Offline Arabic Handwriting Recognition Using Deep Learning: Comparative Study

Lamtougui, Hicham; Moubtahij, Hicham El; Fouadi, Hassan; Yahyaouy, Ali; Satori, Khalid

doi:10.1109/iscv49265.2020.9204214

Cited by 7 publications

(5 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Suppose that the visible layer element of RBM is represented by v and the hidden layer element is represented by h . The formula for calculated the energy of RBM is shown in (19).…”

Section: Emotion Classification 1) Conditional Deep Belief Networkmentioning

confidence: 99%

“…Using SER to achieve public opinion supervision needs high-precision classification algorithm supports, due to the unique layer-by-layer training mechanism, DBN network has more powerful high-dimensional data representation and classification ability in many tasks [19]- [21]. However, the existing DBN-based SER research does not consider the temporal correlation between speech features.…”

Section: Introductionmentioning

confidence: 99%

“…Zheng et al[18] and the Tylor-DBN algorithm proposed by Haridas et al[19] and the CNN bidirectional LSTM algorithm proposed by Yadav et al[35] on the CASIA dataset.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Speech Emotion Analysis of Netizens Based on Bidirectional LSTM and PGCDBN

et al. 2021

View full text Add to dashboard Cite

In recent years, the application of speech emotion recognition (SER) in the supervision of Internet public opinion has received increasing attention. This study proposes a new SER algorithm to analyze the public opinion information of network platforms. Firstly, we extract different spectrum features from speech signals and combine them into frame level speech features. Then, we select conditional deep confidence network (CDBN) which has the ability to learn sequential features as the final classification model. We apply particle swarm optimization (PSO) and genetic algorithm (GA) during the fine-tuning stage of the CDBN to obtain more suitable optimal weights of the whole network, and propose the PSO-GA-CDBN (PGCDBN) model. Compare with the traditional back propagation (BP) algorithm, our training method accelerates the convergence speed of the network and improves the robustness and recognition performance of the network. In our experiment, we used the Chinese Academy of Sciences' Institute of automation (CASIA) Chinese emotional corpus and self-collected Chinese speech datasets, which were collected from Sina Weibo, Tik tok and other online social media platforms. Compare with the popular emotion classifiers such as support vector machine (SVM), deep residual network (ResNet), long short-term memory (LSTM) neural network, DBN, our proposed PGCDBN achieves the best recognition results from both datasets. In addition, we use bidirectional LSTM before PGCDBN to further process the extracted speech features, and the result of bidirectional LSTM has stronger speech signal expression ability. The average recognition accuracy of this new hybrid deep learning model algorithm in two datasets is 98.67%, which can be used for the supervision of netizens' opinions.

show abstract

“…Suppose that the visible layer element of RBM is represented by v and the hidden layer element is represented by h . The formula for calculated the energy of RBM is shown in (19).…”

Section: Emotion Classification 1) Conditional Deep Belief Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Speech Emotion Analysis of Netizens Based on Bidirectional LSTM and PGCDBN

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Online systems use sensors to capture data during the writing process, while offline systems rely on images of the user's handwriting taken from a scanner or digital camera. Research suggests that online recognition has a higher recognition rate than offline mode [2], [3]. Many methods have been proposed for offline Arabic handwriting recognition to convert Arabic writings into a machine-readable format.…”

Section: Introductionmentioning

confidence: 99%

Classification and Localization of Arabic Handwritten Text in KHATT Dataset Based on Faster R-CNN

May Mowaffaq AL-Taee

2023

pst

View full text Add to dashboard Cite

Arabic handwriting recognition is an important research area in computer vision. Due to the complexity of the Arabic script, this is an arduous task. Several approaches have been proposed to address this challenge, including deep learning algorithms. Despite their efficiency, these approaches present some limitations such as the use of lexicon-driven models, the need of a lot of data for training and the huge computational cost. We propose, in this paper, two novel models based on the robust Faster Region-Convolution Neural Network (Faster R-CNN) to recognize Arabic handwritten sentences. The Faster R-CNN is commonly used to detect objects in images and depends on region proposal algorithms. These models use the pre-trained VGG 16 and ResNet50. Moreover, they use a soft non-maximum suppression strategy (Soft-NMS) in the post-processing stage instead of the traditional NMS to increase the detection rate of overlapping items. The models will be trained independently to identify words in the text lines and tested using sentences from the (KFUPM Handwritten Arabic TexT) KHATT dataset. It will be shown that the faster R-CNN models allow greater accuracy and effectiveness in handwriting recognition. They achieve accuracy rates of 99% and 98% for the two networks, VGG16 and ResNet50, respectively

show abstract

“…When using such structured data, a Convolutional Neural Network (CNN) is superior for learning features dependencies in wide datasets. In addition to that, CNN can also provide satisfactory performance with 1-dimentional data [4], [5], [6], [7], [8]. When working with time series data, Long Short-Term Memory (LSTM) algorithm can also learn easily temporal patterns and dependencies using memory cells and gates [9], [10], [11], [12], [13].…”

Section: Introductionmentioning

confidence: 99%

Ethereum Cryptocurrency Entry Point and Trend Prediction using Bitcoin Correlation and Multiple Data Combination

Zaar¹,

Benaya²,

Moubtahij³

et al. 2023

IJACSA

View full text Add to dashboard Cite

Deep learning methods have achieved significant success in various applications, including trend signal prediction in financial markets. However, most existing approaches only utilize price action data. In this paper, we propose a novel system that incorporates multiple data sources and market correlations to predict the trend signal of Ethereum cryptocurrency. We conduct experiments to investigate the relationship between price action, candlestick patterns, and Ethereum-Bitcoin correlation, aiming to achieve highly accurate trend signal predictions. We evaluate and compare two different training strategies for Convolutional Neural Networks (CNNs), one based on transfer learning and the other on training from scratch. Our proposed 1-Dimensional CNN (1DCNN) model can also identify inflection points in price trends during specific periods through the analysis of statistical indicators. We demonstrate that our model produces more reliable predictions when utilizing multiple data representations. Our experiments show that by combining different types of data, it is possible to accurately identify both inflection points and trend signals with an accuracy of 98%.

show abstract

Offline Arabic Handwriting Recognition Using Deep Learning: Comparative Study

Cited by 7 publications

References 51 publications

Speech Emotion Analysis of Netizens Based on Bidirectional LSTM and PGCDBN

Speech Emotion Analysis of Netizens Based on Bidirectional LSTM and PGCDBN

Classification and Localization of Arabic Handwritten Text in KHATT Dataset Based on Faster R-CNN

Ethereum Cryptocurrency Entry Point and Trend Prediction using Bitcoin Correlation and Multiple Data Combination

Contact Info

Product

Resources

About