Muhammad Rzi Abbas Department of Mechatronics and Control Engineering
muhammadrziabbas@uet.edu.pk Lecturer, Mechatronics Dept. University of Engineering and Technology, Lahore Histograms • The brightness histogram hf(z) of an image provides the frequency of the brightness value ‘z’ in the image • The histogram of an image with L gray-levels is represented by a one-dimensional array with L elements. Histograms • The histogram provides a natural bridge between images and a probabilistic description. • We might want to find a first-order probability function p(z; x,y) to indicate the probability that pixel (x,y) has brightness z. • Dependence on the position of the pixel is not of interest in the histogram • A density function Pi(z) is of interest and the brightness histogram is its estimate. Histograms Histograms • The histogram is usually the only global information about the image which is available. • It is used when finding optimal illumination conditions for capturing an image, gray-scale transformations, and image segmentation to objects and background. • Note that one histogram may correspond to several images; for instance, a change of the object position on a constant background does not affect the histogram. Histograms • Histogram Smoothing • Histograms of digital images may have several local minima and maxima which can complicate further processing and deteriorate visual results. • This problem can be addressed by using local smoothing according to the following equation
• K defines the size of the neighborhood
Visual Perception • Even though digital image is processed based on mathematical data, the output should take into the way the HVS perceives an image. • Humans relay on psycho-physical parameters for perceiving an image, which are: • Contrast • Border • Shape • Texture • Color etc. Visual Perception • Contrast • It is the local change in brightness and is defined as the ratio between average brightness of an object and the background • Apparent brightness depends very much on the brightness of the local surroundings; this effect is called conditional contrast Visual Perception • Acuity • It is the ability to detect details in an image. The human eye is less sensitive to slow and fast changes in brightness in the image plane but is more sensitive to intermediate changes. • Acuity also decreases with increasing distance from the optical axis. • Human vision has the best resolution for objects which are at a distance of about 250 mm from an eye under illumination of about 500 lux; this illumination is provided by a 60W bulb from a distance of 400 mm. Under these conditions the distance between two distinguishable points is approximately 0.16 mm Visual Perception • Some Visual Illusions Visual Perception • Perceptual Grouping Visual Perception • Perceptual Grouping • Perceived properties help people to connect elements together based on strongly perceived properties as parallelism, symmetry, continuity and closure taken in a loose sense Visual Perception • Image Quality • Subjective: Dependent on the views of several professional and lay viewers. • Objective: • A more standardized way. A comparison with a reference image is made. This comparison might take a form of mean quadratic difference, mean absolute difference or simply correlation. • Another measure might be the resolution of small or proximate objects in an image. • Such measures can also be used for subjective quality measurement and for parameter optimization. Visual Perception • Noise • Degradation • May come during image capture, transmission, or processing, and may be dependent on, or independent of, the image content • Noise is characterized by its probability characteristics • White Noise: Idealized noise having constant power spectrum • Gaussian Noise: This noise has probability density function given by a Gaussian curve. Gaussian noise is a very good approximation to noise that occurs in many practical cases. Visual Perception • Noise • Additive Noise • Multiplicative Noise • Quantization Noise • Impulse Noise Reading Assignment • Students are advised to reading the following topics on their own from the given text book • Colors Images • Cameras • Text Book • Image Processing, Analysis and Machine Vision by Milan Sonka, Vaclav Hlavac and Roger Boyle, 3rd Edition, 2008. • Chapter 2 (Sections 2.4 and 2.5) References • Image Processing, Analysis and Machine Vision by Milan Sonka, Vaclav Hlavac and Roger Boyle, 3rd Edition, 2008. • Chapter 2 (Section 2.3) • Machine Vision by David Vernon, Published in 1991 • Chapter 3 (Section 3.3 and 3.4)