What is Image Segmentation?

Data annotation is the process of labeling training data to make it usable in supervised learning tasks. In 2018 the survey What AI can and can’t do (yet) for your business by McKinsey states that the first limitation to AI applications is the lack of labeled data.

Labeled images are the backbone of AI systems such as self-driving cars and automated medical imagery analysis which now requires tens, hundreds of thousands, even millions of images to train. Therefore the acquisition cost of those data can not be neglected. Previous techniques of annotation such as bounding boxes while cheap limit the performance of deep learning models. Bounding boxes are limited when annotating overlapping entities or non-rectangular objects. 

Image segmentation

Image segmentation is the process of dividing an image into multiple segments. There are three tasks of image segmentation present in the industry

1- Instance segmentation - In instance segmentation, each individual object of the image is annotated at the pixel level. It is the equivalent of pixel-accurate bounding boxes.

2-Semantic segmentation - In semantic segmentation requires each pixel of an image to be associated with a semantic label without distinction of instances.

3-Panoptic segmentation - In Panoptic segmentation is a combination of instance segmentation and semantic segmentation, each pixel is associated with a semantic label taking into account each instance of objects within the image

Original Source:-  Kili Technology