Vijay P. Shah

An Efficient Pan-Sharpening Method via a Combined Adaptive PCA Approach and Contourlets

High correlation among the neighboring pixels both spatially and spectrally in a multispectral image makes it necessary to use an efficient data transformation approach before performing pan-sharpening. Wavelets and principal component analysis (PCA) methods have been a popular choice for spatial and spectral transformations, respectively. Current PCA-based pan-sharpening methods make an assumption that the first principal component (PC) of high variance is an ideal choice for replacing or injecting it with high spatial details from the high-resolution histogram-matched panchromatic (PAN) image. This paper presents a combined adaptive PCA-contourlet approach for pan-sharpening, where the adaptive PCA is used to reduce the spectral distortion and the use of nonsubsampled contourlets for spatial transformation in pan-sharpening is incorporated to overcome the limitation of the wavelets in representing the directional information efficiently and capturing intrinsic geometrical structures of the objects. The efficiency of the presented method is tested by performing pan-sharpening of the high-resolution (IKONOS and QuickBird) and the medium-resolution (Landsat-7 Enhanced Thematic Mapper Plus) datasets. The evaluation of the pan-sharpened images using global validation indexes reveal that the adaptive PCA approach helps reducing the spectral distortion, and its merger with contourlets provides better fusion results.

On the Performance Evaluation of Pan-Sharpening Techniques

The limitations of the currently existing pan-sharpening quality indices are analyzed: the absolute difference between pixel values, mean shifting, and dynamic range change is frequently used as spatial fidelity measurement, but they may not correlate well with the actual change of image content; and spectral angle is a widely used metric for spectral fidelity, but the spectral angle remains the same if two vectors are multiplied by two individual constants, which means the average spectral angle between two multispectal images is zero even if pixel vectors are multiplied by different constants. Therefore, it is important to evaluate the quality of a pan-sharpened image under a task of its practical use and to assess spectral fidelity in the context of an image. In this letter, three data analysis techniques in linear unmixing, detection, and classification are applied to evaluate spectral information within a spatial scene context. It is demonstrated that those old but simplest approaches, i.e., Brovey and multiplicative (or after straightforward adjustment) methods, can generally yield acceptable data analysis results. Thus, it is necessary to consider the tradeoff between computational complexity, actual improvement on application, and hardware implementation when developing a pan-sharpening method.

Feature Identification via a Combined ICA–Wavelet Method for Image Information Mining

Image transformation is required for color-texture image segmentation. Various techniques are available for the transformation along the spatial and spectral axes. For instance, the HSV-wavelet technique is shown to be very effective for image information mining in remote-sensing applications. However, the HSV transformation approach uses only three spectral bands at a time. In this letter, a new feature set, obtained by combining independent component analysis and wavelet transformation for image information mining in geospatial data, is presented. Experimental results show the effectiveness of the presented method for image information mining in Earth observation data archives.

A framework for semantic reconciliation of disparate earth observation thematic data

There is a growing demand for digital databases of topographic and thematic information for a multitude of applications in environmental management, and also in data integration and efficient updating of other spatially oriented data. These thematic data sets are highly heterogeneous in syntax, structure and semantics as they are produced and provided by a variety of agencies having different definitions, standards and applications of the data. In this paper, we focus on the semantic heterogeneity in thematic information sources, as it has been widely recognized that the semantic conflicts are responsible for the most serious data heterogeneity problems hindering the efficient interoperability between heterogeneous information sources. In particular, we focus on the semantic heterogeneities present in the land cover classification schemes corresponding to the global land cover characterization data. We propose a framework (semantics enabled thematic data Integration (SETI)) that describes in depth the methodology involved in the reconciliation of such semantic conflicts by adopting the emerging semantic web technologies. Ontologies were developed for the classification schemes and a shared-ontology approach for integrating the application level ontologies as described. We employ description logics (DL)-based reasoning on the terminological knowledge base developed for the land cover characterization which enables querying and retrieval that goes beyond keyword-based searches.

Pan-sharpening via the contourlet transform

The wavelet transform has been a popular choice for the spatial transformation in the pan-sharpening process. However, the wavelet transform do not represent the directional information efficiently. On the other hand, the contourlet transform, which also has a property of multiresolution decomposition similar to the wavelet, is known to provide efficient directional information and is also useful in capturing intrinsic geometrical structures of the objects. This property of contourlet transformation is very useful for images that contain geometric features. Principal component analysis (PCA) is generally used for the spectral transformation. In this paper, an alternative algorithm based on the merger of PCA-contourlet transform for pan-sharpening is presented. The efficiency of this method is tested by performing pan-sharpening of the high resolution (IKONOS and Quickbird) and the medium resolution (LandSat7 ETM+) datasets. The resulting pan-sharpened images are evaluated in terms of known global validation indexes. These indexes reveal that this method provides better fusion results than the PCA-wavelet approach.

A Systematic Approach to Wavelet-Decomposition-Level Selection for Image Information Mining From Geospatial Data Archives

Recently, wavelet-based methods have been efficiently used for segmentation and primitive feature extraction to expedite the image-retrieval process of semantic-enabled frameworks for image information mining from geospatial data archives. However, the use of wavelets may introduce aliasing effects due to subband decimation at a certain decomposition level. This paper addresses the issue of selecting a suitable wavelet decomposition level, and a systematic selection process is developed. To validate the applicability of this method, a synthetic image is generated to qualitatively and quantitatively assess the performance. In addition, results for a Landsat-7 Enhanced Thematic Mapper Plus imagery archive are illustrated, and the F-measure is used to assess the feasibility of this method for the retrieval of different classes

Applying modular classifiers to mammographic mass classification

Classification is the last step in the computer aided diagnosis (CAD) system for determining whether a breast mass segmented from a digital mammogram is malignant or benign. Hence it is important to improve sensitivity at this stage. This work investigates the use of modular classifier (MoC) schemes, namely bagging and adaboost algorithms, for automated classification of mammographic masses. CAD systems containing a MoC are compared to CAD systems that contain traditional classifiers (TrC), for example single nearest mean or maximum likelihood classifiers. This study included 200 digitized mammograms, each manually segmented by a radiologist. In order to test the MoC and TrC approaches, conventional shape based features were extracted from the segmented masses. These features were then optimized using Fischers linear discriminant analysis (LDA). When no LDA was utilized, it was observed that MoC schemes increased the sensitivity from 74% to 83% over the TrC approaches. After performing LDA, the sensitivity increased from 83% to 88% for TrC and MoC schemes, respectively.

Tarp Filtering of Block-Transform Coefficients for Embedded Image Coding

Tarp filtering, an image coder with a simple implementation, is coupled with a block-based discrete cosine transform equipped with pre- and postfiltering. The prefilter reduces intra-block and inter-block correlation of the block-based coefficients, resulting in coefficients that are less correlated and thereby more suitable to tarp filtering. Experimental results show that the proposed coder achieves a significant improvement in rate-distortion performance as compared to the corresponding tarp coder in its original wavelet-based formulation for images with highly detailed content. A similar gain over JPEG2000 is seen for these same images, while, for images that are mostly smooth, the proposed coder performs comparably to JPEG2000

Joint spectral and spatial quality evaluation of pan-sharpening algorithms

This research study presents a novel global index based on harmonic mean theory to jointly evaluate the performance of pan-sharpening algorithms without using a reference image. The harmonic mean of relative spatial information gain and relative spectral information preservation provides a unique global index to compare the performance of different methods. The presented index also facilitates in assigning relevance to either the spectral or spatial quality of an image. The information divergence between the multispectral (MS) bands at lower resolutions and the pan-sharpened image provides a measure of the spectral fidelity and mean-shift. Mutual information between the original pan and the synthetic pan images generated from the MS and pan-sharpened images is used to calculate the relative gain. The relative gain helps to quantify the amount of spatial information injected by the method. A trend comparison of the presented approach with other quality indices using well-known pan-sharpening methods on high resolution and medium resolution datasets reveals that the new index can be used to evaluate the quality of pan-sharpened images at the resolution of the pan image without the availability of a reference image.

Image information mining for coastal disaster management

In this paper we propose a framework that focuses on the need for rapid image information mining in a coastal disaster event where it is necessary to explore vast amounts of data from multiple remote sensing sensors in real or near real time. The proposed system; Rapid Image Information Mining (RIIM) is a region based approach where in lieu of prevalent pixel based methods it localizes interesting zones and extracts information from them that are stored in a knowledge base. A set of primitive features are extracted from the regions, whose relevance for a particular land cover class or a combination of classes is then assessed based on a wrapper based genetic algorithm (GA) approach. In this, we use an induction algorithm along with the GA to arrive at an optimal set of features. We investigate feature selection and feature generation using this wrapper approach. A support vector machines based classification is applied for generating predictive models for those land cover classes that are important in coastal disaster events. In RUM, searching for a particular land cover type (e.g. flooded agriculture) is based on the actual meaning and content of it in the image instead of just the metadata.