Authors: Liow Wolf, liza Potikha, nachum Dershowitz, Roni Shweka, Yaacov Choueka
- sparse coding
Q1: What is the ultimate goal of authors?
Two main goals are, providing tools to bring together the fragments of the same page (from Cairo Genizah) and trying to classify handwriting and dates.
Q2: How SIFT is used?
SIFT is used in (all?) points of a letter to generate desxriptors. There are 100.000 descriptors overall before inputting into k-means. SIFT plays the main classification technique.
Q3: How did they produce the letter dictionaries?
Q4: What is sparse coding and its importance?
Sparse coding is to code documents (or any other codable thing) with a separating/descriptive code which shows also the similarity between items. An example might be bag of visuual words approach.
Q5: Are there any relevant techniques for our research?
This is relevant to divan-matching problem. This work might be cited in historical document matching. But it doesn't tell much that I don't know.