Introduction What is “image processing and computer vision”? Image Representation
Image Processing and Computer Vision: 12 What is “Image Processing and Computer Vision”? Image Processing manipulate image data generate another image Computer Vision process image data generate symbolic data
Image Processing and Computer Vision: 13 Computer Vision Reconstruction Recover 3D information from data Recognition Detect and identify objects Understanding What is happening in the scene?
Image Processing and Computer Vision: 14 Historical overview 1920s Coding images for transmission by telegraph (3 hours) 1960s Computers powerful enough to store images and process in realistic times Space program
Image Processing and Computer Vision: s s Applications Medical imaging Remote sensing Astronomy
Image Processing and Computer Vision: 16 Today DTV Image interpretation Biometry GIS Human genome project
Image Processing and Computer Vision: 17 Example images (1)
Image Processing and Computer Vision: 18 Example images (2)
Image Processing and Computer Vision: 19 Sample applications Character recognition (OCR) Printed text, Hand-printed text, Cursive text Biometry GIS
Image Processing and Computer Vision: 110 Printed Text Characteristics Regular shape Regular orientation Good contrast Can compare characters with a prototype
Image Processing and Computer Vision: 111 Template InputOutput
Image Processing and Computer Vision: 112 Hand Printed Text Characteristics Less regularity Must examine components of character
Image Processing and Computer Vision: 113 Cursive Text Totally irregular Careful analysis of strokes
Image Processing and Computer Vision: 114 Biometry Using personal characteristics to identify a person Fingerprints Face Iris DNA Gait etc
Image Processing and Computer Vision: 115 Iris Scan Striations on iris are individually unique Obvious applications: Security PIN
Image Processing and Computer Vision: 116 } fixed number of samples Locate the eye in the head image Radial resampling of iris Numerical description Analysis
Image Processing and Computer Vision: 117 GIS Earth/Planetary Observation Monitoring Exploration
Image Processing and Computer Vision: 118 Examples
Image Processing and Computer Vision: 119 System Overview Enhancement Feature Extraction Feature Recognition Image Recognition Captured data Labels
Image Processing and Computer Vision: 120 Image Representation Image capture Image quality measurements Image resolution Colour representation Camera calibration Parallels with human visual system
Image Processing and Computer Vision: 121 Image Capture Many sources Consider requirements of system Resolution Type of data Transducer
Image Processing and Computer Vision: 122 Representation Sampled data Spatial Amplitude On a rectangular array
Image Processing and Computer Vision: 123 Image Resolution How many pixels Spatial resolution How many shades of grey/colours Amplitude resolution How many frames per second Temporal resolution Nyquist’s theorem
Image Processing and Computer Vision: 124 Nyquist’s Theorem A periodic signal can be reconstructed if the sampling interval is half the period An object can be detected if two samples span its smallest dimension
Image Processing and Computer Vision: 125 Spatial Resolution n, n/2, n/4, n/8, n/16 and n/32 pixels on a side.
Image Processing and Computer Vision: 126 Amplitude Resolution Humans can see: About 40 shades of brightness About 7.5 million shades of colour Cameras can see: Depends on signal to noise ratio 40 dB equates to about 20 shades Images captured: 256 shades
Image Processing and Computer Vision: 127 Shades of Grey 256, 16, 4 and 2 shades.
Image Processing and Computer Vision: 128 Temporal Resolution Nyquist’s theorem for temporal data How much does an object move between frames? Can motion be understood unambiguously?
Image Processing and Computer Vision: 129 Colour Representation Newton White light composed of seven colours red, orange, yellow, green, blue, indigo, violet Three primaries could approximate many colours red, green, blue
Image Processing and Computer Vision: 130 CIE Colour Diagram
Image Processing and Computer Vision: 131 Other Colour Models YMCK IHS YCrCb etc
Image Processing and Computer Vision: 132 Camera Calibration Link image co-ordinates and world co- ordinates Extrinsic parameters Location and orientation of camera with respect to a co-ordinate frame Intrinsic parameters Relate pixel co-ordinates with camera reference frame co-ordinates
Image Processing and Computer Vision: 133 Extrinsic Parameters Camera’s Location Orientation With respect to world origin
Image Processing and Computer Vision: 134 World frame Camera frame translate and rotate
Image Processing and Computer Vision: 135 Intrinsic Parameters Characterise Optical Geometric Digital properties of camera Relate Image co-ordinates to camera co-ordinates
Image Processing and Computer Vision: 136 Pinhole Camera Image Object Optical centre Image and centre, object and centre are similar triangles. f Z
Image Processing and Computer Vision: 137 Distortionless If no distortions uniform sampling Co-ordinates linearly related offset and scale
Image Processing and Computer Vision: 138 Distorted Periphery is distorted k 2 = 0 is good enough
Image Processing and Computer Vision: 139 Parallels With Human Visual System Image capture Retina Focussing Cornea and lens Exposure Iris and retina
Image Processing and Computer Vision: 140 Summary Historical overview Sample applications Resolution Colour models Camera calibration
Image Processing and Computer Vision: k ought to be enough for anybody Bill Gates, 1981