Image segmentation is the task in which we assign a label to pixels (all or some in the image) instead of just one label for the whole image. As a result, image segmentation is also categorized as a dense prediction task. Unlike detection using rectangular bounding boxes, segmentation provides pixel accurate locations of objects in an image. Therefore, image segmentation plays a very important role in medical analysis, object detection in satellite images, iris recognition, autonomous vehicles, and many more tasks.
With the advancements in deep learning methods, image segmentation has greatly improved in the last few years; in terms of both accuracy and speed. We can now generate segmentations of an image within a fraction of a second and still be very accurate and precise.
The Goal of this Post
Through this post, we’ll cover the intuition behind some of the main techniques and architectures used in image segmentation…
View original post 3,274 more words