Figure 6 - available via license: CC BY
Content may be subject to copyright.
Graphical representation of Algorithm 2: (a) reference image; (b) sensed image; (c) template image; and (d) target image.
Source publication
Image registration is a spatial alignment of corresponding images of the same scene acquired from different views, sensors, and time intervals. Especially, satellite image registration is a challenging task due to the high resolution of images. In addition, demands for high resolution satellite imagery are increased for more detailed and precise in...
Context in source publication
Context 1
... the other hand, the performance of area-based methods is degraded due to the similar spectral ranges. The steps for feature extraction are illustrated in Algorithm 2 and its graphical representation is shown in Figure 6. Data: R(x, y): reference image with size (X, Y); Z(x, y): sensed image with size (X, Y); for each input image do divide input images into K blocks, each of (M × N): block size; take K templates, each of (M × N ): template size for k ← 1 to K do for k ← 1 to K do for each position (u, v) in kth block within k th template do Compute mean subtracted images for block and template using (8) and (9); Compute numerator FZNCC through FFT using (10); Compute ZNCC putting numerator FZNCC in (7); ...
Similar publications
Citations
Quality assurance for image matching is the main concern for researchers, especially when it comes to Transformed Images for multidisciplinary fields such as remote sensing, military, security, medicine, and multimedia fields. Based on this, there have been many challenges to the application of image technology. Image matching gets more complicated based on the geometric transformation because the image will lose its edges and make it harder to determine the local invariant features. Related studies were applied for different methods, and few attempted to compare the quality measurement. In this paper, we assessed some quality measurement methods to find out how they are affected by the geometric transformation in the matching process and how these methods can detect the difference between the matched images. We have achieved a significant result that would help in choosing the best method for quality measurement.
Many astrophysical observations and measurement techniques that rely on data from images include an image registration step. The results of such techniques thus heavily rely on the precision of the registration. We present an Iterative Phase Correlation (IPC) algorithm, which is an extension of the well-known phase correlation method of image registration and is ideally suited for problems, where the subpixel registration accuracy plays a crucial role. Furthermore, a sophisticated and reliable method of optimal IPC parameter estimation is described. The paper includes examples of such optimized parameters for Solar Dynamics Observatory ( SDO )/Helioseismic and Magnetic Imager, SDO /Atmospheric Imaging Assembly, and Solar Terrestrial Relations Observatory A / B Sun Earth Connection Coronal and Heliospheric Investigation images. The new method (both with or without the parameter optimization step) significantly outperforms standard image registration methods, such as (non-iterative) phase correlation or (normalized) cross correlation in the sense of subpixel accuracy. A step-by-step pseudocode implementation is also included.
