A Clustering Backed Deep Learning Approach for Document Layout Analysis

Abstract

Large organizations generate documents and records on a daily basis, often to such an extent that processing them manually becomes unduly time consuming. Because of this, automated processing systems for documents are desirable, as they would reduce the time spent handling them. Unfortunately, documents are often not designed to be machine-readable, so parsing them is a difficult problem. Image segmentation techniques and deep-learning architectures have been proposed as a solution to this, but have difficulty retaining accuracy when page layouts are especially dense. This leads to the possibilities of data being duplicated, lost, or inaccurate during retrieval. We propose a way of refining these segmentations, using a clustering based approach that can be easily combined with existing rules based refinements. We show that on a financial document corpus of 2675 pages, when using DBSCAN, this method is capable of significantly increasing the accuracy of existing deep-learning methods for image segmentation. This improves the reliability of the results in the context of automatic document analysis.

Semantic Document Layout Analysis of Handwritten Manuscripts

“…As such, document layout analysis (DLA) is used as a standard preprocessing and an essential prerequisite for developing any document image processing and analysis system. Thus, DLA has emerged as a priority topic and active research domain [3] and has increasingly become a significant interest in numerous research studies [4][5][6][7][8][9]. DLA algorithms can be carried out top-down or bottom-up with respect to their processing order [10].…”

“…Performing consecutive or cumulative connected component (CC) and pixel analyses on a document image was a typical dominant technique enforced to initially identify regions and then classify them, as adopted by the majority of proposed DLA systems [17,19,22]. Furthermore, advanced deep learning models were also used for empowering different DLA frameworks [7][8][9]23].…”

“…Many research studies have been conducted using DLA for document layout-based clustering, highlighting the importance and usefulness of clustering documents-depending on different common layout properties-in several practical applications [18,[24][25][26]. For instance, to solve the problem of non-standard and densely populated documents, a clustering algorithm combined with simple refinement rules was used to cluster some layout constituents and improve document image segmentation [9]. Furthermore, clustering documents by their types (e.g., invoices, articles, letters) is a desirable solution for archiving massive collections of scanned documents.…”