Printed thai character segmentation and recognition

Chomphuwiset, Phatthanaphong

doi:10.1109/iscmi.2017.8279611

Cited by 6 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mookdarsanit & Mookdarsanit [15] presented a combination of hate speech in Thai text memes using Thai OCR. Furthermore, Chomphuwiset [16] presented a technique for recognising printed Thai characters using a feature-based technique and a convolutional neural network (CNN). Other related studies have also found techniques to improve the accuracy of Thai character recognition such as using string matching [35], histogram of gradients (HOG) [36,37], color layout descriptors [36], normalised correlation coefficients [36], and circular-scan histograms [38].…”

Section: Figure 2 Example Of a Thai Word With Three Elements: Letters...mentioning

confidence: 99%

“…Other related studies have also found techniques to improve the accuracy of Thai character recognition such as using string matching [35], histogram of gradients (HOG) [36,37], color layout descriptors [36], normalised correlation coefficients [36], and circular-scan histograms [38]. Regarding the level of accuracy, available techniques for Thai character recognition from images have an accuracy rate of 75-98%; Chomphuwiset [16] applied his method to actual cases, achieving an accuracy of 98.00%. Thammano & Duangphasuk [25] used a technique to recognise both the Thai sign and car license plate, producing an accuracy of 82.42%.…”

Section: Figure 2 Example Of a Thai Word With Three Elements: Letters...mentioning

confidence: 99%

“…Many studies in Thailand have focused on applying optical character recognition (OCR) [14,15] or machine learning technology [16]; however, findings demonstrate that Thai character recognition is still less effective than that of English characters. Somboonsak [17] found detecting new words that were not in the dictionary and adding new words to the dictionary difficult.…”

Section: Introductionmentioning

confidence: 99%

“…Somboonsak [17] found detecting new words that were not in the dictionary and adding new words to the dictionary difficult. Chomphuwiset [16] identified problems with memorizing two Thai words that combine into one word, indentation, and space and considered developing post-processing techniques to solve this problem in the future. Mookdarsanit & Mookdarsanit [15] found homophones, slang, and image noise problems.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automated Data Digitization System for Vehicle Registration Certificates Using Google Cloud Vision API

Thammarak

Sirisathitkul²,

Kongkla³

et al. 2022

Civ Eng J

View full text Add to dashboard Cite

This study aims to develop an automated data digitization system for the Thai vehicle registration certificate. It is the first system developed as a web service Application Programming Interface (API), which is essential for any enterprise to increase its business value. Currently, this system is available on “www.carjaidee.com”. The system involves four steps: 1) an embedded frame aligns a document to be correctly recognised in the image acquisition step; 2) sharpening and brightness filtering techniques to enhance image quality are applied in the pre-processing step; 3) the Google Cloud Vision API receives a prompt to proceed in the recognition step; 4) a specific domain dictionary to improve accuracy rate is developed for the post-processing step. This study defines 92 images for the experiment by counting the correct words and terms from the output. The findings suggest that the proposed method, which had an average accuracy of 93.28%, was significantly more accurate than the original method using only the Google Cloud Vision API. However, the system is limited because the dictionaries cannot automatically recognise a new word. In the future, we will explore solutions to this problem using natural language processing techniques. Doi: 10.28991/CEJ-2022-08-07-09 Full Text: PDF

show abstract

Section: Figure 2 Example Of a Thai Word With Three Elements: Letters...mentioning

confidence: 99%

Section: Figure 2 Example Of a Thai Word With Three Elements: Letters...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated Data Digitization System for Vehicle Registration Certificates Using Google Cloud Vision API

Thammarak

Sirisathitkul²,

Kongkla³

et al. 2022

Civ Eng J

View full text Add to dashboard Cite

show abstract

“…However, in this work, they did not mention about the used features. (Chomphuwiset, 2017) proposed the CNN based Thai character recognition method. It began with character segmentation from a document by using Otsu's thresholding.…”

Section: Learned Feature Based Approachesmentioning

confidence: 99%

Thai scene text recognition

Kobchaisawat

View full text Add to dashboard Cite

Automatic scene text detection and recognition can benefit a large number of daily life applications such as reading signs and�labels, and helping visually impaired persons. Reading scene text images becomes more challenging than reading�scanned documents in many aspects due to many factors such as variations of font styles and unpredictable lighting conditions. The problem can be decomposed into two sub-problems: text localization and text recognition. The proposed scene text localization works at the pixel level combined with a new text representation and a fully-convolutional neural network. This method is capable of detecting arbitrary shape�texts without language limitations. The experimental results on the standard benchmarks show the performance in terms of accuracy and speed compared to the existing works. The cropped text instances are passed into the proposed text recognition algorithm, which consists of four stages:�transformation, feature extraction, sequence modeling, and prediction. The proposed method is designed based on a fully-learnable deep learning-based model in combination with multi-level�attention, which inspires from Thai writing system. The training data is purely synthesized from various fonts and novel techniques to make the generated images looked sensible. The experimental results on the test dataset show excellent accuracy and inference time.

show abstract