Residual HSRCNN: Residual Hyper-Spectral Reconstruction CNN from an RGB Image

• Published in: 2018 24th International Conference on Pattern Recognition (ICPR) pp. 2664 - 2669
• Main Authors: Han, Xian-Hua, Shi, Boxin, Zheng, Yinqiang
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.08.2018
• Subjects: Cameras; Computer architecture; Image reconstruction; Signal resolution; Spatial resolution; Visualization
• DOI: 10.1109/ICPR.2018.8545634

Hyper-spectral imaging has great potential for understanding the characteristics of different materials in many applications ranging from remote sensing to medical imaging. However, due to various hardware limitations, only low-resolution hyper-spectral and high-resolution multi-spectral or RGB images can be captured at video rate. This study aims to generate a hyper-spectral image via enhancing spectral resolution of an RGB image, which might be easily obtained by a commodity camera. Motivated by the success of deep convolutional neural network (DCNN) for spatial resolution enhancement of natural images, we explore a spectral reconstruction CNN for spectral super-resolution with an available RGB image, which predicts the high-frequency content of the fine spectral wavelength in narrow band interval. Since the lost high-frequency content can not be perfectly recovered, by leveraging on the baseline CNN, we further propose a novel residual hyper-spectral reconstruction CNN framework to estimate the non-recovered high-frequency content (Residual) from the output of the baseline CNN. Experiments on benchmark hyper-spectral datasets validate that the proposed method achieves promising performances compared with the existing state-of-the-art methods.