This notebook builds an end-to-end multi-class image detector using Mask-RCNN which is an algorithm for image detection with state of the art results in this subject.
Link for Mask R-CNN repository : https://github.com/matterport/Mask_RCNN
link for scientific paper on Mask R-CNN : https://arxiv.org/abs/1703.06870
Identifying a fruit in an image and drawing a bounding box on it
The data we're using is from Kaggle's Fruit Images for Object Detection competition https://www.kaggle.com/mbkinaci/fruit-images-for-object-detection
Robotic harvesting can provide a potential solution for the ever-increasing labour costs and increasing fruit quality For these reasons, there has been growing interest in the use of agricultural robots for harvesting fruit and vegetables over the past three decades
The Workflow is quite simple Since we'll be using transfer learning on the Mask-RCNN model already trained on the famous COCO Dataset