Effect of supervised learning methodologies in offline handwritten Thai character recognition

Joseph, Ferdin Joe John

doi:10.1007/s41870-019-00366-y

Cited by 16 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, the features of the HOG, GLCM, DWT and skeleton are concatenated together for generating the feature set (𝑥) as shown in Eq. (7). Therefore, a total 20 features i.e., 1 feature from HOG, 14 features from GLCM, 4 features from DWT, and 1 feature from the skeleton are extracted from HFE.…”

Section: Skeleton Featurementioning

confidence: 99%

See 1 more Smart Citation

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: Skeleton Featurementioning

confidence: 99%

“…The characters on the smart devices (e.g., smartphones and tablets) are online whereas the identification of handwritten text on paper is related to the offline [7][8][9]. The characters written by each person aren't matching and change in both shapes and sizes.…”

Section: Introductionmentioning

confidence: 99%

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

2023

IJIES

View full text Add to dashboard Cite

show abstract

“…The approach is implemented based on the Visual Geometry Group (VGG16) model and reached superior results on ICDAR2013 and ICDAR2015 datasets. (Joseph, 2020) proposed OCR approach to recognize Thai characters. Preprocessing operations are used to improve picture quality such as converting the image to grayscale color, binarization, and median filter are used to remove image noise.…”

Section: Related Workmentioning

confidence: 99%

A Printed Arabic Optical Character Recognition System using Deep Learning

Alghyaline¹

2022

Journal of Computer Science

View full text Add to dashboard Cite

Recognizing Arabic script is challenging for many reasons: The Arabic language is cursive and morphologically rich. There is a high similarity between Arabic letters. Moreover, Arabic has many diacritics and dots, and they change the letter's phonetic transcription. This study proposes a Printed Arabic Optical Character Recognition approach (PAOCR) based on the state-of-the-art You Only Look Once (YOLO) object detector. Four techniques were proposed and implemented to design an end-to-end Arabic OCR system. First, the YOLO4 object detector is customized and trained on deep Convolutional Neural Networks (CNNs) to recognize Arabic characters. Second, the overlapped bounding boxes are processed to keep the most accurate box for each character. Third, the Hunspell library checks the word spelling and corrects the wrong ones. Fourth, edit distance is used to compare OCR misspelled words with Hunspell's suggestions and choose the closest correct word. The experimental results in the Arabic Printed Text Image (APTI) dataset showed that the Word Recognition Rate (WRR) of customized YOLO4 Arabic OCR is 66.7%, whereas applying the three proposed techniques with YOLO4 achieved 82.4%. A comparison with two existing OCR systems Tesseract and ABBYY showed that the proposed approach achieved a 95.7% Character Recognition Rate (CRR), whereas Tesseract and ABBYY achieved 92.3 and 84.8%, respectively.

show abstract

A Dynamic Perceptual Detector Module-Related Telemonitoring for the Intertubes of Health Services

Rupapara

Rajest

Regin

et al. 2023

EAI/Springer Innovations in Communication and Computing

View full text Add to dashboard Cite

Effect of supervised learning methodologies in offline handwritten Thai character recognition

Cited by 16 publications

References 8 publications

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

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

A Printed Arabic Optical Character Recognition System using Deep Learning

A Dynamic Perceptual Detector Module-Related Telemonitoring for the Intertubes of Health Services

Contact Info

Product

Resources

About