Computer Vision and Image Processing

- Overview

If you've used Instagram or any photo-sharing app, you've probably seen and/or used image filters. These filters are enabled through image processing techniques. In popular social apps, you may also have come across features that modify live selfies, such as putting bunny ears or swapping faces with someone. These fun and enjoyable experiences are powered by a branch of artificial intelligence commonly known as computer vision, which allows computers to understand digital images. Image processing and computer vision are distinct concepts but are largely complementary. 

Image processing is the process of creating a new image from an existing image, typically simplifying or enhancing the content in some way. It is a type of digital signal processing and is not concerned with understanding the content of an image. A given computer vision system may require image processing to be applied to raw input, e.g. pre-processing images.

Examples of image processing include:

• Normalizing photometric properties of the image, such as brightness or color.
• Cropping the bounds of the image, such as centering an object in a photograph.
• Removing digital noise from an image, such as digital artifacts from low light levels.

Computer vision generally refers to the techniques involved in allowing computers to understand images. The most common application is image recognition, a process that recognizes features of objects and images. Image recognition is used in many applications today, such as medical imaging, security surveillance, facial recognition, logo recognition, and buildings, among others. However, for these models to be useful, images first need to be labeled, segmented, or undergo other processing steps. 

Examples of computer vision include:

• Self-driving cars
• Pedestrian detection
• Parking occupancy detection
• Traffic flow analysis
• Road condition monitoring
• X-Ray analysis
• CT and MRI
• Cancer detection