Document Separation Question
Working with some county record documents, right now about 600 individual .tif files from the early 1920's. I need to perform classification but new document types might start in the middle of a page. For example, page 1 is a warranty deed that ends in the middle of page 2. Another document type lets say an affidavit starts in the middle of page 2 and ends in the middle of page 4. So on and so forth. Any thoughts on how to handle document separation/classification in this scenario?