Topic
Edge enhancement
About: Edge enhancement is a research topic. Over the lifetime, 2324 publications have been published within this topic receiving 30962 citations.
Papers published on a yearly basis
Papers
More filters
•
19 Nov 1986TL;DR: In this article, a slope detector detects the slope of the luminance signal and, when a predetermined slope value is exceeded, produces a detection signal for energizing a counter, in which, as soon as the counter is energizing, the value of the color difference signal is stored and is available as an output signal.
Abstract: The invention relates to a circuit arrangement for increasing the resolution of color contours. A slope detector detects the slope of the luminance signal and, when a predetermined slope value is exceeded, produces a detection signal for energizing a counter. The counter controls an edge enhancement circuit for a color difference signal, in which, as soon as the counter is energizing, the value of the color difference signal is stored and is available as an output signal. After a predetermined number of equidistant clock pulses has been counted, the edge enhancement circuit (7, 16) supplies the actual color difference signal value. If before the end of the counting operation, a new detection signal is produced, then the edge enhancement circuit briefly receives and stores the actual color difference signal value, and the counter starts a new counting cycle.
13 citations
••
TL;DR: A multi-scale iterative framework for underwater image de-scattering, where a convolutional neural network is used to estimate the transmission map and is followed by an adaptive bilateral filter to refine the estimated results, and a strategy based on white balance is proposed to remove color casts of underwater images.
Abstract: Image restoration is a critical procedure for underwater images, which suffer from serious color deviation and edge blurring. Restoration can be divided into two stages: de-scattering and edge enhancement. First, we introduce a multi-scale iterative framework for underwater image de-scattering, where a convolutional neural network is used to estimate the transmission map and is followed by an adaptive bilateral filter to refine the estimated results. Since there is no available dataset to train the network, a dataset which includes 2000 underwater images is collected to obtain the synthetic data. Second, a strategy based on white balance is proposed to remove color casts of underwater images. Finally, images are converted to a special transform domain for denoising and enhancing the edge using the non-subsampled contourlet transform. Experimental results show that the proposed method significantly outperforms state-of-the-art methods both qualitatively and quantitatively.
13 citations
••
TL;DR: Inspired by unsharp masking, a classical technique for edge enhancement that requires only a single coefficient, a new and simplified formulation of the guided filter was proposed in this article, which enjoys a filtering prior from a low-pass filter.
Abstract: The goal of this paper is guided image filtering, which emphasizes the importance of structure transfer during filtering by means of an additional guidance image. Where classical guided filters transfer structures using hand-designed functions, recent guided filters have been considerably advanced through parametric learning of deep networks. The state-of-the-art leverages deep networks to estimate the two core coefficients of the guided filter. In this work, we posit that simultaneously estimating both coefficients is suboptimal, resulting in halo artifacts and structure inconsistencies. Inspired by unsharp masking, a classical technique for edge enhancement that requires only a single coefficient, we propose a new and simplified formulation of the guided filter. Our formulation enjoys a filtering prior from a low-pass filter and enables explicit structure transfer by estimating a single coefficient. Based on our proposed formulation, we introduce a successive guided filtering network, which provides multiple filtering results from a single network, allowing for a trade-off between accuracy and efficiency. Extensive ablations, comparisons and analysis show the effectiveness and efficiency of our formulation and network, resulting in state-of-the-art results across filtering tasks like upsampling, denoising, and cross-modality filtering. Code is available at \url{this https URL}.
13 citations
•
04 Jan 2012
TL;DR: In this paper, the edge enhancement and spot suppression of ultrasound images can be simultaneously realized using a simple algorithm, self adaptation, strong practicality and the like, which can be achieved by hardware, and can be conducted in real time.
Abstract: The invention relates to an image processing technique, particularly relates to an image data processing technique in an ultrasound image, and more particularly to a method and a device for reducing noise in the ultrasound image The method provided by the invention comprises the following steps: reading ultrasound image data; selecting an adjacent region with each pixel point as a center; computing the variance mean value ratio of the pixel points in each direction in the adjacent regions; computing discrimination factors according to the variance mean value ratio; respectively distinguishing the adjacent regions of the pixel points as an edge region, a non-edge region and a semi-edge region according to the discrimination factors; respectively carrying out filtering processing on the different edge regions; and outputting the processed ultrasound image data According to the technical scheme provided by the invention, the edge enhancement and spot suppression of images can be simultaneously realized; and the method provided by the invention has the advantages of simple algorithm, self adaptation, strong practicality and the like, is easy to achieve by hardware, and can be conducted in real time
13 citations
••
TL;DR: In this paper, the edge recognition techniques applied in this paper are the tilt angle (TA) and its horizontal derivative (TA-THDR), as well as the normalized vertical derivative of the total horizontal derivative, in which higher order derivative was involved.
13 citations