18048975. OBLIQUE IMAGE RECTIFICATION simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

OBLIQUE IMAGE RECTIFICATION

Organization Name

INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor(s)

Sebastien Gilbert of Québec (CA)

Michele Merler of New York NY (US)

Dhiraj Joshi of Edison NJ (US)

Apurv Gupta of Vadodara (IN)

Shyama Prosad Chowdhury of Kolkata (IN)

CHIDANSH AMITKUMAR Bhatt of Hightstown NY (US)

Nirmit V. Desai of Yorktown Heights NY (US)

OBLIQUE IMAGE RECTIFICATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 18048975 titled 'OBLIQUE IMAGE RECTIFICATION

Simplified Explanation

The techniques described in the patent application involve rectifying oblique images of circular objects by using machine learning models and affine transformations.

• Receiving an original image depicting an oblique view of a circular object
• Pre-processing the original image into an edge image
• Generating a heatmap including an ellipse formed by the oblique view of the circular object
• Computing ellipse parameters describing the ellipse of the heatmap
• Performing an affine transformation on the original image using the ellipse parameters to generate a rectified image where the ellipse is converted to a circle

Potential Applications

This technology could be applied in fields such as computer vision, image processing, and augmented reality for rectifying oblique images of circular objects.

Problems Solved

This technology solves the problem of rectifying oblique images of circular objects to improve accuracy and visual representation.

Benefits

The benefits of this technology include improved image rectification, enhanced visualization, and better object recognition in images.

Potential Commercial Applications

One potential commercial application of this technology could be in the development of software tools for image editing and enhancement in various industries.

Possible Prior Art

Prior art in this field may include techniques for image rectification and object detection using machine learning models and geometric transformations.

What are the limitations of this technology in terms of image rectification accuracy?

The accuracy of image rectification using this technology may be limited by the quality of the original image and the complexity of the circular object's oblique view.

How does this technology compare to traditional image rectification methods?

This technology offers a more automated and efficient approach to image rectification compared to traditional methods, which may require manual adjustments and calibration.

Original Abstract Submitted

Described are techniques for oblique image rectification. The techniques include receiving an original image depicting an oblique view of a circular object and pre-processing the original image into an edge image. The techniques further include generating, by a machine learning model based on the edge image, a heatmap including an ellipse formed by the oblique view of the circular object. The techniques further include computing ellipse parameters describing the ellipse of the heatmap. The techniques further include performing, using the ellipse parameters, an affine transformation on the original image to generate a rectified image, where the rectified image converts the ellipse to a circle.