Project 10
Mask R-CNN is a convolutional neural network where it is the art of network in terms of image segmentation. The computer vision task image segmentation is the process of partitioning a digital image into multiple segments like sets of pixels. This segmentation is used to locate the objects and boundaries.
There are two types of image segmentation:
- Instance Segmentation
- Semantic Segmentation
Semantic Segmentation:
It classifies each pixel into a fixed set of categories without differentiating object instances. Like it classifies similar objects as a single class from the pixel level.
Instance Segmentation:
It will classify the similar object from each pixel and provide different labels for better identification.
Steps implemented in codings are:
- Creating the bounding boxes according to the image boxes.
- Then using the rectangle function in OpenCV we have created bounding boxes
- Then we extract the region of interest and place those things in mask images
- The mask image is exactly equal in image dimension.
- providing the colors for various mask images for identification.
