Adaptive Edge Detection Algorithm Based on Grey Entropy Theory and Textural Features

Abstract

The traditional edge detection method is altogether inaccurate, nonadaptive, and particularly ineffective on noisy images. This paper proposes a novel edge detection algorithm based on gray entropy theory and local texture features. In the 3×3 neighborhood window, 28 comparison sequences are constructed according to local texture features. The reference sequence is composed of the median of all elements in the 3×3 neighborhood window. A total of 28 gray relation degrees as obtained by gray relation analysis between the 28 comparison sequences and reference sequences, as well as 28 gray relation degrees, are analyzed by gray entropy theory to initially filter the image. Gray entropy analysis is then performed on the comparison sequences composed of 28 texture features and reference sequences composed of the central pixel points of the filtered image to determine the maximum gray entropy difference. A comparative threshold adaptive acquisition method is designed to separate gray entropy difference sequence elements and identify all edge points accordingly. The simulation results show that the proposed algorithm effectively achieves adaptive edge detection and has strong anti-noise capability. The results of this study may provide a workable reference for edge information detection in the field of artificial intelligence (e.g., image recognition, pattern recognition applications).INDEX TERMS Image processing, image edge detection, gray relation analysis, gray entropy theory, textural feature analysis.

Laboratory Evaluation of the Permeability Durability of Utilization of Oil Shale Waste as Fine Aggregate in Open Grade Friction Course in Seasonal Frozen Regions

“…In contrast, a high order system has low entropy. Thus, based on the relationship between entropy and order, the entropy value can be used to describe the order degree of the clogging state and to estimate its evolution direction [39][40][41].…”

Adaptive Edge Detection Algorithm Based on Improved Grey Prediction Model

“…The "edge" is the part of a given image where the gray value changes drastically [1], [2]. The edge represents rich and useful information, making edge detection an important preprocessing step in many artificial intelligence applications [3]- [5], [16].…”

“…A computer does not recognize whether a pixel is an edge in a local area when performing edge detection, so when it processes the image as the computer processes information: with "incomplete global information". Grey system theory is very well-suited to edge detection for this reason [2]. At present, the edge detection algorithms based on the grey system theory mainly use three types of grey models, namely grey correlation model, grey prediction model, and grey correlation entropy model.…”

“…Zhang et al [34] established the grey relation entropy theory based on the theory of Shannon entropy in 1996. Zheng et al [2] proposed an automatic edge detection algorithm based on grey entropy in 2019 which does have excellent edge detection performance, but is prone to double edges and has an overly time-consuming noise filtering algorithm.…”

Multiscale Gradient Maps Augmented Fisher Information-Based Image Edge Detection

“…Entropy theory is an important approach that is widely used for solving the edge detection problem: Zhen et al [11] combined grey entropy theory and textural features to detect the edge, Sert and Avci [20] used a technique that is called a neutrosophy based on maximum norm entropy. Recently, Abdel-Azim et al [1] proposed an edge detection algorithm based on non-parametric Fisher information (FI) measure [3], [4] based local thresholding value selection and masks.…”