Title | ||
---|---|---|
Combining deep learning and language modeling for segmentation-free OCR from raw pixels |
Abstract | ||
---|---|---|
We present a simple yet effective LSTM-based approach for recognizing machine-print text from raw pixels. We use a fully-connected feed-forward neural network for feature extraction over a sliding window, the output of which is directly fed into a stacked bi-directional LSTM. We train the network using the CTC objective function and use a WFST language model during recognition. Experimental results show that this simple system outperforms extensively tuned state-of-the-art HMM models on the DARPA Arabic Machine Print corpus. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/ASAR.2017.8067772 | 2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR) |
Keywords | Field | DocType |
DARPA Arabic Machine Print corpus,deep learning,language modeling,segmentation-free OCR,raw pixels,machine-print text,feed-forward neural network,feature extraction,sliding window,stacked bi-directional LSTM,CTC objective function,WFST language model,simple system,HMM models,LSTM-based approach | Sliding window protocol,Pattern recognition,Segmentation,Computer science,Feature extraction,Image segmentation,Speech recognition,Artificial intelligence,Deep learning,Hidden Markov model,Artificial neural network,Language model | Conference |
ISBN | Citations | PageRank |
978-1-5090-6629-2 | 2 | 0.38 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
stephen rawls | 1 | 59 | 4.08 |
Huaigu Cao | 2 | 347 | 29.09 |
Ekraam Sabir | 3 | 15 | 2.42 |
Premkumar Natarajan | 4 | 874 | 79.46 |