We present a simple but novel hybrid approach to hyperspectral data cube reconstruction from computed tomography imaging spectrometry (CTIS) images that sequentially combines neural networks and the iterative Expectation Maximization (EM) algorithm. We train and test the ability of the method to reconstruct data cubes of $100\times100\times25$ and $100\times100\times100$ voxels, corresponding to 25 and 100 spectral channels, from simulated CTIS images generated by our CTIS simulator. The hybrid approach utilizes the inherent strength of the Convolutional Neural Network (CNN) with regard to noise and its ability to yield consistent reconstructions and make use of the EM algorithm's ability to generalize to spectral images of any object without training. The hybrid approach achieves better performance than both the CNNs and EM alone for seen (included in CNN training) and unseen (excluded from CNN training) cubes for both the 25- and 100-channel cases. For the 25 spectral channels, the improvements from CNN to the hybrid model (CNN + EM) in terms of the mean-squared errors are between 14-26%. For 100 spectral channels, the improvements between 19-40% are attained with the largest improvement of 40% for the unseen data, to which the CNNs are not exposed during the training.
翻译:我们对超光谱数据立方体的重建采用了简单而新颖的混合方法,从计算机成像成像光谱仪模拟器生成的模拟光谱立方体图像中重建超光谱数据立方体,这些立方体连续结合神经网络和迭代期望最大化算法。我们培训和测试重建数据立方体的能力,即100美元100分25分和100分100分100分,相当于25分和100分的光谱信道。混合方法利用了CTIS模拟器生成的模拟CTIS立方体的模拟立方体。对于25分光谱信道而言,CNN-40级神经网络(CNN)的内在强度,以及其产生一致重建的能力,以及利用EM算法的能力,在没有培训的情况下,将任何物体的光谱成光谱图像。混合法方法比CNN和仅见(CNN培训中包含的)CNN-100分光谱频道的性能更好,而CNN-40-26级网络网络网络网络网络的改进程度在平均的频谱上为19分级的改进幅度中,而CCNN+EM级的改进率为19分级的频率为19分级之间的最大。