Found scandata at /var/tmp/autoclean/derive/bulletinofnatura672nat/bulletinofnatura672nat_scandata.xml.
Will skip page 1 because it's a cover page.
Will skip page 104 because it's a cover page.
Seeking title page...

Will skip the following pages as requested: 1,104
Title:      "bulletin of the natural history museum (zoology)"
Start word: "bulletin"

Candidate words:
     p. 2     bulletin            34 px (0.00)
     p. 2     natural             35 px (0.00)
     p. 2     history             44 px (0.00)
     p. 2     zoology             45 px (0.29)
     p. 3     collections         68 px (0.30)
     p. 3     history             87 px (0.00)

Selected title page: 3
Identified leaf 3 as title page.
Marking leaf 3 as 'Title'.
Scandata has been modified. Saving log...