July 2011 Master of Computer Application (MCA) Semester 6 MC0086 Digital Image Processing 4 Credits

(Book ID: B1007)

Assignment Set 1 (60 Marks)

Answer all Questions Each Question carries fifteen Marks

1. Discuss the following with respect to Digital Image Processing: a. Origins of Digital Image Processing b. Examples of Fields that use Digital Image Processing c. Components of an Image Processing System . A

Processing of digital image involves the following steps to be carried out in a sequence: Image acquisition, Image enhancement, Image restoration, Color image processing, Wavelets and Multiresolution processing, Compression, Morphological processing, Segmentation, Representation with description and finally Object recognition. Image acquisition is the first process. To do so requires an imaging sensor and the capability to digitize the signal produced by the sensor. The sensor could be a monochrome or a color TV camera that produces an entire image of the problem domain every 1/30 seconds. The imaging sensor could also be a line-scan camera that produces a single image line at a time. If the output of the camera or other imaging sensor is not already in digital form, an analog-to-digital converter digitizes it. Note that acquisition could be as being given an image that is already in digital form. Generally, the image acquisition stage involves preprocessing, such as scaling.
B

Image enhancement is one of the simplest and most appealing areas of digital image processing. Basically, the idea behind enhancement techniques is to bring out detail that is obscured, or simply to highlight certain features of interest in an image. A familiar example of enhancement is when we increase the contrast of an image because it looks better. It is important to keep in mind that enhancement is a very subjective area of image processing. Image restoration is an area that also deals with improving the appearance of an image. However, unlike enhancement, which is subjective, image restoration is objective, in the sense that restoration techniques tend to be based on mathematical or probabilistic models of image degradation. Color image processing is an area that has been gaining in

importance because of the significant increase in the use of digital images on the Internet. Color is used as the basis for extracting features of interest in an image. Wavelets are the foundation for representing images in various degrees of resolution. In particular, this is used for image data compression and for pyramidal representation, in which images are subdivided successively into smaller regions.
C

Mass storage capability is a must in image processing applications. An image of size 1024X1024 pixels, in which the intensity of each pixel is an 8-bit quantity, requires one megabyte of storage space if the image is not compressed. When dealing with thousands, or even millions, of images, providing adequate storage in an image processing system can be a challenge. Digital storage for image processing applications falls into three principal categories: (1) short-term storage for use during processing. (2) On-line storage for relatively fast re-call, and (3) archival storage, characterized by infrequent access. Storage is measured in bytes (eight bits), Kbytes (one thousand bytes), Mbytes (one million bytes), Gbytes (meaning giga, or one billion, bytes), and Tbytes (meaning tera, or one trillion, bytes). Image displays in use today are mainly color (preferably flat screen) TV monitors. Monitors are driven by the outputs of image and graphics display cards that are an integral part of the computer system. Seldom are there requirements for image display applications that cannot be met by display cards available commercially as part of the computer system. In some cases, it is necessary to have stereo displays, and these are implemented in the form of headgear containing two small displays embedded in goggles worn by the user. Hardcopy devices for recording images include laser printers, film camera, heat-sensitive devices, inkjet units, and digital units, such as optical and CD-ROM disks. Film provides the highest possible resolution, but paper is the obvious medium of choice for written material. For presentations, images are displayed on film transparencies or in a digital medium if image projection equipment is used. The latter approach is gaining acceptance as the standard for image presentations. Networking is almost a default function in any computer system in use today. Because of the large amount of data inherent in image processing applications, the key consideration in image transmission is bandwidth. In dedicated networks, this typically is not a problem, but communications with remote sites via the Internet are not always as efficient. Fortunately, this situation is improving quickly as a result of optical fiber and other broadband technologies.

2. Explain the following terms. A) Adjacency B) Connectivity C) Regions and Boundaries

Specifically, the adjacency matrix of a finite graph G on n vertices is the n n matrix where the non-diagonal entry aij is the number of edges from vertex i to vertex j, and the diagonal entry aii, depending on the convention, is either once or twice the number of edges (loops) from vertex i to itself. Undirected graphs often use the latter convention of counting loops twice, whereas directed graphs typically use the former convention. There exists a unique adjacency matrix for each isomorphism class of graphs (up to permuting rows and columns), and it is not the adjacency matrix of any other isomorphism class of graphs. In the special case of a finite simple graph, the adjacency matrix is a (0,1)-matrix with zeros on its diagonal. If the graph is undirected, the adjacency matrix is symmetric. The relationship between a graph and the eigenvalues and eigenvectors of its adjacency matrix is studied in spectral graph theory.
3. Describe the following with respect to Image Segmentation: a. Detection of Discontinuities b. Edge Linking and Boundary Detection

The purpose of detecting sharp changes in image brightness is to capture important events and changes in properties of the world. It can be shown that under rather general assumptions for an image formation model, discontinuities in image brightness are likely to correspond to[1][2]:

discontinuities in depth, discontinuities in surface orientation, changes in material properties and variations in scene illumination.

In the ideal case, the result of applying an edge detector to an image may lead to a set of connected curves that indicate the boundaries of objects, the boundaries of surface markings as well as curves that correspond to discontinuities in surface orientation. Thus, applying an edge detection algorithm to an image may significantly reduce the amount of data to be processed

and may therefore filter out information that may be regarded as less relevant, while preserving the important structural properties of an image. If the edge detection step is successful, the subsequent task of interpreting the information contents in the original image may therefore be substantially simplified. However, it is not always possible to obtain such ideal edges from real life images of moderate complexity. Edges extracted from non-trivial images are often hampered by fragmentation, meaning that the edge curves are not connected, missing edge segments as well as false edges not corresponding to interesting phenomena in the image thus complicating the subsequent task of interpreting the image data.[3] Edge detection is one of the fundamental steps in image processing, image analysis, image pattern recognition, and computer vision techniques. During recent years, however, substantial (and successful) research has also been made on computer vision methods[which?] that do not explicitly rely on edge detection as a pre-processing step.
b)

Rosenfeld and Troy have proposed a measure of the number of edges in a neighborhood as a textural measure. As a first step in their process, an edge map array E(j, k) is produced by some edge detector such that E(j, k) = 1 for a detected edge and E(j, k) = 0 otherwise. Usually, the detection threshold is set lower than the normal setting for the isolation of boundary points. This texture measure is defined as

Where W = 2w + 1 is the dimension of the observation window. A variation of this approach is to substitute the edge gradient G(j, k) for the edge map array in Eq.6.
4. Describe the following with respect to Image Feature Extraction: a. Image Feature Evaluation b. Amplitude Features c. Transform Coefficient Features d. Texture Definition e. Visual Texture Discrimination

a) This paper is concerned with feature evaluation for content-based image retrieval. Here we concentrate our attention on the evaluation of image features amongst

three alternatives, namely the Harris corners, the maximally stable extremal regions and the scale invariant feature transform. To evaluate these image features in a content-based image retrieval setting, we have used the KD-tree algorithm. We use the KD-tree algorithm to match those features corresponding to the query image with those recovered from the images in the data set under study. With the matches at hand, we use a nearest neighbour approach to threshold the Euclidean distances between pairs of corresponding features. In this way, the retrieval is such that those features whose pairwise distances are small, 'vote' for a retrieval candidate in the data-set. This voting scheme allows us to arrange the images in the data set in order of relevance and permits the recovery of measures of performance for each of the three alternatives. In our experiments, we focus in the evaluation of the effects of scaling and rotation in the retrieval performance. b) Image segmentation decisions are typically based on some measure of image amplitude in terms of luminance, color value, spectral value, or other units. The amplitude values may be used directly or may result from some transformation of the original pixel values. In this section we describe amplitude features that result from measurements over a neighborhood of pixels. For example, the average or mean amplitude in a 2 M+12 M+1 neighborhood centered on (x,y) is given by where . Other commonly used amplitude features include range, variance, median, energy, and entropy. c) Discrete wavelet transform has become a widely used feature extraction tool in pattern recognition and pattern classification applications. However, using all wavelet coefficients as features is not desirable in most applications -- the enormity of data and irrelevant wavelet coefficients may adversely affect the performance. Therefore, this paper presents a novel feature extraction method based on discrete wavelet transform. In this method, Shannon's entropy measure is used for identifying competent wavelet coefficients. The features are formed by

calculating the energy of coefficients clustered around the competent clusters. The method is applied to the lung sound classification problem. The experimental results show that the new method performs better than a well-known feature extraction method that is known to give the best results for lung sound classification problem.

d)
The visual and especially tactile quality of a surface: rough texture. the characteristic structure of the interwoven or intertwined threads, strands, or the like, that make up a textile fabric: coarse texture. the characteristic physical structure given to a material, an object, etc., by the size, shape, arrangement, and proportions of its parts: soil of a sandy texture; a cake with a heavy texture. an essential or characteristic quality; essence.

Master of Computer Application (MCA) Semester 6 MC0086 Digital Image Processing 4 Credits
(Book ID: B1007)

Assignment Set 2 (60 Marks)

Answer all Questions Each Question carries fifteen Marks 1. Describe the following features of Image Extraction: A) Image Feature Evaluation B) Amplitude Features C) Transform Coefficient Features

a. In this paper, we evaluate various image features and different search strategies for fitting Active Shape Models (ASM) to bone object boundaries in digitized radiographs. The original ASM method iteratively refines the pose and shape parameters of the point distribution model driving the ASM by a least squares fit of the shape to update the target points at the estimated object boundary position, as determined by a suitable object boundary criterion. We propose an improved search procedure that is more robust against outlier configurations in the boundary target points by requiring subsequent shape changes to be smooth, which is imposed by a smoothness constraint on the displacement of neighbouring target points at each iteration and implemented by a minimal cost path approach. We compare the original ASM search method and our improved search algorithm with a third method that does not rely on iteratively refined target point positions, but instead optimizes a global Bayesian objective function derived from statistical a priori contour shape and image models. Extensive validation of these methods on a database containing more than 400 images of the femur, humerus and calcaneus using the manual expert segmentation as ground truth shows that our minimal cost path method is the most robust. We also evaluate various measures for capturing local image appearance around each boundary point and conclude that the Mahalanobis distance applied to normalized image intensity profiles extracted normal to the shape is the most suitable criterion among the tested ones for guiding the ASM optimization.
b)

Image segmentation decisions are typically based on some measure of image amplitude in terms of luminance, color value, spectral value, or other units. The amplitude values may be used directly or may result from some transformation of the original pixel values. In this

section we describe amplitude features that result from measurements over a neighborhood of pixels. For example, the average or mean amplitude in a 2 M+12 M+1 neighborhood centered on (x,y) is given by where . Other commonly used amplitude features include range, variance, median, energy, and entropy.
c)

Discrete wavelet transform has become a widely used feature extraction tool in pattern recognition and pattern classification applications. However, using all wavelet coefficients as features is not desirable in most applications -- the enormity of data and irrelevant wavelet coefficients may adversely affect the performance. Therefore, this paper presents a novel feature extraction method based on discrete wavelet transform. In this method, Shannon's entropy measure is used for identifying competent wavelet coefficients. The features are formed by calculating the energy of coefficients clustered around the competent clusters. The method is applied to the lung sound classification problem. The experimental results show that the new method performs better than a well-known feature extraction method that is known to give the best results for lung sound classification problem.

2. Describe the following with respect to Image Enhancement: a. Contrast Manipulation b. Histogram Modification c. Noise Cleaning a. While being in flight, I had to learn new features, introduced in .NET 3.5 SP1. So, lets start

from image manipulation. I want to perform contrast and brightness manipulation in GPU over displayed image. In order to begin, you should download and install .NET 3.5 SP1 and Visual Studio 2008 SP1. Meanwhile (its about 500 MB of download) well learn how to write custom shader effect. b)

Many image processing operations result in changes to the image's histogram. The class of histogram modifications which we consider here include operations where the changes to pixel levels are computed so as to change the histogram in a particular way.

Histogram Stretching
The simplest form of histogram modification is histogram stretching. For example, if the image is under-exposed its values would only occupy the lower part of the dynamic range. You can perform the histogram stretching for an 8-bit image using:
ImageStats/Q imageWave Variable normalization=255/(V_max-V_min) ImageWave=normalization*(ImageWave-V_min)

The normalization variable makes the subsequent operation a bit more efficient. The following images illustrate histogram stretching. In each case the image is shown on the left and the corresponding luminance histogram is shown on the right. Below the image we show the histograms of the RGB components.
c)

While there are dozens of different kinds of noise reduction, the first widely used audio noise reduction technique was developed by Ray Dolby in 1966. Intended for professional use, Dolby Type A was an encode/decode system in which the amplitude of frequencies in four bands was increased during recording (encoding), then decreased proportionately during playback (decoding). The Dolby B system (developed in conjunction with Henry Kloss) was a single band system designed for consumer products. In particular, when recording quiet parts of an audio signal, the frequencies above 1 kHz would be boosted. This had the effect of increasing the signal to noise ratio on tape up to 10dB depending on the initial signal volume. When it was played back, the decoder reversed the process, in effect reducing the noise level by up to 10dB. The Dolby B system, while not as effective as Dolby A, had the advantage of remaining listenable on playback systems without a decoder. Dbx was the competing analog noise reduction system developed by dbx laboratories. It used a root-mean-squared (RMS) encode/decode algorithm with the noise-prone high frequencies boosted, and the entire signal fed through a 2:1 compander. Dbx operated across the entire audible bandwidth and unlike Dolby B was unusable as an open ended system. However it could achieve up to 30 dB of noise reduction. Since Analog video recordings use frequency

modulation for the luminance part (composite video signal in direct colour systems), which keeps the tape at saturation level, audio style noise reduction is unnecessary.

Dynamic Noise Reduction

Dynamic Noise Reduction (DNR) is an audio noise reduction system, introduced by National Semiconductor to reduce noise levels on long-distance telephony.[1] First sold in 1981, DNR is frequently confused with the far more common Dolby noise reduction system.[2] However, unlike Dolby and dbx Type I & Type II noise reduction systems, DNR is a playback-only signal processing system that does not require the source material to first be encoded, and it can be used together with other forms of noise reduction.[3] It was a development of the unpatented Philips Dynamic Noise Limiter (DNL) system, introduced in 1971, with the circuitry on a single chip.[4][5]
3. Describe the following with respect to Image Segmentation: A) Detection of Discontinuities B) Edge Linking and Boundary Detection

a) A Detection Algorithm for the localisation of unknown fault lines of a surface from scattered data is given. The method is based on a local approximation scheme using thin plate splines, and we show that this yields approximation of second order accuracy instead of first order as in the global case. Furthermore, the Detection Algorithm works with triangulation methods, and we show their utility for the approximation of the fault lines. The output of our method provides polygonal curves which can be used for the purpose of constrained surface approximation. 1 Introduction Feature recognition has become an attractive field for research especially within industrial applications. A feature of a surface f : R 2 ! R typically reflects characteristic properties of f , such as discontinuities across planar curves. In geophysical sciences these discontinuities are referred to as fault lines [1], [20], [9]. The motivation for this work is given by applications from oil industry where method...

b) Edge detectors yield pixels in an image lie on edges. The next step is to try to collect these pixels together into a set of edges. Thus, our aim is to replace many points on edges with a few edges themselves. The practical problem may be much more difficult than the idealised case.

Small pieces of edges may be missing, Small edge segments may appear to be present due to noise where there is no real edge, etc.

In general, edge linking methods can be classified into two categories: Local Edge Linkers -- where edge points are grouped to form edges by considering each point's relationship to any neighbouring edge points. Global Edge Linkers -- where all edge points in the image plane are considered at the same time and sets of edge points are sought according to some similarity constraint, such as points which share the same edge equation.

4. Describe the following with respect to Edge Detection: a. First-Order Derivative Edge Detection b. Second-Order Derivative Edge Detection c. Edge-Fitting Edge Detection d. Luminance Edge Detector Performance a. Edge detection is a fundamental tool in image processing and computer vision, particularly

in the areas of feature detection and feature extraction, which aim at identifying points in a digital image at which the image brightness changes sharply or, more formally, has discontinuities. The same problem of finding discontinuities in 1D signals is known as step detection.

The purpose of detecting sharp changes in image brightness is to capture important events and changes in properties of the world. It can be shown that under rather general assumptions for an image formation model, discontinuities in image brightness are likely to correspond to[1][2]:

discontinuities in depth, discontinuities in surface orientation, changes in material properties and variations in scene illumination.

In the ideal case, the result of applying an edge detector to an image may lead to a set of connected curves that indicate the boundaries of objects, the boundaries of surface markings as well as curves that correspond to discontinuities in surface orientation. Thus, applying an edge detection algorithm to an image may significantly reduce the amount of data to be processed and may therefore filter out information that may be regarded as less relevant, while preserving the important structural properties of an image. If the edge detection step is successful, the subsequent task of interpreting the information contents in the original image may therefore be substantially simplified. However, it is not always possible to obtain such ideal edges from real life images of moderate complexity. Edges extracted from non-trivial images are often hampered by fragmentation, meaning that the edge curves are not connected, missing edge segments as well as false edges not corresponding to interesting phenomena in the image thus complicating the subsequent task of interpreting the image data.[3]
b)

John Canny considered the mathematical problem of deriving an optimal smoothing filter given the criteria of detection, localization and minimizing multiple responses to a single edge.[7] He showed that the optimal filter given these assumptions is a sum of four exponential terms. He also showed that this filter can be well approximated by first-order derivatives of Gaussians. Canny also introduced the notion of non-maximum suppression, which means that given the presmoothing filters, edge points are defined as points where the gradient magnitude assumes a local maximum in the gradient direction. Looking for the zero crossing of the 2nd derivative along the gradient direction was first proposed by Haralick .[8] It took less than two decades to find a modern geometric variational meaning for that operator that links it to the MarrHildreth (zero crossing of the Laplacian) edge detector. That observation was presented by Ron Kimmel and Alfred Bruckstein.[9] Although his work was done in the early days of computer vision, the Canny edge detector (including its variations) is still a state-of-the-art edge detector.[10] Unless the preconditions are particularly suitable, it is hard to find an edge detector that performs significantly better than the Canny edge detector.

The Canny-Deriche detector was derived from similar mathematical criteria as the Canny edge detector, although starting from a discrete viewpoint and then leading to a set of recursive filters for image smoothing instead of exponential filters or Gaussian filters.[11] The differential edge detector described below can be seen as a reformulation of Canny's method from the viewpoint of differential invariants computed from a scale-space representation leading to a number of advantages in terms of both theoretical analysis and subpixel implementation.
c)

The detection and tracing of edges of varying diffusion is a problem of importance in image analysis. In particular, it is of interest for the segmentation of meteorological and physiological pictures where the boundaries of objects are possibly not well defined or are obscured to a varying extent by noise. We present an edge detection and line fitting procedure which ascribes a direction, a measure of gradient, and quality of fit to the edge within a square segment of a controlled size or ``scope.'' To detect and fit edges to diffuse objects the scope is adaptively altered based on the confidence of fit to permit tracing of the object's boundary. We discuss predictor-corrector procedures for performing this edge tracing where predicted and calculated lines and confidences are used to generate a better fitting line. The performance of the procedures is demonstrated using both synthetic and satellite meteorological images. d) It seems clear, both from biological and computational evidence, that some form of data compression occurs at a very early stage in image processing. Moreover, there is much physiological evidence suggesting that one form of this compression involves finding edges and other information-high features in images. Edges often occur at points where there is a large variation in the luminance values in an image, and consequently they often indicate the edges, or occluding boundaries, of the objects in a scene. However, large luminance changes can also correspond to surface markings on objects. Points of tangent discontinuity in the luminance signal (rather than simple discontinuity) can also signal an object boundary in the scene. So the first problem encountered with modeling this biological process is that of defining, precisely, what an edge might be. The usual approach is to simply define edges as step discontinuities in the image signal. The method of localising these discontinuities often then becomes one of finding local maxima in the derivative of the signal, or zero-crossings in the

second derivative of the signal. This idea was first suggested to the AI community, both biologically and computationally, by Marr [5], and later developed by Marr and Hildreth [6], Canny [1,2], and many others [3,4]. In computer vision, edge detection is traditionally implemented by convolving the signal with some form of linear filter, usually a filter that approximates a first or second derivative operator. An odd symmetric filter will approximate a first derivative, and peaks in the convolution output will correspond to edges (luminance discontinuities) in the image. An even symmetric filter will approximate a second derivative operator. Zero-crossings in the output of convolution with an even symmetric filter will correspond to edges; maxima in the output of this operator will correspond to tangent discontinuities, often referred to as bars, or lines.