Image registration using Hough transform and phase correlation

Chunhavittayatera, Siwaphon; Chitsobhuk, Orachat; Tongprasert, Kiatnarong

doi:10.1109/icact.2006.206134

Cited by 10 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alignment.-Using the spacial coordinates of wrinkles, we can determine rotation of the images by following the procedure presented by Chitsobhuk et al 21 Rotation of an image in Hough space is represented by a shift along the X axis. By aligning our key points vertically we determine the rotation of the image.…”

Section: Methodsmentioning

confidence: 99%

Communication–Multimodal Image Correlation in Two-Dimensional Materials via Automated Image Processing by Strain and Doping Analysis

Schmidt¹,

Trofe²,

Ignatova³

2022

ECS J. Solid State Sci. Technol.

View full text Add to dashboard Cite

It is common to characterize a single sample using multiple different microscopy methods that have variable scales, rotation, and translation. Correlating or registering hyperspectral images of two-dimensional materials is particularly difficult due to the lack of keypoints on un-patterned substrates. Strain/doping maps can assist by creating these keypoints. Registration of these images allows for multimodal analysis from these various instruments by aligning multiple images into a single coordinate space. This is done by Hough transformations and arbitrary resolution definitions to generate a new coordinate frame where spatial information may be preserved and correlated on a pixel by pixel basis.

show abstract

Section: Methodsmentioning

confidence: 99%

Communication–Multimodal Image Correlation in Two-Dimensional Materials via Automated Image Processing by Strain and Doping Analysis

Schmidt¹,

Trofe²,

Ignatova³

2022

ECS J. Solid State Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Animals were housed overnight at the Animal Resource Center and returned to our laboratory for 24 hours measurements. The field-of-view (FOV) registration was obtained by optical alignment of the SC images at 0 minutes and 24 hours for both experimental and control groups [17][18][19] to prevent erroneous 24 hours measurements. Specific points in the major arteries and veins of the SC images from 24 hours measurement were co-registered with the SC images from 0 minute.…”

Section: Methodsmentioning

confidence: 99%

Perfusion in hamster skin treated with glycerol

et al. 2009

View full text Add to dashboard Cite

show abstract

“…The combination of these properties and use of the Hough transform of gradient images rather than the intensity images differentiates our work from existing approaches such as the gradient field method in [6], intensity-based Hough registration in [3], and the gradientintensity method in [13]. The rotation estimation in [13] is robust w.r.t to non-overlapping areas but the centroid-based translation estimations are sensitive to non-overlapping areas of the image.…”

Section: Approach and Contributionmentioning

confidence: 96%

Image Registration in Hough Space Using Gradient of Images

Shams

Barnes²,

Hartley³

2007

9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (D

View full text Add to dashboard Cite

We present an accurate and fast method for rigid registration of images with large non-overlapping areas using a Hough transformation of image gradients. The Hough space representation of gradients can be used to separate estimation of the rotation parameter from the translation. It also allows us to estimate transformation parameters for 2D images over a 1D space, hence reducing the computational complexity. The cost functions in the Hough domain have larger capture ranges compared to the cost functions in the intensity domain. This allows the optimization to converge better in the presence of large misalignments. We show that the combination of estimating registration parameters in the Hough domain and fine tuning the results in the intensity domain significantly improves performance of the application compared to the conventional intensitybased multi-resolution methods.

show abstract

Image registration using Hough transform and phase correlation

Cited by 10 publications

References 4 publications

Communication–Multimodal Image Correlation in Two-Dimensional Materials via Automated Image Processing by Strain and Doping Analysis

Communication–Multimodal Image Correlation in Two-Dimensional Materials via Automated Image Processing by Strain and Doping Analysis

Perfusion in hamster skin treated with glycerol

Image Registration in Hough Space Using Gradient of Images

Contact Info

Product

Resources

About