Deep Manifold Embedding for Hyperspectral Image Classification

Abstract : Deep learning methods have played a more and more important role in hyperspectral image classification. However, general deep learning methods mainly take advantage of the sample-wise information to formulate the training loss while ignoring the intrinsic data structure of each class. Due to the high spectral dimension and great redundancy between different spectral channels in hyperspectral image, these former training losses usually cannot work so well for the deep representation of the image. To tackle this problem, this work develops a novel deep manifold embedding method (DMEM) for deep learning in hyperspectral image classification. First, each class in the image is modelled as a specific nonlinear manifold and the geodesic distance is used to measure the correlation between the samples. Then, based on the hierarchical clustering, the manifold structure of the data can be captured and each nonlinear data manifold can be divided into several sub-classes. Finally, considering the distribution of each sub-class and the correlation between different sub-classes under data manifold, the DMEM is constructed as the novel training loss to incorporate the special class-wise information in the training process and obtain discriminative representation for the hyperspectral image. Experiments over four real-world hyperspectral image datasets have demonstrated the effectiveness of the proposed method when compared with general samples-based losses and also shown the superiority when compared with the state-of-the-art methods.

 EXISTING SYSTEM :

 ? There is a large variety of HSI classification problems requiring a tailored design or an accurate assessment of existing DL solutions. ? To comply with the specific application requirements, complexity and computational issues as wellas hardware optimization must enter the selection of suitable approaches in addition to pursuing satisfactory accuracy performance. ? we present an overview of DL applications to HSI data subdivided into the main working fields. ? There is still an imbalance between the number of RS related papers with respect to other application fields.

 DISADVANTAGE :

 ? There exists high nonlinearity of samples within each class due to the high spectral channels, which makes the representation under Euclidean distance cannot work well. ? Therefore, how to effectively model and represent the samples of each class tends to be a difficult problem. ? Due to the good performance, this work takes advantage of the deep model to extract features from the hyperspectral image. ? Therefore, how to construct the training loss and fully utilize the data information with a certain limited number of training samples becomes the essential and key problem for training deep model effectively

 PROPOSED SYSTEM :

 • The proposed deep embedding model has demonstrated its superiority and effectiveness in the hyperspectral dimensionality reduction task. • Classification is explored as a potential strategy to quantitatively evaluate the performance of learned embedding representations. • Extensive experiments conducted on the widely-used hyperspectral datasets demonstrate the superiority and effectiveness of the proposed SSME as compared to several state-of-the-art embedding methods in terms of overall accuracy (OA), average accuracy (AA), and kappa coefficient (?).

 ADVANTAGE :

 ? To objectively evaluate the classification performance, metrics of the overall accuracy (OA), average accuracy (AA), and the Kappa coefficient are adopted. ? All the results come from the average value and standard deviation of ten runs of training and testing. ? We present the general performance of the developed manifold embedding for hyperspectral image classification. ? It should be noted that the developed manifold embedding is implemented through CPU and the computational performance can be remarkably improved by modifying the codes to run on the GPUs.