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.

Digital fog effect filter method based on dark primary color channel prior principle

Abstract: The invention, which belongs to the computer application technology field, relates to a digital fog effect filter method based on dark primary color channel prior principle. A model in which an atmospheric scattering model is applied for defogging in haze weather and a dark primary color channel prior principle is employed to carry out operation on an image, wherein the operation including dark primary image extraction, atmospheric light estimation, transmissivity conversion, optimization compensation and fog effect simulation and the like. According to the invention, a solution scheme is proposed for limitation of an exiting model; on the basis of a perspective concept, a traditional defogging method is changed into a fog effect filter method to obtain foggy/fog-free scenes with different fog effects, so that defects existing in the prior art are overcome. According to the method, only a physical model and data calculation are needed to carry out correction operation on the physical model, thereby substantially reducing time and space and improving generality of the method.

Underwater Image Enhancement Using Scene Depth-Based Adaptive Background Light Estimation and Dark Channel Prior Algorithms

Abstract: Due to the complexity of the underwater environment, underwater images captured by optical cameras usually suffer from haze and color distortion. Based on the similarity between the underwater imaging model and the atmosphere model, the dehazing algorithm is widely adopted for underwater image enhancement. As a key factor of the dehazing model, background light directly affects the quality of image enhancement. This paper proposes a novel background light estimation method which can enhance the underwater image. And it can be applied in 30-60m depth with artificial light. The method combines deep learning to obtain red channel information of the background light in the dark channel of the underwater image. Then, the background light is obtained by adaptive color deviation correction. Finally, the experiments of underwater images enhancement are carried out, using the dark channel prior algorithm based on the proposed background light estimation method. The results show that the proposed method effectively improves underwater image blur and color deviation, and is superior to other methods in multiple non-reference image evaluation indicators.

Data processing system with common channel for image and character data

Abstract: A data processing system, in which image data is transmitted in units of predetermined length, e.g., a predetermined number of lines, and code data comprising a character or the like, is transmitted in units each of which contains the code data corresponding to the predetermined unit of the image data. The image and the code data are preferably transmitted on a common transmission channel, and can be separated upon reception for separate processing.

Smart fusion of visible and infrared image data

Abstract: A method combines two digital images, one in the visible range and the other in the infrared range. The combined image provides an intensity band of pixels and shows detected warm objects that are superimposed on the intensity band of pixels. A user of the present invention may (1) view increased detail in the fused image of a scene and (2) have high confidence that an object in the scene is warm or hot. Hot objects collected by the infrared channel, but not visible in the visible channel may also be seen by the viewer in the fused image.

Multi-Scale Adaptive Dehazing Network

Abstract: Since haze degrades an image including contrast decreasing and color lost, which has a negative effect on the subsequent object detection and recognition. single image dehazing is a challenging visual task. Most existing dehazing methods are not robust to uneven haze. In this paper, we developed an adaptive distillation network to solve the dehaze problem with non-uniform haze, which does not rely on the physical scattering model. The proposed model consists of two parts: an adaptive distillation module and a multi-scale enhancing module. The adaptive distillation block reassigns the channel feature response via adaptively weighting the input maps. And then the important feature maps are separated from the trivial for further focused learning. After that, a multi-scale enhancing module containing two pyramid downsampling layers is employed to fuse the context features for haze-free images restoration in a coarse-to-fine way. Extensive experimental results on synthetic and real datasets demonstrates that the proposed approach outperforms the state-of-the-arts in both quantitative and qualitative evaluations.