CNN-N-Gram for HandwritingWord Recognition

Poznanski, Arik; Wolf, Lior

doi:10.1109/cvpr.2016.253

Cited by 121 publications

(104 citation statements)

References 37 publications

Supporting

Mentioning

102

Contrasting

Unclassified

Order By: Relevance

“…To further investigate the relation between confidence measures and attribute vector quality, we conduct the following experiment. The given word spotting system can easily be extended to perform lexicon-based word recognition analogue to the approach of [14]. Let L be the lexicon obtained from all available training and test set transcriptions with corresponding attribute representation l a.…”

Section: Resultsmentioning

confidence: 99%

Exploring Confidence Measures for Word Spotting in Heterogeneous Datasets

Wolf

Oberdiek

Fink

2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

In recent years, convolutional neural networks (CNNs) took over the field of document analysis and they became the predominant model for word spotting. Especially attribute CNNs, which learn the mapping between a word image and an attribute representation, showed exceptional performances. The drawback of this approach is the overconfidence of neural networks when used out of their training distribution. In this paper, we explore different metrics for quantifying the confidence of a CNN in its predictions, specifically on the retrieval problem of word spotting. With these confidence measures, we limit the inability of a retrieval list to reject certain candidates. We investigate four different approaches that are either based on the network's attribute estimations or make use of a surrogate model. Our approach also aims at answering the question for which part of a dataset the retrieval system gives reliable results. We further show that there exists a direct relation between the proposed confidence measures and the quality of an estimated attribute representation.

show abstract

Section: Resultsmentioning

confidence: 99%

Exploring Confidence Measures for Word Spotting in Heterogeneous Datasets

Wolf

Oberdiek

Fink

2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

show abstract

“…[9], [5] used all words in a sentence and paragraph respectively to provide word context. Poznanski and Wolf [23] used deep CNNs to extract n-gram attributes which feed CCA word recognition. [18], [23], [9], [11] use deslanting, training augmentation, and an ensemble of test samples.…”

Section: A Iam Resultsmentioning

confidence: 99%

Fully Convolutional Networks for Handwriting Recognition

Such

Peri

Brockler

et al. 2018

2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR)

View full text Add to dashboard Cite

Handwritten text recognition is challenging because of the virtually infinite ways a human can write the same message. Our fully convolutional handwriting model takes in a handwriting sample of unknown length and outputs an arbitrary stream of symbols. Our dual stream architecture uses both local and global context and mitigates the need for heavy preprocessing steps such as symbol alignment correction as well as complex post processing steps such as connectionist temporal classification, dictionary matching or language models. Using over 100 unique symbols, our model is agnostic to Latin-based languages, and is shown to be quite competitive with state of the art dictionary based methods on the popular IAM and RIMES datasets. When a dictionary is known, we further allow a probabilistic character error rate to correct errant word blocks. Finally, we introduce an attention based mechanism which can automatically target variants of handwriting, such as slant, stroke width, or noise.

show abstract

“…When the data is limited, fine-tuning a pre-trained network has also been demonstrated to be very effective. In the domain of document images these features have shown better performance for word spotting [37,74,76,83], recognition [52], document classification [26], layout analysis [10], etc. In this work, we propose a deep cnn architecture named as HWNet v2, for the task of learning an efficient word level representation for handwritten documents which can handle multiple writers and, is robust to common forms of degradation and noise.…”

Section: Introductionmentioning

confidence: 99%

HWNet v2: an efficient word image representation for handwritten documents

Krishnan

Jawahar

2019

IJDAR

View full text Add to dashboard Cite

We present a framework for learning an efficient holistic representation for handwritten word images. The proposed method uses a deep convolutional neural network with traditional classification loss. The major strengths of our work lie in: (i) the efficient usage of synthetic data to pre-train a deep network, (ii) an adapted version of the ResNet-34 architecture with the region of interest pooling (referred to as HWNet v2) which learns discriminative features for variable sized word images, and (iii) a realistic augmentation of training data with multiple scales and distortions which mimics the natural process of handwriting. We further investigate the process of transfer learning to reduce the domain gap between synthetic and real domain, and also analyze the invariances learned at different layers of the network using visualization techniques proposed in the literature.Our representation leads to a state-of-the-art word spotting performance on standard handwritten datasets and historical manuscripts in different languages with minimal representation size. On the challenging iam dataset, our method is first to report an mAP of around 0.90 for word spotting with a representation size of just 32 dimensions. Furthermore, we also present results on printed document datasets in English and Indic scripts which validates the generic nature of the proposed framework for learning word image representation.

show abstract

CNN-N-Gram for HandwritingWord Recognition

Cited by 121 publications

References 37 publications

Exploring Confidence Measures for Word Spotting in Heterogeneous Datasets

Exploring Confidence Measures for Word Spotting in Heterogeneous Datasets

Fully Convolutional Networks for Handwriting Recognition

HWNet v2: an efficient word image representation for handwritten documents

Contact Info

Product

Resources

About