A quadrilateral distorted image correction algorithm based on block triangle

Xiangyu Deng; Aijia Zhang; Jinhong Ye

doi:10.1117/12.2681121

8 June 2023 A quadrilateral distorted image correction algorithm based on block triangle

Xiangyu Deng, Aijia Zhang, Jinhong Ye

Proceedings Volume 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023); 127074L (2023) https://doi.org/10.1117/12.2681121
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 2023, Changsha, China

Abstract

In the process of image shooting, due to the shooting angle or the shooting reason, the original image has geometric deformation problems in the geometric position, shape, size and orientation, which brings many inconvenience and difficulties to the following image processing fields such as image fusion, image denoising, image recognition, and image edge detection. In order to further improve the image processing ability and recognition accuracy of distorted graphics, this paper proposes a distortion correction algorithm based on block mapping for quadrilateral target images. This algorithm completes the transformation of the image from irregular to regular by dividing the quadrilateral image into two triangle images and performing homography mapping on the pixel points of the triangle image respectively. A large number of experiments show that the algorithm in this paper is superior to traditional methods such as hough and radon transform, and solves the limitations of traditional mapping algorithm in the process of quadrilateral image correction, improves the correction effect of distorted images, and provides a strong support for the subsequent processing of distorted images.

Citation Download Citation

Xiangyu Deng, Aijia Zhang, and Jinhong Ye "A quadrilateral distorted image correction algorithm based on block triangle", Proc. SPIE 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 127074L (8 June 2023); https://doi.org/10.1117/12.2681121

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available