HKR For Handwritten Kazakh &amp; Russian Database

Nurseitov, Daniyar; Bostanbekov, Kairat; Kurmankhojayev, Daniyar; Alimova, Anel; Abdallah, Abdelrahman

doi:10.48550/arxiv.2007.03579

Cited by 4 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this research, our contribution is to present a novel attention-based fully gated convolutional recurrent neural network, trained in Kazakh and Russian dataset [25], it will be processed as follows:…”

Section: Previous Approaches To the Offline Handwriting Text Recognit...mentioning

confidence: 99%

See 1 more Smart Citation

Attention-based Fully Gated CNN-BGRU for Russian Handwritten Text

Abdallah,

Hamada,

Nurseitov

2020

Preprint

Self Cite

View full text Add to dashboard Cite

This research approaches the task of handwritten text with attention encoderdecoder networks that are trained on Kazakh and Russian language. We developed a novel deep neural network model based on Fully Gated CNN, supported by Multiple bidirectional GRU and Attention mechanisms to manipulate sophisticated features that achieve 0.045 Character Error Rate (CER), 0.192 Word Error Rate (WER) and 0.253 Sequence Error Rate (SER) for the first test dataset and 0.064 CER, 0.24 WER and 0.361 SER for the second test dataset. Also, we propose fully gated layers by taking the advantage of multiple the output feature from Tahn and input feature, this proposed work achieves better results and We experimented with our model on the Handwritten Kazakh & Russian Database (HKR). Our research is the first work on the HKR dataset and demonstrates state-of-the-art results to most of the other existing models.

show abstract

Section: Previous Approaches To the Offline Handwriting Text Recognit...mentioning

confidence: 99%

“…Our work is the first research paper in our HKR Dataset [25], this dataset is first open-source in Russian and Kazakh handwritten datasets until now there is no dataset in theses language available to the researchers…”

Section: Related Workmentioning

confidence: 99%

Attention-based Fully Gated CNN-BGRU for Russian Handwritten Text

Abdallah,

Hamada,

Nurseitov

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep learning has recently achieving state-of-the-art using convolutional neural network (CNN) [9] in many tasks including object detection [10], face recognition [11], sequence to sequence learning [12,13], speech recognition [14], semantic segmentation [15], image classification [16], handwritten recognition [17,18,19], and table detection [1,8,6] is demanding because they need to classify tables among the texts and other figures. The presence of split columns or rows, as well as nested tables or embedded figures, makes the detection of a table even more difficult.…”

Section: Introductionmentioning

confidence: 99%

TNCR: Table Net Detection and Classification Dataset

Abdallah,

Berendeyev,

Nuradin

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present TNCR, a new table dataset with varying image quality collected from free websites. TNCR dataset can be used for table detection in scanned document images and their classification into 5 different classes. TNCR contains 9428 high-quality labeled images. In this paper, we have implemented state-of-the-art deep learning-based methods for table detection to create several strong baselines. Cascade Mask R-CNN with ResNeXt-101-64x4d Backbone Network achieves the highest performance compared to other methods with a precision of 79.7%, recall of 89.8%, and f1 score of 84.4% on the TNCR dataset. We have made TNCR open source in the hope of encouraging more deep learning approaches to table detection, classification and structure recognition. The dataset and trained model checkpoints are available at https://github.com/abdoelsayed2016/TNCR_Dataset

show abstract

“…Kernel principal component analysis (KPCA) was calculated from urinary organic (nuclear magnetic resonance) and inorganic (inductively coupled plasma optical emission spectrometry) data. [4,5,6] Along these same lines, existing pseudorandom and heterogeneous algorithms use adaptive information to cache link-level acknowledgments. The emulation of Internet QoS would tremendously improve robust technology.…”

Section: Introductionmentioning

confidence: 99%

Estimate The Efficiency Of Multiprocessor's Cash Memory Work Algorithms

Hamada¹,

Abdallah²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Many computer systems for calculating the proper organization of memory are among the most critical issues. Using a tier cache memory (along with branching prediction) is an effective means of increasing modern multi-core processors' performance. Designing high-performance processors is a complex task and requires preliminary verification and analysis of the model level, usually used in analytical and simulation modeling. The refinement of extreme programming is an unfortunate challenge. Few experts disagree with the synthesis of access points. This article demonstrates that Internet QoS and 16-bit architectures are always incompatible, but it's the same situation for write-back caches. The solution to this problem can be implemented by analyzing simulation models of different complexity in combination with the analytical evaluation of individual algorithms. This work is devoted to designing a multi-parameter simulation model of a multi-process for evaluating the performance of cache memory algorithms and the optimality of the structure. Optimization of the structures and algorithms of the cache memory allows you to accelerate the interaction of the memory process and improve the performance of the entire system.

show abstract

HKR For Handwritten Kazakh & Russian Database

Cited by 4 publications

References 28 publications

Attention-based Fully Gated CNN-BGRU for Russian Handwritten Text

Attention-based Fully Gated CNN-BGRU for Russian Handwritten Text

TNCR: Table Net Detection and Classification Dataset

Estimate The Efficiency Of Multiprocessor's Cash Memory Work Algorithms

Contact Info

Product

Resources

About