As indicated in the previous chapter, the parameters for many point operations can be derived from the histogram of pixel values of the image. This chapter is divided into to two parts: the first considers greyscale histograms and some of their applications, and the second extends this to multidimensional histograms.
7.1 Greyscale Histogram
The histogram of a greyscale image, as shown in Figure 7.1, gives a count of the number of pixels in an image as a function of pixel value.
There are two main steps associated with using histograms for image processing. The first step is to build the histogram, and the second is to extract data from the histogram and use it for processing the image. Building the histogram is discussed in this section, whereas the applications are described in subsequent sections.
To build the histogram, it is necessary to accumulate the counts for each pixel value, as indicated in Equation 7.1. Since each pixel must be visited once, building the histogram is ideally suited to stream processing. To accumulate the pixel count for each pixel value requires maintaining the count so far for each value. This may be accomplished by an array of counters, with the input pixel used to enable the ...