A MATLAB toolbox for hyperspectral image analysis

Arzuaga-Cruz, E.; Jimenez-Rodriguez, Luis O.; Vélez-Reyes, Miguel; Kaeli, David; Rodriguez‐Diaz, Eladio; Velazquez-Santana, H.T.; Castrodad-Carrau, Alexey; Santos-Campis, L.E.; Santiago, Cesar

doi:10.1109/igarss.2004.1370246

Cited by 16 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work the end-to-end processing of the algorithms included in the Hyperspectral Image Analysis Toolbox (HIAT) [5] for MATLAB along with other state of the art algorithms is studied. The HIAT contains algorithms for supervised and unsupervised classification, supervised abundance estimation, resolution enhancement and band subset selection.…”

Section: Simulation Resultsmentioning

confidence: 99%

Comparative study of state-of-the-art algorithms for hyperspectral image analysis

Rivera-Borrero

Hunt

2007

SPIE Proceedings

View full text Add to dashboard Cite

This work studies the end-to-end performance of hyperspectral classification and unmixing systems. Specifically, it compares widely used current state of the art algorithms with those developed at the University of Puerto Rico. These include algorithms for image enhancement, band subset selection, feature extraction, supervised and unsupervised classification, and constrained and unconstrained abundance estimation. The end to end performance for different combinations of algorithms is evaluated. The classification algorithms are compared in terms of percent correct classification. This method, however, cannot be applied to abundance estimation, as the binary evaluation used for supervised and unsupervised classification is not directly applicable to unmixing performance analysis. A procedure to evaluate unmixing performance is described in this paper and tested using coregistered data acquired by various sensors at different spatial resolutions. Performance results are generally specific to the image used. In an effort to try and generalize the results, a formal description of the complexity of the images used for the evaluations is required. Techniques for image complexity analysis currently available for automatic target recognizers are included and adapted to quantify the performance of the classifiers for different image classes.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Comparative study of state-of-the-art algorithms for hyperspectral image analysis

Rivera-Borrero

Hunt

2007

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…Hence, several segmentation algorithms has been proposed in the past to exploit both the spectral and spatial information in hyperspectral imagery. [9][10][11][12][14][15][16] Here, we will consider only three representative unsupervised segmentation algorithms that account for both the spectral and spatial information: unsupervised ECHO (un-ECHO) proposed by Landgrebe et al, 9 which is freely available with the software Multispec, c , a new version of un-ECHO proposed by Jimenez et al 10 that is available in the Hyperspectral Image Analysis Toolbox d (HIAT) in Matlab developed at the University of Puerto Rico in Mayagüez (UPRM), 17 and our hierarchical segmentation algorithm based on the scale-space concept. 11,12 We select these unsupervised segmentation algorithms due to their popularity, availability to our group, and also because in our own experience, ECHO spectral-spatial classifier is one of the best supervised classifiers of hyperspectral imagery.…”

Section: Segmentation Algorithmsmentioning

confidence: 99%

Unsupervised spectral-spatial classification of hyperspectral imagery using real and complex features and generalized histograms

2008

View full text Add to dashboard Cite

In this work, we study unsupervised classification algorithms for hyperspectral images based on band-by-band scalar histograms and vector-valued generalized histograms, obtained by vector quantization. The corresponding histograms are compared by dissimilarity metrics such as the chi-square, Kolmogorov-Smirnorv, and earth mover's distances. The histograms are constructed from homogeneous regions in the images identified by a pre-segmentation algorithm and distance metrics between pixels. We compare the traditional spectral-only segmentation algorithms C-means and ISODATA, versus spectral-spatial segmentation algorithms such as unsupervised ECHO and a novel segmentation algorithm based on scale-space concepts. We also evaluate the use of complex features consisting of the real spectrum and its derivative as the imaginary part. The comparison between the different segmentation algorithms and distance metrics is based on their unsupervised classification accuracy using three real hyperspectral images with known ground truth.

show abstract

“…This can become a problem when threads are complex -as is often the case for multi-dimensional imaging applications 1 . It is possible to reduce the number of registers to improve performance by making simple threads, reusing registers, and possibly using on-chip shared memory as an alternative to registers.…”

Section: Registers Required Per Threadmentioning

confidence: 99%

“…The code for the Matlab-based Hyperspectral imaging toolbox is a collection of functions designed to analyze multiand hyper-spectral images [1]. The majority of the operations performed by the toolbox functions are completely vectorized (they are performed on the entire image matrix).…”

Section: Hyperspectral Toolboxmentioning

confidence: 99%