A Noise-Resistant Superpixel Segmentation Algorithm for Hyperspectral Images

The superpixel segmentation has been widely applied in many computer vision and image process applications.In recent years,amount of superpixel segmentation algorithms have been proposed.However,most of the current algorithms are designed for natural images with little noise corrupted.In order to apply the superpixel algorithms to hyperspectral images which are always seriously polluted by noise,we propose a noiseresistant superpixel segmentation(NRSS)algorithm in this paper.In the proposed NRSS,the spectral signatures are first transformed into frequency domain to enhance the noise robustness;then the two widely spectral similarity measures-spectral angle mapper(SAM)and spectral information divergence(SID)are combined to enhance the discriminability of the spectral similarity;finally,the superpixels are generated with the proposed frequency-based spectral similarity.Both qualitative and quantitative experimental results demonstrate the effectiveness of the proposed superpixel segmentation algorithm when dealing with hyperspectral images with various noise levels.Moreover,the proposed NRSS is compared with the most widely used superpixel segmentation algorithm-simple linear iterative clustering(SLIC),where the comparison results prove the superiority of the proposed superpixel segmentation algorithm.

Classification of hyperspectral remote sensing images using frequency spectrum similarity

An algorithm of hyperspectral remote sensing images classification is proposed based on the frequency spectrum of spectral signature.The spectral signature of each pixel in the hyperspectral image is taken as a discrete signal,and the frequency spectrum is obtained using discrete Fourier transform.The discrepancy of frequency spectrum between ground objects' spectral signatures is visible,thus the difference between frequency spectra of reference and target spectral signature is used to measure the spectral similarity.Canberra distance is introduced to increase the contribution from higher frequency components.Then,the number of harmonics involved in the proposed algorithm is determined after analyzing the frequency spectrum energy cumulative distribution function of ground object.In order to evaluate the performance of the proposed algorithm,two hyperspectral remote sensing images are adopted as experimental data.The proposed algorithm is compared with spectral angle mapper (SAM),spectral information divergence (SID) and Euclidean distance (ED) using the product accuracy,user accuracy,overall accuracy,average accuracy and Kappa coefficient.The results show that the proposed algorithm can be applied to hyperspectral image classification effectively.

Rapid discovery and identification of 68 compounds in the active fraction from Xiao-Xu-Ming decoction(XXMD) by HPLC-HRMS and MTSF technique

Xiao-Xu-Ming decoction（XXMD） was a traditional Chinese prescription and first recorded in ＂Bei Ji Qian Jin Yao Fang＂.It has been widely used to treat theoplegia and the sequel of theoplegia in China.In the present work,high-performance liquid chromatography coupled with high resolution mass spectrometry（HPLC-HRMS） combined with the mass spectral tree similarity filter technique（MTSF）was used to rapidly discover and identify the compounds of the active fraction of XXMD.A total of 3362 compounds were automatically detected by HPLC-HRMS,and final 68 compounds were identified in the active fraction of XXMD.including 14 templated compounds（reference compounds）,50 related compounds fished by MTSF technique,and 4 unrelated compounds identified by manual method.This study successfully applied MTSF technology for the first time to discover and identify the components of Chinese prescription.The results demonstrated that MTSF technique should be useful to the discovery and identification of compounds in Chinese prescription.This study also proved that MTSF can be applied to the targeted phytochemical separation.