TY - CONF AU - Mohamed Ali Souibgui AU - Alicia Fornes AU - Y.Kessentini AU - C.Tudor A2 - ICPR PY - 2021// TI - A Few-shot Learning Approach for Historical Encoded Manuscript Recognition BT - 25th International Conference on Pattern Recognition SP - 5413 EP - 5420 N2 - Encoded (or ciphered) manuscripts are a special type of historical documents that contain encrypted text. The automatic recognition of this kind of documents is challenging because: 1) the cipher alphabet changes from one document to another, 2) there is a lack of annotated corpus for training and 3) touching symbols make the symbol segmentation difficult and complex. To overcome these difficulties, we propose a novel method for handwritten ciphers recognition based on few-shot object detection. Our method first detects all symbols of a given alphabet in a line image, and then a decoding step maps the symbol similarity scores to the final sequence of transcribed symbols. By training on synthetic data, we show that the proposed architecture is able to recognize handwritten ciphers with unseen alphabets. In addition, if few labeled pages with the same alphabet are used for fine tuning, our method surpasses existing unsupervised and supervised HTR methods for ciphers recognition. L1 - http://refbase.cvc.uab.es/files/SFK2021.pdf UR - http://dx.doi.org/10.1109/ICPR48806.2021.9413255 N1 - DAG; 600.121; 600.140 ID - Mohamed Ali Souibgui2021 ER -