| 摘要: | 隨著時代的發展，交換信息的方式也在不斷的變化，人與人的交流越來
越方便。人們從最初的書信交流轉換為使用手機，平板電腦，計算機和其
他工具。網際網路不僅改變了人們之間的交流方式，也改變了傳統的教育
方式。不限時間地點的在線學習課程越來越受歡迎，許多數位學習平台也
大量出現。人們開始使用手機和平板電腦進行學習，並且智能筆開始被廣
泛使用，學習者利用智能筆在電子設備上做筆記 或紀錄知識。由於越來越多的用戶放棄了過往的紙筆作業，轉而使用智慧筆進行書寫。因此，手寫辨識這項技術變得越來越重要，對於多語言國家、地區，使用多種語言、文字的手寫文件數量也在逐步的增加。目前市面上也有許多成熟的手寫識別系統，但他們卻也有很大的侷限性。在單一語種的辨識具有較高的準確性，但對於多語種的文本的辨識，依然還有很大的改善空間。圖像中的多腳本識別是基於內容的圖像檢索和多語言系統開發的重要方向。在多語言文檔中，需要先進行文字區域偵測，並識別語言種類，找到用同一語言書寫的文本部分，再將其放入特定語言的識別系統。為了識別越來越多的語言、腳本的手寫文檔，並允許用戶在書寫文件時不受限制。因此本計畫中，我們將致力於建立一個可以正確識別多種語言手寫文本的系統。;With the development of the times, the way of exchanging information is constantly changing, and the communication between people is becoming more and more convenient. People have transformed from the initial communication of letters to the use of mobile phones, tablets, computers and other tools. The Internet has not only changed the way people communicate, but also the traditional way of education. Unlimited online learning courses are becoming
more and more popular, and many digital learning platforms are also appearing in large numbers. People began to use mobile phones and tablet computers for learning, and smart pens began to be widely used. Learners use smart pens to
take notes or record knowledge on electronic devices. As more and more users abandon their past paper-and-pen assignments, and instead use smart pens for writing. Therefore, the handwriting recognition technology has become more and more important. For multilingual countries and regions, the number of handwritten documents in multiple languages and scripts is gradually increasing.
There are many mature handwriting recognition systems on the market, but they also have great limitations. The recognition in a single language has high accuracy, but there is still much room for improvement in the recognition of multilingual texts. Multi-script recognition in images is an important direction
for content-based image retrieval and multi-language system development. In a multi-language document, it is necessary to first detect the text area and identify the language type, find the text part written in the same language, and then put it into the recognition system of the specific language. In order to recognize more
and more handwritten documents in languages and scripts, and allow users to be unrestricted when writing documents. Therefore, in this project, we will strive to establish a system that can correctly recognize handwritten text in multiple languages. |
