Edge enhancement

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

Apparatus and method for smoothing regions and enhancing edges in gray scale images

Abstract: An apparatus and method for enhancing image data elements used to form a gray scale image are disclosed. The apparatus includes an adaptive neighborhood mask that is applied to a group of data image elements centered about a selected pixel to segregate the elements into center and surround regions about the selected element or pixel. The mask further modifies the elements with weighting factors to derive a contrast vector for the selected data elements in the adaptive neighborhood. This vector is compared to a smoothing window and a pair of edge enhancement windows to determine whether the selected element requires smoothing or enhancement to more clearly define a surface or an edge, respectively. If the element requires smoothing or enhancing, its gray scale value is modified, otherwise it is not modified. The device performs this task for each data element. The enhanced data is analyzed to determine if further enhancement is possible and, if so, the process continues upon the adjusted data until the enhancement of the image data is maximized. An edge area selector may further enhance the image data elements by selecting a small group of elements at the unterminated end of a detected edge in the enhance image. The selected group is enhanced by adjusting the edge enhancement window or by changing the weighting factors and restoring the gray scale values of the selected group to their unenhanced values.

Mathematical-morphology-based edge detectors for detection of thin edges in low-contrast regions

Abstract: A new edge detector based on mathematical morphology to preserve thin edge features in low-contrast regions as well as other apparent edges is proposed. A quad-decomposition edge enhancement process, a thresholding process, and a mask-based noise filtering process were developed and used to enhance thin edge features, extract edge points and filter out some meaningless noise points, respectively. Moreover, five bipolar oriented edge masks were also designed to remove most of the incorrectly detected edge features. Many experiments were conducted to evaluate and compare the performance of the proposed algorithm and several conventional ones. Pratt's figure of merit achieved by the proposed algorithm was as high as 92.5. The comprehensive experimental results show that the proposed algorithm is capable of preserving thin edge details successfully in low-contrast regions and is robust against noise.

A new high resolution filter for source edge detection of potential field data

Abstract: Determining the source edges is a frequently requested task in the analysis of potential fields. However, the edge detection methods have some drawbacks or shortcomings, for example, blurred respon...

Efficient Transformer for Remote Sensing Image Segmentation

Abstract: Semantic segmentation for remote sensing images (RSIs) is widely applied in geological surveys, urban resources management, and disaster monitoring. Recent solutions on remote sensing segmentation tasks are generally addressed by CNN-based models and transformer-based models. In particular, transformer-based architecture generally struggles with two main problems: a high computation load and inaccurate edge classification. Therefore, to overcome these problems, we propose a novel transformer model to realize lightweight edge classification. First, based on a Swin transformer backbone, a pure Efficient transformer with mlphead is proposed to accelerate the inference speed. Moreover, explicit and implicit edge enhancement methods are proposed to cope with object edge problems. The experimental results evaluated on the Potsdam and Vaihingen datasets present that the proposed approach significantly improved the final accuracy, achieving a trade-off between computational complexity (Flops) and accuracy (Efficient-L obtaining 3.23% mIoU improvement on Vaihingen and 2.46% mIoU improvement on Potsdam compared with HRCNet_W48). As a result, it is believed that the proposed Efficient transformer will have an advantage in dealing with remote sensing image segmentation problems.