Yalamati , Susmitha (2018) Image Registration Using SIFT Algorithm. MTech thesis.
Restricted to Repository staff only
Image Registration is an important step in the real time environment and it is the process of combining or overlaying two or more images taken from different sensors, different viewpoints or the different times. Image registration is mostly used in remote sensing ,image fusion, weather forecasting, image mosaicking ,computer tomography(CT),cartography etc. Image registration has been classified into two groups (1).Intensity based methods (2). Feature based methods. Intensity based methods are also called as the Area based methods .In intensity based methods it lay stress on the feature matching rather than on the Feature detection whereas in the Feature based methods it is based con extracting salient features in the images .For Eg detecting regions like boundaries, rivers, roads, forests ,lakes, corners etc .Image Registration basically consists of four steps (1) Feature Detection (2) Feature Matching (3) Transform model estimation (4) Image resampling and transformation .In feature detection features such as lines, intersections, corners, distinctive points are detected. In feature matching the features between the sensed and the reference image are to be detected .In transform model estimation the mapping points between the sensed and the reference image are to be established. In Image Resampling and transformation we get the image registered and different transformation techniques are applied to the image and the sensed image is to be mapped with the reference image.
|Item Type:||Thesis (MTech)|
|Uncontrolled Keywords:||SIFT algorithm; SURF; Random sample consensus|
|Subjects:||Engineering and Technology > Electronics and Communication Engineering > Image Processing|
|Divisions:||Engineering and Technology > Department of Electronics and Communication Engineering|
|Deposited By:||IR Staff BPCL|
|Deposited On:||11 Jun 2019 10:38|
|Last Modified:||11 Jun 2019 10:38|
|Supervisor(s):||Pati , Umesh Chandra|
Repository Staff Only: item control page