconstruction without sacrificing transmission bandwidth. This approach is shown to result in a relatively robust design which is reasonably insensitive to channel errors and yet provides performance approaching theoretical performance limits. Analytical results are provided for assumed 2-D autoregressive image models, while simulation results are provided for real-world images.

135 citations

Proceedings ArticleDOI
01 Jul 2016
TL;DR: The proposed salient object detection method for RGB-D images based on evolution strategy outperforms the state-of-the-art methods and utilizes cellular automata to iteratively propagate saliency on the initial saliency map.
Abstract: Salient object detection aims to detect the most attractive objects in images, which has been widely used as a fundamental of various multimedia applications. In this paper, we propose a novel salient object detection method for RGB-D images based on evolution strategy. Firstly, we independently generate two saliency maps on color channel and depth channel of a given RGB-D image based on its super-pixels representation. Then, we fuse the two saliency maps with refinement to provide an initial saliency map with high precision. Finally, we utilize cellular automata to iteratively propagate saliency on the initial saliency map and generate the final detection result with complete salient objects. The proposed method is evaluated on two public RGB-D datasets, and the experimental results show that our method outperforms the state-of-the-art methods.

134 citations

Posted Content
TL;DR: A novel approach is proposed, called mGANprior, to incorporate the well-trained GANs as effective prior to a variety of image processing tasks, by employing multiple latent codes to generate multiple feature maps at some intermediate layer of the generator and composing them with adaptive channel importance to recover the input image.
Abstract: Despite the success of Generative Adversarial Networks (GANs) in image synthesis, applying trained GAN models to real image processing remains challenging. Previous methods typically invert a target image back to the latent space either by back-propagation or by learning an additional encoder. However, the reconstructions from both of the methods are far from ideal. In this work, we propose a novel approach, called mGANprior, to incorporate the well-trained GANs as effective prior to a variety of image processing tasks. In particular, we employ multiple latent codes to generate multiple feature maps at some intermediate layer of the generator, then compose them with adaptive channel importance to recover the input image. Such an over-parameterization of the latent space significantly improves the image reconstruction quality, outperforming existing competitors. The resulting high-fidelity image reconstruction enables the trained GAN models as prior to many real-world applications, such as image colorization, super-resolution, image inpainting, and semantic manipulation. We further analyze the properties of the layer-wise representation learned by GAN models and shed light on what knowledge each layer is capable of representing.

134 citations

Journal ArticleDOI
TL;DR: The proposed single image dehazing method is based on a physical model and the dark channel prior principle and the selection of an atmospheric light value is directly responsible for the color authenticity and contrast of the resulting image.

132 citations

Proceedings ArticleDOI
16 Dec 2011
TL;DR: The experimental results show that the proposed approach can effectively enhance the underwater image and reduce the execution time, and requires less computing resource and is well suitable for implementing on the surveillance and underwater navigation in real time.
Abstract: Blurred underwater image is always an annoying problem in the oceanic engineering. In this paper, we propose an efficient and low complexity underwater image enhancement method based on dark channel prior. Our method employs the median filter instead of the soft matting procedure to estimate the depth map of image. Moreover, a color correction method is adopted to enhance the color contrast for underwater image. The experimental results show that the proposed approach can effectively enhance the underwater image and reduce the execution time. Besides, this method requires less computing resource and is well suitable for implementing on the surveillance and underwater navigation in real time.

130 citations


Network Information
Related Topics (5)
Feature extraction
111.8K papers, 2.1M citations
86% related
Image processing
229.9K papers, 3.5M citations
85% related
Feature (computer vision)
128.2K papers, 1.7M citations
85% related
Image segmentation
79.6K papers, 1.8M citations
85% related
Convolutional neural network
74.7K papers, 2M citations
84% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202216
2021559
2020643
2019696
2018613
2017496