Next Article in Journal
Experimental Study on the Surface Properties of Nanoalumina-Filled Epoxy Resin Nanocomposites
Next Article in Special Issue
Image Super-Resolution Based on CNN Using Multilabel Gene Expression Programming
Previous Article in Journal
Properties of Curved Parts Laser Cladding Based on Controlling Spot Size
Previous Article in Special Issue
Optical Flow-Based Fast Motion Parameters Estimation for Affine Motion Compensation
Article

Image Registration Algorithm Based on Convolutional Neural Network and Local Homography Transformation

Faculty of Information Science and Engineering, Ningbo University, Ningbo 315211, China
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(3), 732; https://doi.org/10.3390/app10030732
Received: 18 December 2019 / Revised: 15 January 2020 / Accepted: 16 January 2020 / Published: 21 January 2020
(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)
In order to overcome the poor robustness of traditional image registration algorithms in illuminating and solving the problem of low accuracy of a learning-based image homography matrix estimation algorithm, an image registration algorithm based on convolutional neural network (CNN) and local homography transformation is proposed. Firstly, to ensure the diversity of samples, a sample and label generation method based on moving direct linear transformation (MDLT) is designed. The generated samples and labels can effectively reflect the local characteristics of images and are suitable for training the CNN model with which multiple pairs of local matching points between two images to be registered can be calculated. Then, the local homography matrices between the two images are estimated by using the MDLT and finally the image registration can be realized. The experimental results show that the proposed image registration algorithm achieves higher accuracy than other commonly used algorithms such as the SIFT, ORB, ECC, and APAP algorithms, as well as another two learning-based algorithms, and it has good robustness for different types of illumination imaging. View Full-Text
Keywords: image registration; homography matrix; local homography transformation; convolutional neural network; moving direct linear transformation image registration; homography matrix; local homography transformation; convolutional neural network; moving direct linear transformation
Show Figures

Figure 1

MDPI and ACS Style

Wang, Y.; Yu, M.; Jiang, G.; Pan, Z.; Lin, J. Image Registration Algorithm Based on Convolutional Neural Network and Local Homography Transformation. Appl. Sci. 2020, 10, 732. https://doi.org/10.3390/app10030732

AMA Style

Wang Y, Yu M, Jiang G, Pan Z, Lin J. Image Registration Algorithm Based on Convolutional Neural Network and Local Homography Transformation. Applied Sciences. 2020; 10(3):732. https://doi.org/10.3390/app10030732

Chicago/Turabian Style

Wang, Yuanwei, Mei Yu, Gangyi Jiang, Zhiyong Pan, and Jiqiang Lin. 2020. "Image Registration Algorithm Based on Convolutional Neural Network and Local Homography Transformation" Applied Sciences 10, no. 3: 732. https://doi.org/10.3390/app10030732

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop