Are Multidimensional Recurrent Layers Really Necessary for Handwritten Text Recognition?

Puigcerver, Joan

doi:10.1109/icdar.2017.20

Cited by 223 publications

(197 citation statements)

References 10 publications

Supporting

Mentioning

194

Contrasting

Order By: Relevance

“…The current state-of-the-art in many text recognition tasks additionally integrate CNNs for an improved low-level feature extraction prior to the recurrent layers. This approach is applied to offline HTR by [4]. Recently there have been developments towards fully convolutional architectures, i.e.…”

Section: Related Workmentioning

confidence: 99%

“…Generally, the de facto standard for HTR tasks have been systems based on Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) [3], [4], which are utilizing the Connectionist Temporal Classification (CTC) [5] objective function. However, CTC-based architectures are subject to inherent limitations like strict monotonic input-output alignments and an output sequence length that is bound by the, possibly subsampled, input length.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition

Michael

Labahn

Grüning³

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

104

View full text Add to dashboard Cite

Encoder-decoder models have become an effective approach for sequence learning tasks like machine translation, image captioning and speech recognition, but have yet to show competitive results for handwritten text recognition. To this end, we propose an attention-based sequence-to-sequence model. It combines a convolutional neural network as a generic feature extractor with a recurrent neural network to encode both the visual information, as well as the temporal context between characters in the input image, and uses a separate recurrent neural network to decode the actual character sequence. We make experimental comparisons between various attention mechanisms and positional encodings, in order to find an appropriate alignment between the input and output sequence. The model can be trained end-to-end and the optional integration of a hybrid loss allows the encoder to retain an interpretable and usable output, if desired. We achieve competitive results on the IAM and ICFHR2016 READ data sets compared to the state-of-theart without the use of a language model, and we significantly improve over any recent sequence-to-sequence approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition

Michael

Labahn

Grüning³

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

104

View full text Add to dashboard Cite

show abstract

“…We show that FCNs with dilated 1×3 convolutions detect long text lines as single entities significantly better than FCNs that use only un-dilated 3×3 convolutions. We choose to detect text at the line level as this is the input expected by state-of-the-art handwriting recognition methods [13]. Figure 2.…”

Section: Detectionmentioning

confidence: 99%

Deep Visual Template-Free Form Parsing

Davis

Morse

Cohen

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

Automatic, template-free extraction of information from form images is challenging due to the variety of form layouts. This is even more challenging for historical forms due to noise and degradation. A crucial part of the extraction process is associating input text with pre-printed labels. We present a learned, template-free solution to detecting preprinted text and input text/handwriting and predicting pairwise relationships between them. While previous approaches to this problem have been focused on clean images and clear layouts, we show our approach is effective in the domain of noisy, degraded, and varied form images. We introduce a new dataset of historical form images (late 1800s, early 1900s) for training and validating our approach. Our method uses a convolutional network to detect pre-printed text and input text lines. We pool features from the detection network to classify possible relationships in a language-agnostic way. We show that our proposed pairing method outperforms heuristic rules and that visual features are critical to obtaining high accuracy.

show abstract

“…Bluche et al [12], [13] described an end-to-end system that uses an MD-RNN along with an LSTM to encode multiple lines of text. Although the described system shows promise to automatically recognise multiple lines, it may not be a practical solution as it requires a large amount of computational power [11]. Winglinton et al [14] utilised a region proposal network to find the starting positions of text lines and a line follower network was trained to trace the line of text.…”

Section: B Text Recognitionmentioning

confidence: 99%

A Computationally Efficient Pipeline Approach to Full Page Offline Handwritten Text Recognition

Chung¹,

Delteil²

2019

2019 International Conference on Document Analysis and Recognition Workshops (ICDARW)

View full text Add to dashboard Cite

Offline handwriting recognition with deep neural networks is usually limited to words or lines due to large computational costs. In this paper, a less computationally expensive full page offline handwritten text recognition framework is introduced. This framework includes a pipeline that locates handwritten text with an object detection neural network and recognises the text within the detected regions using features extracted with a multi-scale convolutional neural network (CNN) fed into a bidirectional long short term memory (LSTM) network. This framework achieves comparable error rates to state of the art frameworks while using less memory and time. The results in this paper demonstrate the potential of this framework and future work can investigate production ready and deployable handwritten text recognisers.

show abstract

Are Multidimensional Recurrent Layers Really Necessary for Handwritten Text Recognition?

Cited by 223 publications

References 10 publications

Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition

Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition

Deep Visual Template-Free Form Parsing

A Computationally Efficient Pipeline Approach to Full Page Offline Handwritten Text Recognition

Contact Info

Product

Resources

About