Recognition of Handwritten Japanese Characters Using Ensemble of Convolutional Neural Networks

• URL: http://arxiv.org/abs/2306.03954v1
• Date: Tue, 6 Jun 2023 18:30:51 GMT
• Title: Recognition of Handwritten Japanese Characters Using Ensemble of Convolutional Neural Networks
• Authors: Angel I. Solis, Justin Zarkovacki, John Ly and Adham Atyabi
• Abstract summary: The study used an ensemble of three convolutional neural networks (CNNs) for recognizing handwritten Kanji characters. The results indicate feasibility of using proposed CNN-ensemble architecture for recognizing handwritten characters.
• Score: 0.17646262965516946
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Japanese writing system is complex, with three character types of Hiragana, Katakana, and Kanji. Kanji consists of thousands of unique characters, further adding to the complexity of character identification and literature understanding. Being able to translate handwritten Japanese characters into digital text is useful for data analysis, translation, learning and cultural preservation. In this study, a machine learning approach to analyzing and recognizing handwritten Japanese characters (Kanji) is proposed. The study used an ensemble of three convolutional neural networks (CNNs) for recognizing handwritten Kanji characters and utilized four datasets of MNIST, K-MNIST, Kuzushiji-49 (K49) and the top 150 represented classes in the Kuzushiji-Kanji (K-Kanji) dataset for its performance evaluation. The results indicate feasibility of using proposed CNN-ensemble architecture for recognizing handwritten characters, achieving 99.4%, 96.4%, 95.0% and 96.4% classification accuracy on MNIST, K-MNIS, K49, and K-Kanji datasets respectively.

Related papers

• Bukva: Russian Sign Language Alphabet [75.42794328290088]
  This paper investigates the recognition of the Russian fingerspelling alphabet, also known as the Russian Sign Language (RSL) dactyl. Dactyl is a component of sign languages where distinct hand movements represent individual letters of a written language. We provide Bukva, the first full-fledged open-source video dataset for RSL dactyl recognition.
  arXiv  Detail & Related papers  (2024-10-11T09:59:48Z)
• Multi-Modal Multi-Granularity Tokenizer for Chu Bamboo Slip Scripts [65.10991154918737]
  This study focuses on the Chu bamboo slip (CBS) script used during the Spring and Autumn and Warring States period (771-256 BCE) in Ancient China. Our tokenizer first adopts character detection to locate character boundaries, and then conducts character recognition at both the character and sub-character levels. To support the academic community, we have also assembled the first large-scale dataset of CBSs with over 100K annotated character image scans.
  arXiv  Detail & Related papers  (2024-09-02T07:42:55Z)
• Multichannel Attention Networks with Ensembled Transfer Learning to Recognize Bangla Handwritten Charecter [1.5236380958983642]
  The study employed a convolutional neural network (CNN) with ensemble transfer learning and a multichannel attention network. We evaluated the proposed model using the CAMTERdb 3.1.2 data set and achieved 92% accuracy for the raw dataset and 98.00% for the preprocessed dataset.
  arXiv  Detail & Related papers  (2024-08-20T15:51:01Z)
• Tails Tell Tales: Chapter-Wide Manga Transcriptions with Character Names [53.24414727354768]
  This paper aims to generate a dialogue transcript of a complete manga chapter, entirely automatically. It involves identifying (i) what is being said, detecting the texts on each page and classifying them into essential vs non-essential. It also ensures the same characters are named consistently throughout the chapter.
  arXiv  Detail & Related papers  (2024-08-01T05:47:04Z)
• Kurdish Handwritten Character Recognition using Deep Learning Techniques [26.23274417985375]
  This paper attempts to design and develop a model that can recognize handwritten characters for Kurdish alphabets using deep learning techniques. A comprehensive dataset was created for handwritten Kurdish characters, which contains more than 40 thousand images. The tested results reported a 96% accuracy rate, and training accuracy reported a 97% accuracy rate.
  arXiv  Detail & Related papers  (2022-10-18T16:48:28Z)
• Kencorpus: A Kenyan Language Corpus of Swahili, Dholuo and Luhya for Natural Language Processing Tasks [0.0]
  The Kencorpus project intends to bridge the gap by collecting and storing text and speech data. The Kencorpus dataset is a text and speech corpus for three languages predominantly spoken in Kenya: Swahili, Dholuo and Luhya. The datasets are useful for downstream machine learning tasks such as model training and translation.
  arXiv  Detail & Related papers  (2022-08-25T13:27:14Z)
• Comprehensive Benchmark Datasets for Amharic Scene Text Detection and Recognition [56.048783994698425]
  Ethiopic/Amharic script is one of the oldest African writing systems, which serves at least 23 languages in East Africa. The Amharic writing system, Abugida, has 282 syllables, 15 punctuation marks, and 20 numerals. We presented the first comprehensive public datasets named HUST-ART, HUST-AST, ABE, and Tana for Amharic script detection and recognition in the natural scene.
  arXiv  Detail & Related papers  (2022-03-23T03:19:35Z)
• Writer Recognition Using Off-line Handwritten Single Block Characters [59.17685450892182]
  We use personal identity numbers consisting of the six digits of the date of birth, DoB. We evaluate two recognition approaches, one based on handcrafted features that compute directional measurements, and another based on deep features from a ResNet50 model. Results show the presence of identity-related information in a piece of handwritten information as small as six digits with the DoB.
  arXiv  Detail & Related papers  (2022-01-25T23:04:10Z)
• Predicting the Ordering of Characters in Japanese Historical Documents [6.82324732276004]
  Change in Japanese writing system in 1900 made historical documents inaccessible for the general public. We explore a few approaches to the task of predicting the sequential ordering of the characters. Our best-performing system has an accuracy of 98.65% and has a perfect accuracy on 49% of the books in our dataset.
  arXiv  Detail & Related papers  (2021-06-12T14:39:20Z)
• SHUOWEN-JIEZI: Linguistically Informed Tokenizers For Chinese Language Model Pretraining [48.880840711568425]
  We study the influences of three main factors on the Chinese tokenization for pretrained language models. We propose three kinds of tokenizers: SHUOWEN (meaning Talk Word), the pronunciation-based tokenizers; 2) JIEZI (meaning Solve Character), the glyph-based tokenizers. We find that SHUOWEN and JIEZI tokenizers can generally outperform conventional single-character tokenizers.
  arXiv  Detail & Related papers  (2021-06-01T11:20:02Z)
• HKR For Handwritten Kazakh & Russian Database [1.7499351967216341]
  We present a new Russian and Kazakh database (with about 95% of Russian and 5% of Kazakh words/sentences respectively) for offline handwriting recognition. The database is written in Cyrillic and shares the same 33 characters. It can serve researchers in the field of handwriting recognition tasks by using deep and machine learning.
  arXiv  Detail & Related papers  (2020-07-07T15:57:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.