next up previous contents
Next: 5.6 Image Up: 5. Image processing menus Previous: 5.4 Format   Contents


5.5 Histogram

This menu groups operations for finding and transforming image histograms. nip represents histograms and lookup tables as images with SPMquottype" set to SPMquothistogram". Histograms may have pixels in any format and any number of bands.

See also Find_profile in the Morphology menu.

Hist_find
Use this to find the histogram for an image. Histograms of 8-bit images are displayed as 256 $\times{}$ 256 images. Histograms of 16-bit images are displayed as $n$ by $m$ pixel images, where $n$ is the maximum pixel value and $m$ is the maximum frequency.

Hist_find_nD
Use this to find an $n$-dimensional histogram of an $n$-band image, where $n$ is 1, 2 or 3. The bins=> member sets the number of bins each axis is divided into. Works for 8- and 16-bit images.

Hist_map
Use this to map an image through a histogram. Select the histogram first and then the image and click Hist_map=>. The histogram must have either 1 band (in which case all image bands are passed though the same histogram band), or the same number of bands as the image.

Hist_cumulative
Use this to calculate a cumulative histogram. It works for any unsigned integer format.

Hist_normalise
Use this to normalise a histogram. The maximum histogram value becomes equal to the number of pixels in the histogram. In effect, the histogram becomes `square'. Each channel is normalised separately.

Hist_match
Use this to match the PDFs of two histograms. They need to have the same number of bands.

Hist_equalise
Use Global on an image to do global histogram equalisation. Mark a region on an image and use Local to equalise with a roving window the size of the region.

Guide_slice
Mark a guide on an image (drag from the rulers in an image display window) and use this to graph the pixels along the slice.


next up previous contents
Next: 5.6 Image Up: 5. Image processing menus Previous: 5.4 Format   Contents
John Cupitt 2003-07-21