Task of Computer Vision- Semantic Segmentation, Classification and Localization, Instance Segmentation
Computer vision is a field of artificial intelligence (AI) that focuses on enabling machines to interpret, understand, and make decisions based on visual data from the world.
In this blog, we will discuss some tasks of Computer vision.
- Semantic Segmentation
- Classification and Localization
- Object Detection and Classification
- Instance Segmentation
1.Semantic Segmentation: In simple terms, We take an image as input and then output a decision of a category for every pixel in that image rather than assigning a single category to the entire image. Following methods can be used to implement this: a. Sliding window, b. Fully convolutional, c. Design a network which does Downsampling and Upsampling
2. Classification and Localization: In order to predict the correct category we also want to predict the location of the object in the image i.e. we also want to draw a boundary box around the image. This model will produce two different outputs. One is the class score and the other giving the coordinates of the bounding box describing the location.
3. Object Detection and Classification: Object detection deals with multiple objects and their spatial locations, while classification addresses a single overarching label for the entire image or a specific region. Approaches to implement: Sliding window approach, 2. Region based Convolutional Neural Network, 3. Fast R CNN, 4. Faster R CNN
4. Instance Segmentation: Instance segmentation is very similar to semantic segmentation. The only difference is that it distinguishes between different objects of the same class. While semantic segmentation tells us the class label of every pixel in the image, instance segmentation differentiates between different objects of the same class.
