PHOCNet: A Deep Convolutional Neural Network for Word Spotting in Handwritten Documents

TL;DR

This paper introduces PHOCNet, a deep CNN architecture trained with PHOC representation, which outperforms existing methods in handwritten word spotting benchmarks with efficient training and testing times.

Contribution

The paper presents a novel CNN architecture, PHOCNet, specifically designed for handwritten word spotting, demonstrating superior performance over previous methods.

Findings

Outperforms state-of-the-art in word spotting benchmarks

Achieves short training and testing times

Effective use of PHOC representation in CNNs

Abstract

In recent years, deep convolutional neural networks have achieved state of the art performance in various computer vision task such as classification, detection or segmentation. Due to their outstanding performance, CNNs are more and more used in the field of document image analysis as well. In this work, we present a CNN architecture that is trained with the recently proposed PHOC representation. We show empirically that our CNN architecture is able to outperform state of the art results for various word spotting benchmarks while exhibiting short training and test times.