A method for spectral image registration based on feature maximum submatrix

• Main Authors: Ke Wang, Huiqin Wang, Meng Wu, Zhan Wang, Jialin Liu
• Format: Article
• Language: English
• Published: SpringerOpen 2018-12-01
• Series: EURASIP Journal on Image and Video Processing
• Subjects: Geometric offset; SURF feature; Maximum submatrix; Registration
• Online Access: http://link.springer.com/article/10.1186/s13640-018-0377-4

Abstract In order to solve the geometric offset caused by replacing the filter during imaging of multichannel spectral image data, a multichannel spectral image registration method based on SURF feature merged with maximum submatrix is proposed. Firstly, the feature of multichannel spectral image is extracted by SURF. Then, a perspective transformation is performed to obtain a preliminary registration image. For the problem of invalid areas with zero pixel values appearing at the boundary of the image after registration, the largest submatrix is used to detect the maximum inscribed rectangle of the image to remove the invalid boundary region, and maximize the reserved effective region information. Experimented was processed with multichannel imaging data of murals. Experimental results agree with the theoretic analysis and verified that the proposed registration method is better adapted to image scale and brightness changing. At the same time, it can avoid the influence of invalid regions generated by other registration methods on subsequent spectral reconstruction and color restoration which has better performance.