Image Segmentation by Agent-Based Pixel Homogenization

Image segmentation is the process of partitioning an image into multiple regions or objects, each representing a coherent and meaningful part of the image. Segmentation methods are highly sensitive to the lack of homogeneity in regions or objects owing to noise and intensity inconsistencies. Under such conditions, most approaches exhibit poor quality performance. This paper proposes an agent-based model approach for homogenization of images to reduce the presence of noisy pixels and undesirable artifacts. In our approach, each pixel in the image represents an agent, and a set of rules evaluates the states of neighboring agents to modify the intensity values of each pixel iteratively until different regions from the image assume homogeneous grayscale levels. The proposed method has been used in combination with the Otsu's method to evaluate its performance in image segmentation. The approach was evaluated with different types of images considering their homogeneity. Experimental results indicated that the proposed approach produces better-segmented images in terms of quality and robustness.