各種金融保險和投資應用網站都要求客戶上傳身份證明文件，例如財力證明和汽車行照，以驗證其身份。然而，人工驗證這些文件的成本很高。因此，自動文件識別的需求越來越大。在本研究中，我們提出一個穩健有效車輛行照辨識系統。本研究內的文字偵測分為兩個階段。在第一階段，矯正網路矯正了經常出現在未掃描行照中可能出現的變形。在第二階段，定位網路準確定位每個行照內欄位並切割成欄位影像。隨後欄位影像由商業文字識別軟體辨識欄位中的文字。由於車輛行照內資料的敏感性，很難收集到足夠的訓練資料進行模型訓練。因此，在進行模型訓練前，我們合成了假行照影像數據集，並且進行預處理以避免過擬合。此外，在進行文本識別之前，還利用降噪網路消除行照背景雜訊，消除文本的邊界，使模糊的文本更加清晰。我們的方法只需要客戶上傳一張行照照片，即使照片拍得不好，行照內欄位文字也能被識別。 最後，通過真實數據集對本系統的性能進行了評估，辨識系統準確率接近90％。 ;upload identity documents, such as financial certificates and vehicle licenses, to verify their identities. Manual verification of these documents is costly. As a result, there is an increasing demand for automatic document recognition. This study proposes a robust method for pre-processing vehicle license before text recognition. The proposed method has two stages. In the first stage, the possible distortion that often appears in non-scanned documents is repaired. In the second stage, each data field is accurately located. The subsequent captured fields are then processed by commercial text recognition model. As the vehicle license is sensitive, it is difficult to collect enough entries for model training. Consequently, the fake vehicle licenses are synthesized and pre-processed to avoid the overfitting when used for model training. Additionally, before text recognition, an encoder is applied to reduce the background noise, remove the border crossing over text, and make the blurred text clearer. Our approach only requires the customer to upload a photo of the vehicle license and the text can be recognized even when the photo is taken poorly. The performance of the proposed method is evaluated through true dataset, and the accuracy is close to 0.9.
