Introduction to Computer Vision (CV)

Introduction to Computer Vision:

• CV is a field of artificial intelligence that trains machines to understand and interpret the visual world.
• Appliances that use or manipulate images tend to use CV.
• We process about 90% of data in visual form, so computer vision can tackle all the jobs that rely on human vision.

Types of Computer Vision:

1. Classic Computer Vision:
   • Relies on pre-built libraries of features.
   • It collects images, labels them according to similar characteristics, and groups them in a dataset, or library of features.

   INPUT => Feature Engineering (Manual Extraction +Selection) => Features => Classifier with Shallow Structure => Output

2. Deep Learning Computer Vision:
   • Requires neural networks to function, specifically convolutional neural networks (CNN).
   • The key difference between the two types is that classic CV uses features that we have already input into the library, while deep learning CV generates its own library of characteristics by using its CNN.

   INPUT => Feature Learning + Classifier (End-to-End Learning) => OUTPUT

Applications of computer vision:

1. Image segmentation
   • Partitions an image into multiple regions which can be examined/ manipulated separately. Ex: Image blur feature in Skype meetings
2. Object tracking
   • Monitors movement of an object. Ex: tracking pedestrian routes; monitoring car speeds.
3. Edge detection
   • Finds the outside edges of an object to identify image content accurately. Ex: night vision.
4. Object detection
   • Helps to identify important parts of an image. Ex: identifying human life; oil spills.
5. Facial recognition
   • Identifies specific individuals. E.g., automating the process of photo tagging.
6. Optical character recognition (OCR)
   • Recognizes words and numbers in scanned printed and hand- written documents, with accuracy rates of over 99%. E.g., manuscript study; note-taking.
7. Feature matching
   • Finds similar characteristics and groups them together. E.g., similar objects in photographs.
8. Pattern detection
   • Matches repeated shapes, colors and other visual indicators in images. E.g., handwriting recognition, fingerprint analysis.