Edge enhancement

About: Edge enhancement is a research topic. Over the lifetime, 2324 publications have been published within this topic receiving 30962 citations.

A generic 2D sharpness enhancement algorithm for luminance signals

Abstract: In this paper we attempt to generalize a sharpness enhancement technique for TV applications. Basically, the enhancement is accomplished by adding overshoot to luminance edges. However, the optimal amount of overshoot added for a high image quality depends on the local image statistics. For this purpose, four properties of the video signal are analysed locally by separate units and depending on this analysis, we regulate the amount of sharpness enhancement to be provided. Due to these additional controls, the system is robust with respect to varying image statistics and yields a high performance.

Analysis of the fractional Hilbert transform

Abstract: The Hilbert transform is of interest for image-processing applications because it forms an image that is edge enhanced relative to an input object. Recently a fractional Hilbert transform was introduced that can select which edges are enhanced and to what degree the edge enhancement occurs. Although experimental results of this selective edge enhancement were presented, there was no explanation of this phenomenon. We analyze a one-dimensional fractional Hilbert transform acting on a one-dimensional rectangle function and show how it produces an output image that is selectively edge enhanced.

Adaptive Region-Based Image Enhancement Method for Robust Face Recognition Under Variable Illumination Conditions

Abstract: Variable illumination conditions, especially the side lighting effects in face images, form a main obstacle in face recognition systems. To deal with this problem, this paper presents a novel adaptive region-based image preprocessing scheme that enhances face images and facilitates the illumination invariant face recognition task. The proposed method first segments an image into different regions according to its different local illumination conditions, then both the contrast and the edges are enhanced regionally so as to alleviate the side lighting effect. Different from existing contrast enhancement methods, we apply the proposed adaptive region-based histogram equalization on the low-frequency coefficients to minimize illumination variations under different lighting conditions. Besides contrast enhancement, by observing that under poor illuminations the high-frequency features become more important in recognition, we propose enlarging the high-frequency coefficients to make face images more distinguishable. This procedure is called edge enhancement (EdgeE). The EdgeE is also region-based. Compared with existing image preprocessing methods, our method is shown to be more suitable for dealing with uneven illuminations in face images. Experimental results on the representative databases, the Yale B+Extended Yale B database and the Carnegie Mellon University-Pose, Illumination, and Expression database, show that the proposed method significantly improves the performance of face images with illumination variations. The proposed method does not require any modeling and model fitting steps and can be implemented easily. Moreover, it can be applied directly to any single image without using any lighting assumption, and any prior information on 3-D face geometry.

A no-reference blocking artifact measure for adaptive video processing

Abstract: Objective image quality metrics offer the prospect of adapting video processing algorithms to the quality of the incoming signal. In the context of image enhancement, such as peaking, contrast enhancement or color mapping, the original image does not necessarily correspond to the subjective optimum. There is, therefore, a compelling need for reliable quality metrics that are based exclusively on the characteristics of the processed images (no-reference). In this paper, we illustrate the design and application of no-reference quality metrics for the case of blocking artifacts that commonly degrade the quality of block-based DCT encoded video. We outline a simple cost-effective method that allows the grid position and its visibility to be determined without the need for access to the coding parameters. This information, in turn, is used to effectively suppress blocking artifacts while preserving the sharpness of object edges.