Wound healing is a physiological process involving molecular and cellular activity with the aim to restore tissue integrity. Cell migration is essential for morphogenesis, inflammation, and cancer metastasis, and play a crucial role in tumor development and invasion. The wound healing assay is widely employed in the study of cell migration due to its simplicity and effectiveness as it enables real-time observation of cell movement, allowing quantitative analysis of migration and wound healing dynamics. However, when performed manually, quantitative analysis is a time-consuming process that can lead to inaccurate results, as is limited by human ability to delineate the border between cellular and free area. In this paper, we present a method for the automatic detection of edges that separate the cell-occupied area from the cell-free area using morphological image processing operations and a Convolutional Neural Network (CNN). This allows for an automatic, fast and fully reproducible temporal analysis of the migration rate of cells. The tool was designed to be user-friendly, minimizing the number of parameters required to obtain an accurate analysis, while still ensuring flexibility and robustness. The tool automatically calculates the migratory rate of cells from one time point acquisition and the next and to allow visualization of the evolutionary trend. Machine learning (ML) is already widely employed in medical imaging. Indeed, the use of a CNN alongside morphological processing operations for the study of wound healing assay also guarantees a good level of reproducibility to new cell lines. Finally, this paper presents a proof of concept demonstrating the applicability of a classification algorithm for cell-free area detection.