Yapay Zeka Hızlı Bakış & Çıkarımlar
AI InsightThe experimental results show that the proposed method can significantly reduce the speckle noise from digital images while preserving edges, textures, and valuable details.
📌 3 Maddede Bu Makale
Özet
In this paper, a novel fuzzy system-based method for speckle noise removal is proposed. The proposed method consists of a fuzzy inference system, an edge detection and dilation unit, and an image combiner. The fuzzy inference system includes 5 inputs and 1 output, and it is responsible for filtering the speckle noisy image. The inputs of the fuzzy system consist of the center pixel of the filtering window and its 2 horizontal and vertical neighbors. The edge detection and dilation unit is used for classifying the uniform areas and nonuniform image regions such as edges. The image combiner unites the output images filtered 1 and 2 times according to the information coming from the edge detection and dilation unit. The training phase of the fuzzy inference system is implemented using the clonal selection optimization algorithm with appropriate training data. The performance of the proposed method is compared with popular speckle noise removal filters available in the literature by performing extensive simulations. The experimental results show that the proposed method can significantly reduce the speckle noise from digital images while preserving edges, textures, and valuable details.
Abstract
In this paper, a novel fuzzy system-based method for speckle noise removal is proposed. The proposed method consists of a fuzzy inference system, an edge detection and dilation unit, and an image combiner. The fuzzy inference system includes 5 inputs and 1 output, and it is responsible for filtering the speckle noisy image. The inputs of the fuzzy system consist of the center pixel of the filtering window and its 2 horizontal and vertical neighbors. The edge detection and dilation unit is used for classifying the uniform areas and nonuniform image regions such as edges. The image combiner unites the output images filtered 1 and 2 times according to the information coming from the edge detection and dilation unit. The training phase of the fuzzy inference system is implemented using the clonal selection optimization algorithm with appropriate training data. The performance of the proposed method is compared with popular speckle noise removal filters available in the literature by performing extensive simulations. The experimental results show that the proposed method can significantly reduce the speckle noise from digital images while preserving edges, textures, and valuable details.