Here, we’ll be learning the methodologies to implement Object Detection
Basically, how does Object Detection work?
The basic principle of Object Detection is Deep learning (also known as deep structured learning is part of a broader family of machine learning methods based on artificial neural networks with representation learning. This learning can supervise, semi-supervised, or unsupervised).
To read more about Deep learning – https://en.wikipedia.org/wiki/Deep_learning
Deep learning-based object detection models typically have two parts. An encoder takes an image as input and runs it through a series of blocks and layers that learn to extract statistical features had used to locate and label objects. Outputs from the encoder need to pass to a decoder, which predicts bounding boxes and labels for all pictures. The encoder and the decoder play a rapid work in this.
I don’t want to bore you guys, so let’s skip the theory part and go to the methodologies.
Deep learning-based object detection models
- R-CNN (Region-based Convolutional Neural Networks)
- YOLO (You look only once)
There are few other models out there, but they’re not so popular as
- SSD (Single Shot Detector)
- MobileNet + SSD
We’ll be learning YOLO with the implementation in upcoming parts
I’ll end this part by telling you the differences in Image Classification