Taylor series-based generic demosaicking algorithm for multispectral image

• Published in: AOPC 2017: Optical Sensing and Imaging Technology and Applications Vol. 10462; pp. 1046237 - 1046237-8
• Main Authors: Han, Jiatong, Zhang, Geng, Liu, Xuebin
• Format: Conference Proceeding
• Language: English
• Published: SPIE 24.10.2017
• ISBN: 9781510614055; 1510614052
• ISSN: 0277-786X
• DOI: 10.1117/12.2285052

Using coated mosaic video spectrometer to collect multispectral image which reduce the spectral information redundancy and data volume greatly and achieve real-time data transmission conditions. The mosaic video spectrometer imaging technique use a similar mosaic template to capture all the pixels and output a two-dimensional multi-spectral image with dozens of spectral information. The image is divided into a certain size of matrix in its field, and each pixel in the pixel matrix is only for one wavelength information response and every pixel response for different wavelength. The size of the pixel matrix block depends on the number of spectral segments, which results in a low spatial resolution of the single spectral segment image and the spectral information of each pixel absenting severely. Therefore, to reconstruct the complete multi-spectral image, we must estimate and interpolate the missing spatial information and spectral information by demosaicking multispectral image. In this paper, we present a novel demosaicking method to produce the high resolution multispectral image and reconstruct missing spectrum information in high accuracy. The proposed method computes the first-and second-order derivatives of the original single multispectral image to measure the geometry of edges in the image and the spectrum value of missing pixel. Two metrics are used to evaluate the generic algorithm, including the structural similarity index-measurement system (SSIM) for reconstruction performance and the procession time. Experimental results show that the demosaicked images present higher SSIM (more than 0.9) and comparable calculated time performance as traditional ways. This algorithm brings the greatest advantage that make up for the weakness of mosaick multispectral image and reduce the data transmission process cost and storage needs.