COMPUTER VISION
   Creating Artificial Life




                                                       Ameer Mohamed Rajah
                              GRandD, International Water Management Institute
COMPUTER VISION
• Introduction


• System of Computer Vision


• Applications


• Example
WHAT IS COMPUTER VISION?

•   Computer vision is a field that includes methods for acquiring,
    processing, analyzing, and understanding images
•   Known as Image analysis, Scene Analysis, Image Understanding


•   duplicate the abilities of human vision by electronically perceiving and
    understanding an image


•   Theory for building artificial systems that obtain information from images.


•   Image data can take many forms, such as a video sequence, depth
    images, views from multiple cameras, medical scanner, satellite sensors
    etc.
COMPUTER VISION VS HUMAN VISION




     What we see         What a computer sees
COMPUTER VISION VS HUMAN VISION…
• Vision is an amazing feat of natural intelligence
• More human brain devoted to vision than anything else
• There are about 30,000 visual categories.
    • Learn 4.5 categories per day  18 years
    • At age 6, child can learn roughly all 30,000 (13.5day)
• Machines Can't Replicate Human Image Recognition, Yet. they
  do not possess our ability to recognize distorted images
WHY IS COMPUTER VISION DIFFICULT?
• It is a many-to-one mapping


• It is computationally intensive


• We do not understand the recognition problem
RELATION BETWEEN COMPUTER VISION AND
VARIOUS OTHER FIELDS [
COMPUTER VISION SYSTEM METHODS

•   Image acquisition
•   Pre-processing
•   Feature extraction
•   Detection/segmentation
•   Recognition an interpretation
RECOGNITION CUES
•   Color
•   Texture
•   Pattern
•   Shape
•   Association
MATHEMATICS IN COMPUTER VISION
  • Calculus
  • Linear Algebra
  • Probabilities and Statistics
  • Signal Processing
  • Projective Geometry
  • Computational Geometry
  • Optimization Theory
  • Control Theory
COMPUTER VISION APPLICATIONS
•   Controlling processes
•   Navigation
•   Detecting events
•   Organizing information
•   Modeling objects or environments
•   Interaction
•   Automatic inspection, e.g. in manufacturing applications
•   much more …...
OPTICAL CHARACTER RECOGNITION (OCR)
LOGIN WITHOUT A PASSWORD…
TARGET RECOGNITION
INTERPRETATION OF HIGH RESOLUTION
SATELLITE IMAGES
TRAFFIC MONITORING
FACE DETECTION
3D SHAPE RECONSTRUCTION
OBJECT RECOGNITION (IN MOBILE PHONES)




  Google Goggles
SPORTS
•   Hawk-Eye
SMART CARS
INTERACTIVE GAMES
INDUSTRIAL ROBOTS




    Vision-guided robots position nut runners on wheels
MOBILE ROBOTS
MEDICAL IMAGING
EXAMPLE
CAPTURING DIGITAL PHOTO (SENSOR)
CALCULATE PROBABILITY
PROBABILITY THRESHOLD
CLUMP
FILTER BY SIZE
FOCAL FILTERING FOR SMOOTHING
ERASING OUT
CONVERT TO VECTOR
FILTERING ISLANDS
CLIPPING OUTLIERS
IDENTIFY GEOMETRIC PARAMETERS AND
CALCULATE PARAMETER VALUES
FILTERING BY PROBABILITY
SMOOTHING POLYGONS
CREATE ORIENTED BOUNDING BOX
IDENTIFICATION OF AGRO WELLS
MACHINES CAN'T REPLICATE HUMAN IMAGE
            RECOGNITION

           THANK YOU

Computer Vision

Editor's Notes

  • #10 Standard procedures are applied to improve image quality
  • #28 Kjhk