CHAPTER 2
Overview of Image Processing
Raghuveer M. Rao, Manoj K. Arora
2.1
Introduction
The current mode of image capture in remote sensing of the earth by aircraft or
satellite based sensors is in digital form. The pixels correspond to localized spatial information while the quantization levels in each spectral band correspond
to the quantized radiometric measurements. It is most logical to regard each
image as a vector array, that is, the pixels are arranged on a rectangular grid
but the value of the image at each pixel is a vector whose elements correspond
to radiometric levels (also known as intensity values or digital numbers) of the
different bands. The image formed for each band is a monochrome image and
for this reason, we refer to the quantized values of such an image as gray levels.
The images may be acquired in a few bands (i.e. multi-spectral image) or in
hundreds of bands (i. e. hyperspectral image). Image processing operations
for both multispectral and hyperspectral images can therefore be either scalar
image oriented, that is, each band is processed separately as an independent
image or vector image oriented, where the operations take into account the
vector nature of each pixel. Image processing can take place at several different
levels. At its most basic level, the processing enhances an image or highlights
specific objects for the analyst to view. At higher levels, processing can take on
the form of automatically detecting objects in the image and classifying them.
The aim of this chapter is to provide an overview of image processing of multispectral and hyperspectral data from the basic to the advanced techniques.
While a few excellent books are available on the subject (Jensen 1996; Mather
1999; Richards and Jia 1999; Campbell 2002), the purpose here is to provide
a ready reference to go with the other chapters of the book. It will be seen that
the bulk of processing techniques for image enhancement are those that have
been developed for consumer and document image processing and are thus
generic. They do not differ substantially in their applicability as a function
of the imaging platform be it hyperpsectral or otherwise and many of the
illustrations in this chapter use images in the visible band.
P. K. Varshney et al., Advanced Image Processing Techniques for Remotely Sensed Hyperspectral Data
© Springer-Verlag Berlin Heidelberg 2004
Overview of Image Processing
Raghuveer M. Rao, Manoj K. Arora
2.1
Introduction
The current mode of image capture in remote sensing of the earth by aircraft or
satellite based sensors is in digital form. The pixels correspond to localized spatial information while the quantization levels in each spectral band correspond
to the quantized radiometric measurements. It is most logical to regard each
image as a vector array, that is, the pixels are arranged on a rectangular grid
but the value of the image at each pixel is a vector whose elements correspond
to radiometric levels (also known as intensity values or digital numbers) of the
different bands. The image formed for each band is a monochrome image and
for this reason, we refer to the quantized values of such an image as gray levels.
The images may be acquired in a few bands (i.e. multi-spectral image) or in
hundreds of bands (i. e. hyperspectral image). Image processing operations
for both multispectral and hyperspectral images can therefore be either scalar
image oriented, that is, each band is processed separately as an independent
image or vector image oriented, where the operations take into account the
vector nature of each pixel. Image processing can take place at several different
levels. At its most basic level, the processing enhances an image or highlights
specific objects for the analyst to view. At higher levels, processing can take on
the form of automatically detecting objects in the image and classifying them.
The aim of this chapter is to provide an overview of image processing of multispectral and hyperspectral data from the basic to the advanced techniques.
While a few excellent books are available on the subject (Jensen 1996; Mather
1999; Richards and Jia 1999; Campbell 2002), the purpose here is to provide
a ready reference to go with the other chapters of the book. It will be seen that
the bulk of processing techniques for image enhancement are those that have
been developed for consumer and document image processing and are thus
generic. They do not differ substantially in their applicability as a function
of the imaging platform be it hyperpsectral or otherwise and many of the
illustrations in this chapter use images in the visible band.
P. K. Varshney et al., Advanced Image Processing Techniques for Remotely Sensed Hyperspectral Data
© Springer-Verlag Berlin Heidelberg 2004