Image Processing Introduction PDF

Image Processing “Introduction” Imaging Systems, Applications, Representations, and Tools Lecturer: Dr. Taban Fouad Majeed E-mail : [email protected] 4th Stage CS 2024-2025  Introduction An Image is Worth mo...

Image Processing “Introduction” Imaging Systems, Applications, Representations, and Tools Lecturer: Dr. Taban Fouad Majeed E-mail : [email protected] 4th Stage CS 2024-2025  Introduction An Image is Worth more than a Thousand Words!!! Dr. Taban F. Majeed 1  What is a Digital Image? A digital image is a representation of a two- dimensional image as a finite set of digital values, called picture elements or pixels. Dr. Taban F. Majeed 2  What is a Digital Image? (cont.) Pixel values typically represent gray levels, colours. Remember digitization implies that a digital image approximates a real scene. 1 pixel Dr. Taban F. Majeed 3  What is a Digital Image? (cont.) Common image formats include: – 1 sample per point (B&W or Grayscale) – 3 samples per point (Red, Green, and Blue) – 4 samples per point (Red, Green, Blue, and “Alpha”) Dr. Taban F. Majeed 4  What is DIP? (cont.) The continuum from image processing to computer vision can be broken up into low-, mid- and high- level processes. Low Level Process Mid Level Process High Level Process Input: Image Input: Image Input: Attributes Output: Image Output: Attributes Output: Understanding Examples: Noise Examples: Object Examples: Scene removal, image recognition, understanding. sharpening segmentation Dr. Taban F. Majeed 5  History of Digital Image Processing One of the first applications of digital images was in the newspaper industry. Pictures were sent by submarine cable between London and New York. Introduction of the Bartlane cable picture transmission system in the early 1920s. – Reduced the time required to transport a picture across the atlantic from more than a week to less than three hours. – Specialised printing equipment were used to code pictures for cable transmission. – Pictures were reconstructed at the receiving end. Dr. Taban F. Majeed 6  Digital picture produced in 1921 from coded tape by a telegraph printer Dr. Taban F. Majeed 7  Early 15 Tone Digital Image Dr. Taban F. Majeed 8  History of DIP (cont.) - 1960s: Improvements in computing technology and the onset of the space race led to a surge of work in digital image processing. - 1964: Computers used to improve the quality of the images of the moon taken by the Ranger 7 probe. - Such techniques were used in other space missions including the Apollo landings. Dr. Taban F. Majeed 9  A picture of the moon taken by the Ranger 7 probe minutes before landing Dr. Taban F. Majeed 10  History of DIP (cont.) - 1970s: Digital image processing begins to be used in medical applications. – 1979: Sir Godfrey N. Hounsfield & Prof. Allan M. Cormack share the Nobel Prize in medicine for the invention of tomography, the technology behind Computerised Axial Tomography (CAT) scans. Dr. Taban F. Majeed 11 Typical head slice CAT image 12  History of DIP (cont.) 1980s - Today: The use of digital image processing techniques has exploded, and they are now used for all kinds of tasks in all kinds of areas – Image enhancement/restoration – Artistic effects – Medical visualisation – Industrial inspection – Law enforcement – Human computer interfaces Dr. Taban F. Majeed 13  Examples: Image Enhancement One of the most common uses of DIP techniques: improve quality, remove noise etc Dr. Taban F. Majeed 14  Examples: The Hubble Telescope Launched in 1990 the Hubble telescope can take images of very distant objects However, an incorrect mirror made many of Hubble’s images useless Image processing techniques were used to fix this Dr. Taban F. Majeed 15  Examples: Medicine Take slice from MRI scan of heart, and find boundaries between types of tissue – Image with gray levels representing tissue density – Use a suitable filter to highlight edges Original MRI Image of a Dog Heart Edge Detection Image Dr. Taban F. Majeed 16  Telemedicine: The use of computing and communication technology to avail/transfer medical data (e.g. images) over a phone/PDA or the Internet for: – video-conferencing for real-time consultation between medical specialists in different countries. – Remote medical examinations or medical procedures (Telesurgery). Tiny cameras that fit inside a pill and can be swallowed by patients to search for warning signs of internal illness such as cancer. – Such a devise is used as an alternative to traditional endoscopes – Takes high-quality, colour pictures in confined spaces – Traditional endoscopes capture images using a long, flexible cord about nine millimetres wide. – The cord is so wide; patients must be sedated during the scan. Dr. Taban F. Majeed 17  Biological image analysis Dr. Taban F. Majeed Chest X-ray Head CT 18  Examples: GIS Geographic Information Systems – Digital image processing techniques are used extensively to manipulate satellite imagery. Dr. Taban F. Majeed 19  Examples: Law Enforcement Image processing techniques are used extensively by law enforcers – Number plate recognition for speed cameras/automated toll systems – Fingerprint recognition – Enhancement of CCTV images Dr. Taban F. Majeed 20  Examples: HCI Try to make human computer interfaces more natural – Face recognition – Gesture recognition Dr. Taban F. Majeed 21  The Visible Light Visible Light (VL) is a narrow subspectrum of the EM spectrum. The wavelength of VL range ranges from 400 nanometer (nm) to 700 nm. Dr. Taban F. Majeed 22  Colours of visible light When White (Sun) light passes through a “prism” it is analysied into the colors of the rainbow. No color ends abruptly, but blends smoothly into the next color section. Objects reflecting no light are black, but objects reflecting light that is balanced in all visible wavelength (400 - 700nm) are white. Objects/material that favor reflectance in a limited range of the visible wavelength exhibits some shades of color. Dr. Taban F. Majeed 23  Aditivity of light colour Light reflected on an object and detected by a sensor is an additive (linear) combination of different wavelengths (i.e. Colours). Red, Green, and Blue are the primary colors. Other colors are a linear combination of R, G and B. i.e light color space is 3 dimentional with {R, G, B} as its base and every other colour can be expressed as: a*R +b*G + c*B where 0  a, b, c  1 and a + b + c = 1. RGB perfectly interprets human vision system Dr. Taban F. Majeed 25  Colour Space and transforms Images can be viewed in any single colour or in a multi- colour system. Color models other than the RGB are useful for specific applications. There are mathematical linear formulae to transform images from one colour system to another. Dr. Taban F. Majeed 26  Example Colour image Red chennel Green chennel Blue chennel Grey-scale Dr. Taban F. Majeed 27  Example RGB Red Green Blue Grayscale Dr. Taban F. Majeed 28  What is digital image processing An image can be defined as a 2D function, f (x; y), where – x and y are spatial (plane) coordinates – amplitude of f at any coordinates (x,y) is called the intensity or grey-level of the image at that point When x, y and the intensity values of f are finite, discrete quantitiess, the image is a digital image Digital image processing refers to processing digital images by means of a digital computer Dr. Taban F. Majeed 29  Digitising an image To convert the continuous function f(x,y) to digital form we need to sample the continuous sensed data in both coordinates and in amplitude using finite and discrete sets of values. – Digitizing the coordinate values is called sampling. – Digitizing the amplitude values is called quantisation. The number of selected values in the sampling process is known as the image spatial resolution. This is simply the number of pixels relative to the given image area The number of selected values in the quantisation process is called the grey-level (colour level) resolution. This is expressed in terms of the number of bits allocated to the colour levels. The quality of a digitised image depends the resolution parameters on both processes. Dr. Taban F. Majeed 30  A monochrome digital image is a 2-dimensional light intensity function f (x,y) whose independent variables (x,y) are digitised through spatial sampling, and whose intensity values are quantised by a finite uniformly spread grey-levels. Therefore, an image f is defined as a 2-dimentional array: f(1,1) f(1,2) f(1,3) … f(1,n) f(2,1) f(2,2) f(2,3) … f(2,n) f= f(3,1) f(3,2) f(3,3) … f(3,n) : : : : : : : : : : f(m,1) f(m,2) f(m,3) … f(m,n) Dr. Taban F. Majeed 31  Usually, m=n and the number of graylevels are g=2k for some k. The spatial resolution is mn and g is the greylevel resolution. RGB based colour images are represented similarly except that f(i,j) is a 3D vector representing intensity of the three primary colors at the (i,j) pixel posiotion. Dr. Taban F. Majeed 32  Key Stages in Digital Image Processing Image Morphological Restoration Processing Image Segmentation Enhancement Image Object Acquisition Recognition Representation Problem Domain & Description Colour Image Image Processing Compression Dr. Taban F. Majeed 33