Semantic classification for hyperspectral image by integrating distance measurement and relevance vector machine
- 533 Downloads
Accurate hyperspectral image classification requires not only image features but also semantic concept. Similarity and relevance relation are both key factors in building image features and semantic measurement. To perform hyperspectral image classification from the viewpoint of semantic, this study focuses on creating a semantic annotation-based image classification method with relevance and similarity measurement. First, the computational model of relevance vector machine is utilized to perform cluster computation for hyperspectral image data. Then multi-distance learning algorithm is optimized as holding capability for multiple dimensions data. The proposed multi-distance learning algorithm with multiple dimensions is used to measure the similarity, according to the result of cluster computation through relevance vector machine. Finally, semantic annotation is introduced to complete classification of hyperspectral image with semantic concept. Validation with the ground truth data illustrates that the proposed method can provide more accurate and integrated classification result compared with the other methodologies. Therefore, the integration of similarity and relevance measurement is able to improve the performance of hyperspectral image classification.
KeywordsSemantic classification Hyperspectral image Relevance vector machine Multi-distance learning with multiple dimensions
This work is jointly supported by the International Science and Technology Collaboration Project of China (2010DFA92720-24), National Natural Science Foundation program (No. 41301403 and No. 41471340); Chongqing Basic and Advanced Research General Project (No. cstc2013jcyjA40010); Hunan Provincial Natural Science Foundation of China (No. S2013J504B). The authors of this paper would also like to appreciate Prof. Paolo Gamba for his kindly providing hyperspectral image data of Pavia University, Pavia, northern Italy.
- 13.Zhang, L., Gao, Y., Xia, Y., et al.: A fine-grained image categorization system by cellet-encoded spatial pyramid modeling. IEEE Trans Ind Electron 99, 1 (2014)Google Scholar