MayoBMI at ImageCLEF 2016 Handwritten Document Retrieval Task

In this working note, we introduce our participation at the ImageCLEF 2016 Handwritten Document Retrieval Task. We mainly focused on hyphenation detection using line images and information retrieval using n-best results. The hyphenation detection step utilizes extracted image features from beginning and end of a line and a binary classifier to determine if a line contains hyphenation. Then the spell correction step is used to eliminate spelling errors from the concatenation of a broken word from the end of a line and the beginning of the next line. The final text retrieval step employs a suffix stripping algorithm to normalize the word tense and form and TF-IDF scheme to rank the retrieved relevant segment results of our submission.