Data Augmentation for Recognition of Handwritten Words and Lines Using a CNN-LSTM Network

Wigington, Curtis; Stewart, Seth; Davis, Brian L.; Barrett, Bill; Price, Brian; Cohen, Scott

doi:10.1109/icdar.2017.110

Cited by 154 publications

(104 citation statements)

References 17 publications

Supporting

Mentioning

103

Contrasting

Unclassified

Order By: Relevance

“…In the paper [64], two data expansion and normalization techniques were presented, namely, a novel profile normalization technique for both word and line images and an extension of existing text images using random perturbations on a regular grid. These techniques, combined with LSTM CNN, significantly reduce error rates when recognizing the handwriting in characters and words.…”

Section: Literature Reviewmentioning

confidence: 99%

Application of the Deep CNN-Based Method in Industrial System for Wire Marking Identification

et al. 2021

View full text Add to dashboard Cite

Industry 4.0, a term invented by Wolfgang Wahlster in Germany, is celebrating its 10th anniversary in 2021. Still, the digitalization of the production environment is one of the hottest topics in the computer science departments at universities and companies. Optimization of production processes or redefinition of the production concepts is meaningful in light of the current industrial and research agendas. Both the mentioned optimization and redefinition are considered in numerous subtopics and technologies. One of the most significant topics in these areas is the newest findings and applications of artificial intelligence (AI)—machine learning (ML) and deep convolutional neural networks (DCNNs). The authors invented a method and device that supports the wiring assembly in the control cabinet production process, namely, the Wire Label Reader (WLR) industrial system. The implementation of this device was a big technical challenge. It required very advanced IT technologies, ML, image recognition, and DCNN as well. This paper focuses on an in-depth description of the underlying methodology of this device, its construction, and foremostly, the assembly industrial processes, through which this device is implemented. It was significant for the authors to validate the usability of the device within mentioned production processes and to express both advantages and challenges connected to such assembly process development. The authors noted that in-depth studies connected to the effects of AI applications in the presented area are sparse. Further, the idea of the WLR device is presented while also including results of DCNN training (with recognition results of 99.7% although challenging conditions), the device implementation in the wire assembly production process, and its users’ opinions. The authors have analyzed how the WLR affects assembly process time and energy consumption, and accordingly, the advantages and challenges of the device. Among the most impressive results of the WLR implementation in the assembly process one can be mentioned—the device ensures significant process time reduction regardless of the number of characters printed on a wire.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Application of the Deep CNN-Based Method in Industrial System for Wire Marking Identification

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Neural Networks (CNNs) [14] as a combination of convolutional and fully connected neural networks applied with data augmentation and training techniques [15]. The AlexNet was the winner of the ImageNet Large Scale Visual Recognition Challenge 2012 [16], and continues to be the source of inspiration for winners in years thereafter.…”

Section: Imagenet Classification With Deep Convolutionalmentioning

confidence: 99%

Real-Time Object Recognition Using Deep-Learning

Omar¹,

Mohammed²,

Khisro³

2021

ACAD J NAWROZ UNIV

View full text Add to dashboard Cite

The great interest at the moment is focused on the field of technology, especially artificial intelligence, also do not devoid of our daily life of the use of phone applications and computer programs, that increasing of phone and computer usage demands more programs and applications to satisfy the needs of users. However, this approach starts with acquirement an image of a particular medical or engineering tool, is displayed on the computer through a webcam, whether this image is a photo or digital through a display screen, or even the device itself, the computer will identify the tool and a simplified explanation of the way it works with a video demonstration throughout MATLAB IDE for implementing this project as well as easy to use by anyone even the user doesn't have any experience software.Finally, this approach has been created this project to save time and effort for the users instead of searching on a specific tool that they need about its name, how to use so we tried to facility this matter. The proposed algorithm got accurate result, for the doctor's tools the accuracy was 95.8 %, for the engineer's tools was 98.3 % and for mix of them was approximately 94.1 %.

show abstract

“…To artificially increase the amount of training data, we augment the existing preprocessed images by applying minor alterations to them. To simulate naturally occuring variations in handwritten text line images, we combine dilation, erosion and grid-like distortions [37]. These methods are applied to the original line image randomly with an independent probability of 50 %.…”

Section: E Preprocessing and Data Augmentationmentioning

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

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

Data Augmentation for Recognition of Handwritten Words and Lines Using a CNN-LSTM Network

Cited by 154 publications

References 17 publications

Application of the Deep CNN-Based Method in Industrial System for Wire Marking Identification

Application of the Deep CNN-Based Method in Industrial System for Wire Marking Identification

Real-Time Object Recognition Using Deep-Learning

Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition

Contact Info

Product

Resources

About