Pakistan Research Repository Home

Title of Thesis

Asmat Ullah
Institute/University/Department Details
Faculty of Computer Science and Engineering/ Ghulam Ishaq Khan Institute of Engineering Sciences and Technology
Computer Science
Number of Pages
Keywords (Extracted from title, table of contents and abstract of thesis)
image restoration, machine learning, kriging, gaussian noise, edge preservation, fuzzy logic, semivariograms, matrix inversion failure, negative weights, punctual kriging, , neuro-fuzzy filter, denoising, hybrid image restoration

Restoration of degraded images has become an important and effective tool for many technological applications like space imaging, medical imaging and many other post-processing techniques. Most of the image restoration techniques model the degradation phenomena, usually blur and noise, and then obtain an approximation of the image. Whereas, in realistic situation, one has to estimate both the true image and the blur from the degraded image characteristics in the absence of any prior information about the blurring system. The objective of this thesis is to develop a new punctual kriging based image restoration approach using machine-learning techniques. To achieve this objective, the research concentrates on the restoration of images corrupted with Gaussian noise by making good tradeoffs between two contradicting properties; smoothness versus edge preservation.

This thesis makes the following contributions: (1) Quantitative analysis of the at hand punctual kriging based image restoration technique is carried out, (2) Fuzzy logic, punctual kriging and fuzzy averaging are used intelligently to develop a better image restoration technique, (3) A new image quality measure is proposed in terms of the semi-variograms to judge the performance of image restoration techniques, (4) Analysis of the effect of neighbourhood size on negative weights and the subsequent improvement in punctual kriging based image restoration is performed, (5) To avoid both the problems of matrix inversion failure and the negative weights in punctual kriging, artificial neural network is used to develop a neuro-fuzzy filter for image denoising, (6) Further, using genetic programming, a hybrid technique for image restoration based on fuzzy punctual kriging is developed, the developed machine learning technique uses local statistical measures along with kriged information for subsequent pixel estimation. Main parameters considered for evaluation of the proposed technique are image quality measure and computational cost. The image quality measures used for evaluation and comparison include MSE, PSNR, SSIM, wPSNR, VMSE and VPSNR. A series of empirical investigations have been made to evaluate the performance of the proposed techniques using database of standard images that show the effectiveness of our methodology

Download Full Thesis
1323.91 KB
S. No. Chapter Title of the Chapters Page Size (KB)
1 0 Contents
129.55 KB
2 1 Introduction 1
45.56 KB
  1.1 Background And Motivations 1
  1.2 Research Perspective 2
  1.3 Contributions 3
  1.4 Thesis Layout 4
3 2 Literature Review
282.82 KB
  2.1 Digital Image Restoration 5
  2.2 Applications Of Geostatistical Techniques In Image Restoration 11
  2.3 Soft Computing Approaches 18
  2.4 Summary 26
4 3 Fuzzy Punctual Kriging Based Image Restoration
281.28 KB
  3.1 Introduction 27
  3.2 Fuzzy Inference System And Fuzzy Smoothing 30
  3.3 Image Quality Measures 31
  3.4 The New Approach 32
  3.5 Results And Discussion 35
  3.6 Conclusions 42
5 4 Effect Of Neighborhood Size On Kriging Weights
124.44 KB
  4.1 Introduction 43
  4.2 Results And Discussion 45
  4.3 Conclusions 50
6 5 Neuro-Fuzzy Kriging Filter For Image Restoration
209.39 KB
  5.1 Introduction 51
  5.2 The Proposed Hybrid Approach 53
  5.3 Results And Discussions 61
  5.4 Conclusions 66
7 6 Hybrid Image Restoration Approach 67
207.04 KB
  6.1 Introduction 67
  6.2 Fuzzy Logic 69
  6.3 Genetic Programming 69
  6.4 The Proposed Hybrid Image Restoration Approach 70
  6.5 Implementation Details 75
  6.6 Results And Discussion 76
  6.7 Conclusions 80
8 7 Conclusion 82
51.31 KB
  7.1 Contributions : Detail In Reference To Individual Chapter 82
  7.2 Recommendations For Future Work 84
9 8 Appendix 86
134.84 KB