ImageTaggingAndDenseAnnotation (In progress...!!!)

Before Diving deep into Dense Annotation, Let me go through Mask RCNN

This project is under progress

The project cites to the following papers on paper directory. And cites following repo

1. SSD: Single-Shot MultiBox Detector
2. Mask R-CNN for Object Detection and Segmentation

• Instance Segmentation i.e object Detection and Semantic Segmentation

• uses Faster Region Convolution Neural Network (FCNN) and Fully Connected Network (FCN)

Real Time (Video) tagging with Mask-RCNN

However frame rate is too low. Requires improvement on the algorithm, also my machine doesn't have an GPU