Retrieving Unrecognized Objects using Hyperspectral Imaging

This paper deals with the analysis for retrieving unrecognized objects from an image using Hyper spectral camera and high-resolution image. Retrieving unrecognized objects from an image is made possible using spectral analysis and spatial analysis. The method proposed to retrieve unrecognized object from a high-resolution image is more efficient in comparison with the other image retrieval techniques. To identify objects in an image, it should be detected and the detection technique to identify objects in an image is accomplished in two steps: anomaly detection based on the spectral data and the classification phase, based on spatial analysis. During the classification phase, the detected points of the searched object are projected on to the high-resolution images through registration algorithms. After that, each detected point is classified using linear discrimination functions and decision surfaces based on spatial features. The two detection steps possess spectral and spatial information. In order to overcome the problems associated with the smoothness of the edges of an image, transcoding technique is used using filter arrays.