How to design synthetic images to validate and evaluate hyperspectral imaging algorithms

Many hyperspectral imaging algorithms are available for applications such as spectral unmixing, subpixel detection, quantification, endmember extraction, classification, compression, etc and many more are yet to come. It is very difficult to evaluate and validate different algorithms developed and designed for the same application. This paper makes an attempt to design a set of standardized synthetic images which simulate various scenarios so that different algorithms can be validated and evaluated on the same ground with completely controllable environments. Two types of scenarios are developed to simulate how a target can be inserted into the image background. One is called Target Implantation (TI) which implants a target pixel by removing the background pixel it intends to replace. This type of scenarios is of particular interest in endmember extraction where pure signatures can be simulated and inserted into the background with guaranteed 100% purity. The other is called Target Embeddedness (TE) which embeds a target pixel by adding this target pixel to the background pixel it intends to insert. This type of scenarios can be used to simulate signal detection models where the noise is additive. For each of both types three scenarios are designed to simulate different levels of target knowledge by adding a Gaussian noise. In order to make these six scenarios a standardized data set for experiments, the data used to generate synthetic images can be chosen from a data base or spectral library available in the public domain or websites and no particular data are required to simulate these synthetic images. By virtue of the designed six scenarios an algorithm can be assessed objectively and compared fairly to other algorithms on the same setting. This paper demonstrates how these six scenarios can be used to evaluate various algorithms in applications of subpixel detection, mixed pixel classification/quantification and endmember extraction.

[1]  P. Switzer,et al.  A transformation for ordering multispectral data in terms of image quality with implications for noise removal , 1988 .

[2]  Chein-I Chang,et al.  A posteriori least squares orthogonal subspace projection approach to desired signature extraction and detection , 1997, IEEE Trans. Geosci. Remote. Sens..

[3]  Chein-I Chang,et al.  Orthogonal subspace projection (OSP) revisited: a comprehensive study and analysis , 2005, IEEE Trans. Geosci. Remote. Sens..

[4]  Chein-I. Chang.  Hyperspectral Imaging: Techniques for Spectral Detection and Classification , 2003 .

[5]  Mario Winter,et al.  N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral data , 1999, Optics & Photonics.

[6]  Chein-I Chang,et al.  Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery , 2001, IEEE Trans. Geosci. Remote. Sens..

[7]  Xiaoli Yu,et al.  Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution , 1990, IEEE Trans. Acoust. Speech Signal Process..

[8]  Chein-I Chang.  Exploration of virtual dimensionality in hyperspectral image analysis , 2006, SPIE Defense + Commercial Sensing.

[9]  J. Boardman,et al.  Geometric mixture analysis of imaging spectrometry data , 1994, Proceedings of IGARSS '94 - 1994 IEEE International Geoscience and Remote Sensing Symposium.

[10]  Chein-I Chang,et al.  Target signature-constrained mixed pixel classification for hyperspectral imagery , 2002, IEEE Trans. Geosci. Remote. Sens..

[11]  Chein-I Chang,et al.  Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach , 1994, IEEE Trans. Geosci. Remote. Sens..