Pho(SC)Net: An Approach Towards Zero-shot Word Image Recognition in Historical Documents

05/31/2021
by   Anuj Rai, et al.
0

Annotating words in a historical document image archive for word image recognition purpose demands time and skilled human resource (like historians, paleographers). In a real-life scenario, obtaining sample images for all possible words is also not feasible. However, Zero-shot learning methods could aptly be used to recognize unseen/out-of-lexicon words in such historical document images. Based on previous state-of-the-art methods for word spotting and recognition, we propose a hybrid representation that considers the character's shape appearance to differentiate between two different words and has shown to be more effective in recognizing unseen words. This representation has been termed as Pyramidal Histogram of Shapes (PHOS), derived from PHOC, which embeds information about the occurrence and position of characters in the word. Later, the two representations are combined and experiments were conducted to examine the effectiveness of an embedding that has properties of both PHOS and PHOC. Encouraging results were obtained on two publicly available historical document datasets and one synthetic handwritten dataset, which justifies the efficacy of "Phos" and the combined "Pho(SC)" representation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/21/2022

I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification

Despite the tremendous progress in zero-shot learning(ZSL), the majority...
research
10/22/2013

Word Spotting in Cursive Handwritten Documents using Modified Character Shape Codes

There is a large collection of Handwritten English paper documents of Hi...
research
07/12/2022

REZCR: A Zero-shot Character Recognition Method via Radical Extraction

The long-tail effect is a common issue that limits the performance of de...
research
08/27/2018

Open Set Chinese Character Recognition using Multi-typed Attributes

Recognition of Off-line Chinese characters is still a challenging proble...
research
12/08/2021

Prompt-based Zero-shot Relation Classification with Semantic Knowledge Augmentation

Recognizing unseen relations with no training instances is a challenging...
research
04/21/2021

Revisiting Document Representations for Large-Scale Zero-Shot Learning

Zero-shot learning aims to recognize unseen objects using their semantic...
research
06/25/2011

Morphological Reconstruction for Word Level Script Identification

A line of a bilingual document page may contain text words in regional l...

Please sign up or login with your details

Forgot password? Click here to reset