Development of New Image Fusion Techniques / (Record no. 217579)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 04127 a2200193 4500 |
| 003 - CONTROL NUMBER IDENTIFIER | |
| control field | Nust |
| 005 - DATE AND TIME OF LATEST TRANSACTION | |
| control field | 20260206190537.0 |
| 040 ## - CATALOGING SOURCE | |
| Transcribing agency | Nust |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 621.382,AHM |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Ahmad, Attiq |
| 9 (RLIN) | 35417 |
| 245 ## - TITLE STATEMENT | |
| Title | Development of New Image Fusion Techniques / |
| Statement of responsibility, etc. | Attiq Ahmad |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Place of publication, distribution, etc. | Rawalpindi, |
| Name of publisher, distributor, etc. | MCS (NUST), |
| Date of publication, distribution, etc. | 2016 |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | xix, 100 p |
| 505 ## - FORMATTED CONTENTS NOTE | |
| Formatted contents note | Image fusion techniques merge the complementary information of several images<br/>(multi-focus, multi-exposure and multi-modal). Each of these scenarios poses different<br/>challenges for image fusion techniques, which are being extensively researched.<br/>However, most of these works assume that source images are preregistered, which is a<br/>less practical scenario. Both registered and unregistered image fusion algorithms are<br/>considered in this thesis. The registration involves the geometrical / spatial alignment<br/>of source images taken using different sensors or a sensor in different operating conditions.<br/>This research is concerned with the reliable fusion schemes of several scenario<br/>images (including muti-focus, Infra Red (IR) and visible, Computed Tomography (CT)<br/>and Magnetic Resonance (MR), and multi-exposure images) demonstrating high quality<br/>fused results without loss of useful information.<br/>The first scheme is a textural registration based multi-focus scheme involving the<br/>Gabor filtering (with specific frequency and orientation) for extracting texture features<br/>from the images. The filtered images are aligned/registered using affine transformation.<br/>Noise and blur play an important role in image fusion and need to be classified and<br/>treated for quality image fusion. The next two fusion schemes deal with multi-exposure<br/>noisy (real and synthetic both) and blur images. In the first algorithm, the noisy, blurry<br/>and clean images are classified using Laplacian filter and histogram spread. The noise<br/>is reduced in the frequency domain. Heavy weights are assigned to noise free pixels and<br/>the blur images are passed through the Wiener filter. In the second algorithm, a noise<br/>resistant image fusion scheme for multi-exposure sensors using color dissimilarity (for<br/>motion detection and removal), median and noise maps is proposed. A well exposed<br/>image is obtained as a result of weighted average of multi-exposure source images.<br/>Higher valued weights are assigned to pixels containing low values of noises, high<br/>values of color dissimilarity and median maps.<br/>The next work (two schemes) involve pre-registered visible and IR images. In the<br/>first one, a three stage image fusion scheme using Genetic Algorithm (GA) is presented.<br/>In the first stage, it segments the image into homogeneous regions and generates<br/>segmentation maps. In the second stage, the segmentation maps are combined<br/>by an adaptive weight adjustment procedure. The third stage fuses the input images<br/>and segmentation maps via GA based multi- objective optimization strategy. The second<br/>image fusion scheme uses Un-Decimated Dual Tree Complex Wavelet Transform<br/>(UDTCWT) for astronomical images. The UDTCWT reduces noise effects and improves<br/>object classification due to its inherited shift invariance property. Local standard<br/>deviation and distance transforms are used to extract useful information, especially<br/>small objects.<br/>In the medical (CT and MR) image fusion scheme, the source images are contrast<br/>enhanced using histogram equalization. It is a sparse decomposition based fusion technique<br/>that uses the dictionary learnt from input images and k-mean singular value decomposition<br/>algorithm. The scheme splits CT and MR images into texture and gradient<br/>images. The texture decomposition improves the overall performance of the sparse representation<br/>based fusion.<br/>The quantitative analysis performed using mutual information, structural similarity<br/>measure and edge dependent based performance metrics, yields improved results for<br/>proposed schemes, as compared to existing schemes. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | PhD Electrical Engineering Thesis |
| 9 (RLIN) | 133107 |
| 651 ## - SUBJECT ADDED ENTRY--GEOGRAPHIC NAME | |
| Geographic subdivision | PhD EE Thesis |
| 9 (RLIN) | 133108 |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Supervised by Dr. Tahir Zaidi |
| 9 (RLIN) | 133114 |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Koha item type | Thesis |
| Source of classification or shelving scheme | |
| Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Permanent Location | Current Location | Shelving location | Date acquired | Full call number | Barcode | Date last seen | Price effective from | Koha item type | Public note |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Military College of Signals (MCS) | Military College of Signals (MCS) | General Stacks | 12/12/2016 | 621.382,AHM | MCSPhD EE-07 | 12/08/2016 | 12/12/2016 | Thesis | Almirah No.68, Shelf No.6 |