Abstract
Structuring elements of fixed shape and size are used in most conventional mathematical morphology operations, which makes the border of image targets shift, produces new image artifacts and loses small image objects due to the diversity and complexity of the image targets. In this paper, a new construction algorithm for adaptive structuring elements is proposed based on the neighborhood gray difference changing vector field and relative density. The proposed structuring element is able to adaptively change shape according to the gray and edge characteristics of an image. This algorithm involves first incorporating the gray difference changing vector field to smooth the local image region and make the gray level within the image target more uniform and then defining a border degree function based on relative density to determine whether the center pixel of the local image region is a border pixel. The adaptive structuring element is composed of all the strong border pixels found in a local image region. Dilation and erosion operations and other derivative operations are proposed with this new adaptive structuring element based on conventional morphology operation principles. The experimental results show that this proposed algorithm is able to effectively suppress the shifting effect of the image target borders while accurately locating the border of the image target region. Additionally, other effective image information is retained and image distortion is reduced while weakening the image details.
Highlights
Mathematical morphology [1], [2] is a theory based on set theory, integral geometry and grid algebra that is used to analyze the geometric structure characteristics of images and to extract image features using structuring elements of a certain shape and size to perform morphology operations on all the pixels
EXPERIMENTAL RESULTS AND ANALYSIS To test the border preservation and antidistortion performance of the proposed adaptive structuring element in morphological operations, a simple binary image, a complex binary image and a grayscale image are used as experimental data
EXPERIMENTAL EVALUATION INDEXES The Abdou-Pratt quality factor (PFOM ), mean square error (MSE), peak signal-to-noise ratio (PSNR), structural similarity (SSIM ), gradient magnitude similarity deviation (GMSD) and time complexity are used as numerical indexes in the border retention and image distortion experiments
Summary
Mathematical morphology [1], [2] is a theory based on set theory, integral geometry and grid algebra that is used to analyze the geometric structure characteristics of images and to extract image features using structuring elements of a certain shape and size to perform morphology operations on all the pixels. A construction algorithm for adaptive morphology structuring elements is proposed based on neighborhood grayscale difference changing vector field and relative density This algorithm uses the grayscale and border (edge pixels) characteristics of an image to construct adaptive morphology structuring elements with variable shapes. The adaptive structuring elements can correspond to the shape of the image target, thereby maintaining the integrity of the necessary information of the target, improving the accuracy of locating the border of the image target region, and reducing the distortion of the target structure details This proposed algorithm is achieved by first smoothing the local region in the image using the neighborhood grayscale difference changing vector field and determining whether the center pixel of a local region is a border pixel by using a border degree function based on relative density.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
