Overview of Computer Vision
and Its Applications
Group one
Introduction to Computer Vision
• • Computer Vision (CV) is a field of AI that
enables computers to process, analyze, and
interpret visual data.
• • Mimics human vision to extract insights from
images/videos.
• • Used in various industries like healthcare,
security, autonomous vehicles, etc.
History of Computer Vision
• 1960s-1980s: Edge detection (Sobel, Canny),
3D vision.
• 1990s: Machine Learning (Support Vector
Machines).
• 2000s: Large datasets (ImageNet), deep
learning progress.
• 2010s-Present: CNNs revolutionized image
recognition, object detection.
Key Computer Vision Tasks
• Image Classification: Assigning labels to images.
• Object Detection: Identifying objects with
bounding boxes.
• Image Segmentation: Dividing an image into
meaningful parts.
• Object Tracking: Following objects across frames
in videos.
• Pose Estimation: Identifying key points of
objects/people.
Applications of Computer Vision
• Healthcare: Medical imaging, tumor detection.
• Autonomous Vehicles: Object detection, lane
detection.
• Security: Facial recognition, surveillance.
• Retail: Automated checkout, customer
behavior analysis.
• Agriculture: Crop monitoring, automated
harvesting.
Image Basics in Computer Vision
• Pixels: Smallest unit of a digital image.
• Resolution: Determines image clarity (e.g.,
1920×1080).
• Color Spaces: RGB (screen), Grayscale (edge
detection), HSV (color filtering), CMYK
(printing).
Practical Example: Image
Classification
• Task: Identify whether an image contains a cat
or a dog.
• Approach: Use a Convolutional Neural
Network (CNN) trained on labeled images.
• Example: Google Photos uses CNNs to classify
and organize images.
Practical Example: Object
Detection
• Task: Detect pedestrians and vehicles in a
traffic video.
• Approach: Use YOLO (You Only Look Once) or
SSD (Single Shot Detector).
• Example: Self-driving cars (Tesla, Waymo) use
object detection to avoid collisions.
Practical Example: OCR (Optical
Character Recognition)
• Task: Extract text from a scanned document.
• Approach: Use Tesseract OCR to convert text
images into digital format.
• Example: Google Lens extracts and translates
text from images.
Conclusion
• Computer Vision is transforming industries by
enabling machines to interpret images.
• Deep Learning and CNNs have greatly
advanced its capabilities.
• Applications range from healthcare to self-
driving cars, retail, and agriculture.
• The future of CV includes AI-driven
automation and smarter image analysis.
