where smean and hmean denote the average stroke width and
the average text line height of a slide frame, and ymax
denotes the maximum vertical position of a text line object
(starts from the top-left corner of the image).
To further extract the lecture outline, we firstly apply a
spell checker to sort out text line objects which do not satisfy
the following conditions:
a valid text line object must have more than three
characters,
a valid text line object must contain at least one
noun,
the textual character count of a valid text line object
must be more than 50 percent of the entire string
length.