Document image retrieval based on 2D density distributions of terms with pseudo relevance feedback

Document image retrieval is a task to retrieve document images relevant to a user's query. Most existing methods based on word-level indexing rely on the representation called "bag of words" which originated in the field of information retrieval. This paper presents a new representation of documents that utilizes additional information about the location of words in pages so as to improve the retrieval performance. We consider that pages are relevant to a query if they contain its terms densely. This notion is embodied as density distributions of terms calculated in the proposed method. Its performance is improved with the help of "pseudo relevance feedback", i.e., a method of expanding a query by analyzing pages. Experimental results on English document images show that the proposed method is superior to conventional methods of electronic document retrieval at recall levels 0.0-0.6.