Similarity-based Text Recognition by Deeply Supervised Siamese Network

11/13/2015
by   Ehsan Hosseini-Asl, et al.
0

In this paper, we propose a new text recognition model based on measuring the visual similarity of text and predicting the content of unlabeled texts. First a Siamese convolutional network is trained with deep supervision on a labeled training dataset. This network projects texts into a similarity manifold. The Deeply Supervised Siamese network learns visual similarity of texts. Then a K-nearest neighbor classifier is used to predict unlabeled text based on similarity distance to labeled texts. The performance of the model is evaluated on three datasets of machine-print and hand-written text combined. We demonstrate that the model reduces the cost of human estimation by 50%-85%. The error of the system is less than 0.5%. The proposed model outperform conventional Siamese network by finding visually-similar barely-readable and readable text, e.g. machine-printed, handwritten, due to deep supervision. The results also demonstrate that the predicted labels are sometimes better than human labels e.g. spelling correction.

READ FULL TEXT

page 2

page 10

research
09/02/2021

Semi-Supervised Learning using Siamese Networks

Neural networks have been successfully used as classification models yie...
research
12/20/2019

What do Asian Religions Have in Common? An Unsupervised Text Analytics Exploration

The main source of various religious teachings is their sacred texts whi...
research
09/12/2019

A Deep Learning-Based Approach for Measuring the Domain Similarity of Persian Texts

In this paper, we propose a novel approach for measuring the degree of s...
research
10/12/2021

SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Text

There are two cases describing how a classifier processes input text, na...
research
07/08/2018

Replicated Siamese LSTM in Ticketing System for Similarity Learning and Retrieval in Asymmetric Texts

The goal of our industrial ticketing system is to retrieve a relevant so...
research
02/01/2019

Learning icons appearance similarity

Selecting an optimal set of icons is a crucial step in the pipeline of v...

Please sign up or login with your details

Forgot password? Click here to reset