Segmentation of digital images with region growing algorithm
Amin Sakhaei, Zahra Ghanbari · 2024
Image segmentation plays a pivotal role in image processing. With the advent and proliferation of artificial intelligence (AI), and its various algorithms deployed in digital image processing, assessing the accuracy of these algorithms has become increasingly important. However, manual segmentation is a labor-intensive and time-consuming task that requires considerable expertise and knowledge. To mitigate these issues, a traditional technique known as ‘region growing’ is often utilized in image segmentation. Region growing is a method that consolidates pixels or subregions into larger regions, following specific growth criteria. This study aimed to improve the segmentation of different regions of the images. Therefore, a pre-processing such as adaptation was performed on additional images, and then a region-growing algorithm was performed using eight-neighborhood to generate new pixels. Finally, different areas were separated from each other.