Image edge detection is a vital process in various applications, such as medical image analysis, computer vision, and security systems. Several models were proposed to determine image edges. However, each method has some limitations in finding the best edges, such as choosing the ideal parameters or the presence of noise. New techniques, such as nature-inspired optimization, have emerged as a promising approach in several domains. These techniques may have the potential to provide advanced capabilities to improve the image edge detection process. A metaheuristic model such as the Bat algorithm may offer appropriate parameters for the edge detection algorithm. Therefore, the primary focus of this study is to build a new hybrid model that integrates the Bat algorithm and Canny filter to enhance the output of image edge detection process. To achieve the goal of this study, the hybrid model has been applied to JPG images. Notable improvements in edge detection were observed during the application of the proposed system on the tested images compared to the traditional Canny algorithm. The improvement rate in the performance of the proposed system reached 30%. It was concluded from this study that modifying the parameters of the Canny filter using the proposed dynamic model leads to optimizing the image edge detection processes. Therefore, integrating other algorithms, such as deep learning techniques, is recommended to study the parameters and performance of edge detection operators.