Document image classification, with a specific view on applications of patent images

TL;DR

This paper conducts an extensive experimental study on document image classification and retrieval, focusing on parameter optimization for RL and FV representations across diverse datasets, including patent images, to guide effective feature selection.

Contribution

It provides comprehensive guidelines for parameter choices in RL and FV image representations, enhancing their applicability to various document image classification and retrieval tasks, especially patents.

Findings

Optimal parameters vary across datasets and tasks

RL and FV representations perform well with proper tuning

The same features can be used for classification and retrieval

Abstract

The main focus of this paper is document image classification and retrieval, where we analyze and compare different parameters for the RunLeght Histogram (RL) and Fisher Vector (FV) based image representations. We do an exhaustive experimental study using different document image datasets, including the MARG benchmarks, two datasets built on customer data and the images from the Patent Image Classification task of the Clef-IP 2011. The aim of the study is to give guidelines on how to best choose the parameters such that the same features perform well on different tasks. As an example of such need, we describe the Image-based Patent Retrieval task's of Clef-IP 2011, where we used the same image representation to predict the image type and retrieve relevant patents.