機械学習を用いた空中手書き文字認識の検討

DOI 機関リポジトリ Web Site

書誌事項

タイトル別名
  • Studies on Aerial Handwritten Character Recognition Using Machine Learning
  • キカイ ガクシュウ オ モチイタ クウチュウ テガキキ モジ ニンシキ ノ ケントウ

この論文をさがす

説明

This paper presents a method to recognize a character handwritten in the air. We had prototyped an aerial handwritten hiragana character recognition system that detect single character period by hovering in the air using DP (dynamic programming) matching. In this time, we investigate an aerial handwritten character recognition system using machine learning. We use two features, vector and picture. Feature of vector is relative direction of handwriting information. It is a time series information so we use LSTM (Long Short Term Memory) to learn data of characters. Feature of picture is absolutely handwriting information. We use CNN (Convolution Neural Network) to learn data of characters, because this model is suitable for picture recognize. We compared correct recognition rate of using LSTM and using CNN. We estimated features of both methods.

収録刊行物

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ