Histograms and Scatter Plots
The purpose and value of histogram data plots have been discussed in Section 1.
Here we will learn how to produce and display these and scatter plots as
aids to understanding the statistical distribution of DN values in individual
and paired bands.
- For the moment we will work with the default image in the PIT window. Click
on Windows, then drag over Open, then (in the small window to its right) click
on Histogram, and then on Small View. Releasing the mouse button brings a
small window up on the left called PIT - Histogram. Click on the Plot button,
which drops a gray window with Source (highlight). Drag the mouse to the right
into a window which has Thumbnail highlighted, then right again to a list
of the bands that are active. Choose band 1 and release the mouse button.
A histogram appears. Note the maximum and minimum DN values (the spread),
the values where the first significant frequencies occur, and the peak values
of the mono- or polymodal distribution; also the degree to which the distribution
is gaussian or normal. This information is especially important when used
by image processing programs that have several modes of contrast stretching. To see the histograms for other bands, just click back on Plot-->Source-->Thumbnail and choose a band.
- PIT Histogram has an interesting feature. You can select a portion of the
displayed histogram, which blocks out all the DN values in this range, and
then display in the image that is up all the pixels that fall within that
value range. This demarcates visually the spatial distribution of all such
- To do this, take the histogram display window (assuming it is being shown),
and placing the mouse cursor on its Title banner, drag the window away from
the Thumbnail image to the open screen space to the right. Now, place the
cursor somewhere within the actual histogram at whatever left DN point you
wish to start the DN range. Drag the cursor rightward; as you do, that portion
will fill in with color; continue until the area of the histogram containing
the range you are going to display on the image has been highlighted (you
can change color by clicking on Ranges, then checking the color desired). If the image actively displayed is not the same band as the histogram, you must return to the Interpretation window (or open it if it had been closed by the usual pathway: Windows Button-->Interpretation-->Left Scheme-->View-->Display Image Control Window, and then select the proper band).
When that window is displayed, click on the button called Matching, then on
Draw Boxes, followed by From Histogram. Watch as the color in the histogram
starts to fill in image pixels falling in the chosen range, with this proceeding
downward until the entire image is thus colored. All pixels within the range
are now identified in their spatial positions. (Note, drag the PIT - Interpretation
leftward until the image is near the left screen margin - this will allow
you to see both image and histogram window fully. Even better - use 1280 x
1024 screen resolution and top schemes.)
- To see pixel distributions for the other bands, first, remove the colored
area on the histogram now open by clicking on the Delete button in color-bordered
box in PIT - Histogram. Then, click and slide on Plot - Source - Thumbnail - Band Listing (make choice). The histogram for the chosen band
is displayed. But, the image in the PIT window is the default Thumbnail. You
need to display the new band. From the PIT Window, choose View, then Display
Image Control Window, and then from the dropdown window labeled Thumbnail
Image Control, select (replace number or hit black triangle) the band desired.
Once it is displayed, go through the histogram coloring and Match procedures
- Next, let us explore Scatter Diagrams. From the basic PIT window, click and drag
through Windows-->Open-->Scatter-->Small View, and release. The PIT
Scatter window drops into place. Click on Plot-->Source-->Thumbnail. You will see a window with a listing of Band 1 vs N through Band 7 vs N and by dragging further right a listing of
the bands. To set up the scatter pairing do this: move cursor to any band
of interest in the vs window; it will bring up a second screen to the right; then move
cursor to this last window and to the other band which will also highlight.
Click on that and the Scatter Diagram will appear. Note that it consists of
some geometric pattern in several shades of gray (the lighter the tone, the
greater the number of pixels in the distribution). If the pattern is a narrow
ellipse, with about a 45° angle, the two bands are strongly correlated; if
the angle is less or greater than 45° the same pixel point has two somewhat different
DN values but there is still some correlation. If other than an ellipse occurs,
this usually denotes a bimodal or polymodal distribution. Examination of the
corresponding histograms helps in the interpretation of the type of pattern
that emerges. To see Scatter Diagrams for other band pairs, simply repeat
the process starting with Plot and ending with the desired pairing. To remove
the diagram, click on Plot - Clear Plot.
Nicholas M. Short, Sr.
Jeff Love, PIT Developer (email@example.com