Cross lingual handwritten character recognition using long short term memory network with aid of elephant herding optimization algorithm

Guptha, Nirmala S; Balamurugan, V.; Megharaj, Geetha; Sattar, Khalid Nazim Abdul; Rose, J.

doi:10.1016/j.patrec.2022.04.038

Cited by 32 publications

(14 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Guptha [21] presented the deep learning based approach to perform automatic character recognition. At first, Gaussian filtering and skew detection were used to perform the pre-processing for the images acquired from Chars74K & MADbase digits datasets.…”

Section: Related Workmentioning

confidence: 99%

“…The dataset used for the English and Kannada HCR is the Chars74k dataset. The comparative analysis between the HF-LSTM [19], EHO-LSTM [21] and HFE-MSSAE for Kannada characters is shown in Table 3 and Fig. 7, where NA refers the values which are not available.…”

Section: Comparative Analysismentioning

confidence: 99%

“…Similarly, the comparative analysis between the CNN [18], HF-LSTM [19], EHO-LSTM [21] and HFE-MSSAE for English characters is shown in Table 4 and Fig. 8.…”

Section: Comparative Analysismentioning

confidence: 99%

“…From the analysis, it is known that the HFE-MSSAE provides better performance than the CNN [18], HF-LSTM [19] and EHO-LSTM [21]. For example, the accuracy of the HFE-MSSAE for Kannada is 96.73% whereas the accuracy of HF-LSTM [19] is 95.06% and EHO-LSTM [21] is 96.67%. The CNN [18] and HF-LSTM [19] obtains less accuracy because it processes all the extracted features during the classification.…”

Section: Comparative Analysismentioning

confidence: 99%

“…The CNN [18] and HF-LSTM [19] obtains less accuracy because it processes all the extracted features during the classification. The EHO-LSTM [21] and Kannada characters.…”

Section: Comparative Analysismentioning

confidence: 99%

See 4 more Smart Citations

Handwritten Character Recognition Using Morlet Stacked Sparse Auto Encoder based Feature Dimension Reduction

2023

IJIES

View full text Add to dashboard Cite

Handwritten character recognition (HCR) is a growing field in the applications of pattern recognition, image processing, communication technologies, and so on. But, the identification of handwritten characters affected because of different styles of writers, or even one writer's style differed according to the conditions. Moreover, the huge amount of features from the handwritten characters also affect the classification. To address the aforementioned issues, the hybrid feature extraction (HFE) with morlet stacked sparse auto-encoder (MSSAE) based feature dimensionality reduction is proposed for improving the classification of HCR. Here, the HFE is the combination of different textural and shape features such as histogram of oriented gradients (HOG), gray-level co-occurrence matrix (GLCM), discrete wavelet transform (DWT), and skeleton features. The morlet wavelet activation function is used in the MSSAE to enhance the dimensionality reduction ability that used for an effective reduction of feature dimensions. The reduction of feature dimension using MSSAE is used to improve the classification using multi-class support vector machine (MSVM). In this research, the real-time indigenous languages i.e., English and Kannada handwritten characters from the Chars74K dataset are used for the analysis i.e., offline recognition. On the other hand, the online recognition of Kannada characters is also done for analyzing the HFE-MSSAE method. The HFE-MSSAE method is analyzed in terms of accuracy, precision, recall, CSI and F-measure. The existing researches namely convolutional neural network (CNN), hybrid feature based long short term memory (HF-LSTM) and elephant herding optimization -long short term memory (EHO-LSTM) are used to evaluate the HFE-MSSAE method. The accuracy of the HFE-MSSAE for Kannada is 96.73% which is higher than the HF-LSTM and EHO-LSTM.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Comparative Analysismentioning

confidence: 99%

“…Similarly, the comparative analysis between the CNN [18], HF-LSTM [19], EHO-LSTM [21] and HFE-MSSAE for English characters is shown in Table 4 and Fig. 8.…”

Section: Comparative Analysismentioning

confidence: 99%

Section: Comparative Analysismentioning

confidence: 99%

“…The CNN [18] and HF-LSTM [19] obtains less accuracy because it processes all the extracted features during the classification. The EHO-LSTM [21] and Kannada characters.…”

Section: Comparative Analysismentioning

confidence: 99%

See 3 more Smart Citations