Selected Topics in Computer Science Introduction to Digital Image ProcessingDigital Image Processing (DIP) + A digital image is a representation of a two-dimensional image as a finite set of digital values, called picture elements or pixels. A OD Imation every of a YN N _ Mi + ‘ a b [oe ims ene Lens NI image = Resolution (riera image plane ‘Scene elementDigital Image Processing (DIP) What is an image? * Image is used to capture objects from the real-environment * It is a 2-D object, which is stored as a specific arrangement of dots, or pixels. * To store an image, the image is represented in a 2-D matrix, in which each value corresponds to the data associated with one image pixel.Digital Image Processing (DIP) What is a digital image? * A digital image is an image f(x, y) that has been discretised both in spatial coordinates and in brightness. * It is represented by a 2D integer array, or a series of 2D arrays, one for each color band. The digitized brightness value is called grey level. * Each element of the array is called Pixel or pel, derived from the term “picture element”.Digital Image Processing (DIP) Why do we process images? Image processing has been developed in response to three major problems concerned with pictures: * Picture digitization and coding to facilitate transmission, printing and storage of pictures; * Picture enhancement and restoration in order, for example, to interpret more easily pictures of the surface of other plants taken by various probes; * Picture segmentation and description as an early stage to Machine Vision. Image processing nowadays refers mainly to the processing of digital images.Digital Image Processing (DIP) What is digital image processing? * The field of digital image processing refers to processing digital images by means of a digital computer. * DIP is a discipline in which both the input and output of a process are images. =) SE]Digital Image Processing (DIP) * Nowadays, image processing is among rapidly growing technologies. It forms core research area within computer engineering & science disciplines too. * The most common uses of DIP techniques include: improve image quality, remove noise etc. so as to facilitate extraction of image features for image analysis. + Examples: * Poorly exposed x-ray image: The result from contrast & edge enhancement * Image blurred by motion: The result of de-blurring * Finding the outline & shape of image objectsDigital Image Processing (DIP) Digital image processing focuses on two major tasks * Improvement of pictorial information for human interpretation * Processing of image data for storage, transmission and representation for autonomous machine perception Some argument about where image processing ends and fields such as image analysis and computer vision startApplications of Image Processing (example) * Signature verification is a technique used by banks, intelligence agencies and high-profile institutions to validate the identity of an individual. Signature verification is often used to compare signatures in bank offices and other branch capture.Applications of Image Processing (example) * Biometrics authentication is used in computer science as a form of identification and access control. * It is also used to identify individuals in groups that are under surveillance.Applications of Image Processing (example) * Fingerprint Verification / Identification Match |» Yes/No Match i OF TM Maen 79) 1:1 Match (y yy Named { (Distriouted} Biometries Biometrics Database DatebaseApplications of Image Processing (example) * Congestion of public road networks is a growing problem in many countries. * On motorways, on trunk roads or on urban roads, a permanent and real time traffic monitoring is often necessary. Not only for collecting data for statistics, but also for managing traffic in real time.Challenges of image processing There are a number of challenges in image processing. Some of these challenging problems include image enhancement or restoration, image recognition, image classification, and image visualization. + In image enhancement, it aims to process images to improve their quality. An image may be of poor quality because Its contrast is low, or it is noisy, or it is blurred, etc. Many algorithms have been devised to remove these degradations. The challenging problem is how to remove degradations without hurting the signal. +A recognition system needs to classify an unknown input pattern into one of a set of prespecified classes.Challenges of image processing... * Image classification is a big challenge doing image analysis tasks, especially the selection of methods and techniques in exploiting the result of image processing and pattern recognition, classification methods, subsequently validating the classification result into expert knowledge. * Image visualization is considered as a part of computer graphics. The main task is to generate images or image sequences based on three- dimensional object and scene models.Types of Digital Images *Grayscale image + Usually we use 256 levels for each pixel. That means, the numerical value for gray levels range from 0 (for black pixels) to FF (256) for white. Thus we need 8 bits to represent each pixel (28 = 256) + Gray scale ranges from black to grays and finally to white. Binary Image * Abinary image has only two values (0 or 1). Anumerical value may represent either a black (0) or a white (1) dot/pixel. * Binary image is quite important in image analysis and object detection applications. Image.Color Image * Characterization of light is central to the science of color. * There are different color models: RGB, YUV, YIQ, HSV, CMYK, etc. color model 24 bit imageRGB Color Model *To form a color with RGB, three separate color signals of one red, one green, & one blue must be mixed. Each of the three signals can have an arbitrary intensity, from fully off to fully on, in the mixture. *The RGB color model is an additive color mixing model using which every color can be encoded as a combination of red, green, & blue light. *Projection of primary color lights on a screen shows secondary colors where they overlap; for instance, the combination of all three of red, green, & blue in appropriate intensities makes white. B R G Magenta Blue white Back Yellow GreatRGB Color Model = The figure shows an RGB image, along with its separate R, G and B components. Note that, * strong red, green, and blue produces white color; + strong red and green with little blue gives brown; * strong green with little red or blue gives dark green; strong blue and moderately strong red and green provides light blue sky. = The number of bits used to represent each pixel in RGB space is called the pixel depth. * Consider an RGB image in which each of the red, green, and blue color is an 8-bit representation. Under these conditions each RGB color pixel have a depth of 24 bits. + Compute the total number of colors ina 24-bit RGB image ?RGB Color Model * The main purpose of the RGB color model is for display of images in electronic systems, such as televisions and computers. * Typical RGB input devices are color TV & video cameras, image scanners, and digital cameras. * Typical RGB output devices are TV sets of various technologies (CRT, LCD, plasma, etc.), computer and mobile video projectors, phone displays, etc. * Color printers, on the other hand, are usually not RGB devices, but subtractive color devices (typically CMYK color model).Representing an Image *To represent an image without noticeable deterioration, we would have to use a matrix of at least 640 x 480 pixels. «Is there any difference in space requirement by the grey-scale image vs. color image? * each pixel in grey-scale image is represented by an 8-bit integer. This image specification results in a matrix containing 307, 200 eight-bit numbers (or, a total of 2, 457, 600 bits or 307 KBs). Where as, color image requires 921 KBs.Classification of DIP The continuum from image processing to computer vision can be broken up into low-,mid- and high-level processes Image Processing pri Low-Level Process (inputs and outputs ; Mid-Level Process (outputs High-Level asks ee are attributes extracted Process operations, like from input images) + Making Sense + Binarization + Segmentation of an + Skew detection + Feature Extraction or Ensemble of + Image restoration description of objects Recognized + Image Enhancement — * “lassification or Objects recognition of objectsClassification of DIP... * 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: (Image analysis) + Inputs are images, Outputs are attributes extracted from those images (edges, contours, identity of individual objects * major functions: + Segmentation (partitioning an image into regions or objects) + Description of those objects to reduce them to a form suitable for computer processing * Classifications (recognition) of objects * High-level process (Computer Vision) “make sense of an ensemble of recognized objects; perform the cognitive functions normally associated with visionImage analysis * Image processing is often used to prepare images prior to analysis. * Image analysis is a process by which meaningful information or measurements can be extracted from digital images, typically by computer algorithms. * Image analysis is a computer-based process of extracting quantitative information from images. The process begins with the input of an image and ends with the output of numerical data * Image analysis tasks can be as simple as reading bar coded tags or as sophisticated as identifying a person from their faceImage analysis... * Computer vision is the science and technology of machines that see. * Concerned with the theory for building artificial systems that obtain information from images. * The image data can take many forms, such as a video sequence, depth images, views from multiple cameras, or multi-dimensional data from a medical scanner Health Security Access SafetyImage Processing vs. Image analysis Low Level Image Processing Acquisition, representation, compression, transmission image enhancement Feature extraction Pattern matching image “understanding” Computer Vision (Recognition) High LevelReferences >T. S. Huang and K. Aizawa, “Image processing: Some challenging problems,” in Proceedings of the National Academy of Sciences of the United States of America, 1993, vol. 90, no. 21, pp. 9766-9769. >E. Miranda, M. Aryuni, and E. Irwansyah, “A survey of medical image classification techniques,” Proc. 2016 Int. Conf. Inf. Manag. Technol. ICIMTech 2016, November, pp. 56-61, 2017. »R. C. Gonzalez and R. E. Woods, Digital Image Processing, 3rd ed., no. September. Upper Saddle River, New Jersey: Pearson Education, Inc, 2015. Gerabirhan Paulos ‘[email protected]