Digital Image Processing DIP Dr Abdul Basit Siddiqui
Digital Image Processing (DIP) Dr. Abdul Basit Siddiqui Assistant Professor-FURC 11/1/2020 FURC-BCSE 7 1
Digital Image Processing (DIP) Instructor Dr. Abdul Basit Siddiqui Text Book R. C. Gonzalez and R. E. Woods, “Digital Image Processing, Pearson Education, Inc. , 2002. Prerequisites 1. Fundamental knowledge of probability and random variables, Vectors and Matrices. 2. Working knowledge of Matlab 3. DSP topics such as convolution, FFT, filtering, etc. Yahoo Group Lectures and Assignments will be updated on yahoo group regularly. 11/1/2020 FURC-BCSE 7 2
Grading Policy Attendance 05% Assignments 05% Quizzes 05% Project 05% Midterm 30% Final 50% 11/1/2020 FURC-BCSE 7 3
History • 1921: Image transmission – Newspaper industry – Cable transmission – London – New York 11/1/2020 FURC-BCSE 7 4
History • 1960’s: Space program – Moon picture – Enhancement by computer • 1970: Computerized tomography (CT) • The first picture of the moon by a U. S. spacecraft on July 31, 1964 at 9: 09 A. M. (courtesy of NASA) 11/1/2020 FURC-BCSE 7 5
Why Do We Process Images? § Facilitate picture storage and transmission – Efficiently store an image in a digital camera – Send an image through mobile phone § Enhance and restore images – Remove scratches from an old photo – Improve visibility of tumor in a radiograph 11/1/2020 FURC-BCSE 7 6
Why Do We Process Images? § Extract information from images – Measure water pollution from aerial images – Measure the 3 D distances and heights of objects from stereo images § Prepare for display or printing – Adjust image size – Halftoning 11/1/2020 FURC-BCSE 7 7
Image Processing Applications – – – Nuclear medicine Medical Diagnostics Automated Industrial Inspection Remote Sensing • Weather Prediction • Military reconnaissance Geological exploration Astronomical Observations Image database management The paperless office Photographers, advertising agencies and publishers Machine vision Biometrics • Finger Prints • Iris etc. Movies and entertainment 11/1/2020 FURC-BCSE 7 8
Image Enhancement 11/1/2020 FURC-BCSE 7 9
Image Processing Examples Photo Restoration Damaged Image 11/1/2020 Restored Image FURC-BCSE 7 10
Image Processing Examples Photo Restoration 11/1/2020 FURC-BCSE 7 11
Image Processing Examples Photo Colorization Original B/W Image 11/1/2020 Colorized Image Original Image FURC-BCSE 7 Colorized Image 12
Image Processing Examples Photo Colorization 11/1/2020 FURC-BCSE 7 13
Image Processing Examples Original Images 11/1/2020 Enhanced Images FURC-BCSE 7 14
Image Processing Examples Restoration of Image from Hubble Space Telescope Faulty Image of Saturn 11/1/2020 Recovered Image FURC-BCSE 7 15
Image Processing Examples Halftoning 11/1/2020 FURC-BCSE 7 16
Image Processing Examples Halftoning 11/1/2020 FURC-BCSE 7 17
Image Processing Examples Halftoning 11/1/2020 FURC-BCSE 7 18
Image Processing Examples Extraction of Settlement Area from an Aerial image Faulty Image of Saturn 11/1/2020 Recovered Image FURC-BCSE 7 19
Image Processing Examples Earthquake Analysis from Space Image shows the ground displacement of a typical area due to earthquake 11/1/2020 FURC-BCSE 7 20
Image Processing Examples Stereo Images from Satellite Image shows the ground displacement of a typical area due to earthquake 11/1/2020 FURC-BCSE 7 21
Image Processing Examples 11/1/2020 FURC-BCSE 7 22
Image Processing Examples Face Detection Image shows the ground displacement of a typical area due to earthquake 11/1/2020 FURC-BCSE 7 23
Image Processing Examples Face Tracking Image shows the ground displacement of a typical area due to earthquake 11/1/2020 FURC-BCSE 7 24
Image Processing Examples Face Morphing Faulty Image of Saturn 11/1/2020 Recovered Image FURC-BCSE 7 25
Image Morphing 11/1/2020 FURC-BCSE 7 26
Image Processing Examples Fingerprint Recognition Faulty Image of Saturn 11/1/2020 Recovered Image FURC-BCSE 7 27
Applications of DIP § Electromagnetic (EM) band Imaging – Gamma ray band images – X-ray band images –Ultra-violet band images – Visual light and infra-red images – Imaging based on micro-waves and radio waves 11/1/2020 FURC-BCSE 7 28
– Some Research Projects 11/1/2020 FURC-BCSE 7 29
Monitoring Human Behavior from Video Taken in an Office Environment • A system which makes context-based decisions about the actions of people in a room. These actions include entering, using a computer terminal, opening a cabinet, picking up a phone, etc. • Source: http: //server. cs. ucf. edu/~vision/ 11/1/2020 FURC-BCSE 7 30
EM Spectrum 11/1/2020 FURC-BCSE 7 31
Applications of DIP (EM Band Imaging) § Gamma-Ray Imaging – Nuclear medicine, astronomical observations. § X-Ray Imaging – Medical diagnostics (CAT scans, x-ray scans), industry, astronomy. § Ultra-Violet Imaging – Fluorescence microscopy, astronomy § Visible & Infrared-band Imaging (most widely used) – Light microscopy, astronomy, remote sensing, industry, law enforcement, military recognizance, etc. § Micro-wave and Radio band Imagery – Radar, Medicine (MRI), astronomy 11/1/2020 FURC-BCSE 7 32
MONITORING HEAD/EYE MOTION FOR DRIVER ALERTNESS 11/1/2020 FURC-BCSE 7 33
MONITORING FAST FOOD PRODUCTION • The purpose of the project is to automatically monitor a fast food employee as she puts together a sandwich. Helpful in determining correctness of sandwich assembly, collecting statistics on employee performance and food safety inspection. 11/1/2020 FURC-BCSE 7 34
Classification of DIP and Computer Vision Processes § Low-Level Process: (DIP) – Primitive operations where inputs and outputs are images; major functions: image pre-processing like noise reduction, contrast enhancement, image sharpening, etc. § Mid-Level Process (DIP and Computer Vision) – Inputs are images, outputs are attributes (e. g. , edges); major functions: segmentation, description, classification / recognition of objects § High-Level Process (Computer Vision) – Make sense of an ensemble of recognized objects; perform the cognitive functions normally associated with vision 11/1/2020 FURC-BCSE 7 35
Image Processing Steps 11/1/2020 FURC-BCSE 7 36
DIP Course § § Digital Image Fundamentals and Image Acquisition (briefly) Image Enhancement in Spatial Domain – Pixel operations – Histogram processing – Filtering § Image Enhancement in Frequency Domain – Transformation and reverse transformation – Frequency domain filters – Homomorphic filtering § Image Restoration – Noise reduction techniques – Geometric transformations 11/1/2020 FURC-BCSE 7 37
DIP Course § Color Image Processing – Color models – Pseudocolor image processing – Color transformations and color segmentation § Wavelets and Multi-Resolution Processing – Multi-resolution expansion – Wavelet transforms, etc. § Image Compression – Image compression models – Error free compression – Lossy compression, etc 11/1/2020 FURC-BCSE 7 38
DIP Course § Image Segmentation – Edge, point and boundary detection – Thresholding – Region based segmentation, etc 11/1/2020 FURC-BCSE 7 39
Image Representation • Image – Two-dimensional function f(x, y) – x, y : spatial coordinates • Value of f : Intensity or gray level 11/1/2020 FURC-BCSE 7 40
Digital Image • A set of pixels (picture elements, pels) • Pixel means – pixel coordinate – pixel value – or both • Both coordinates and value are discrete 11/1/2020 FURC-BCSE 7 41
Example • 640 x 480 8 -bit image 11/1/2020 FURC-BCSE 7 42
11/1/2020 FURC-BCSE 7 43
- Slides: 43