Presentation of folded documents is not an uncommon case in modern society. Digitizing such documents by capturing them with a smartphone camera can be tricky since a crease can divide the document contents into separate planes. To unfold the document, one could hold the edges potentially obscuring it in a captured image. While there are many geometrical rectification methods, they were usually developed for arbitrary bends and folds. We consider such algorithms and propose a novel approach Unfolder developed specifically for images of documents with a crease from folding in half. Unfolder is robust to projective distortions of the document image and does not fragment the image in the vicinity of a crease after rectification. A new Folded Document Images dataset was created to investigate the rectification accuracy of folded (2, 3, 4, and 8 folds) documents. The dataset includes 1600 images captured when document placed on a table and when held in hand. The Unfolder algorithm allowed for a recognition error rate of 0.33, which is better than the advanced neural network methods DocTr (0.44) and DewarpNet (0.57). The average runtime for Unfolder was only 0.25 s/image on an iPhone XR.

翻译：在现代社会中，展示折叠文件并非罕见情况。使用智能手机摄像头拍摄此类文件并将其数字化可能具有挑战性，因为折痕会将文件内容分割到不同平面。为了展平文件，人们可能需握住边缘，但这会导致其在拍摄图像中被遮挡。尽管存在多种几何矫正方法，但它们通常针对任意弯曲和折叠而设计。我们考察了这类算法，并提出了一种专门针对对折文件图像的新方法Unfolder。Unfolder对文件图像的投影畸变具有鲁棒性，且在矫正后不会在折痕附近造成图像碎片化。为研究折叠文件（2、3、4和8折）的矫正精度，我们创建了一个新的折叠文档图像数据集。该数据集包含1600张图像，分别拍摄于文件置于桌面和手持时。Unfolder算法的识别错误率为0.33，优于先进的神经网络方法DocTr（0.44）和DewarpNet（0.57）。在iPhone XR上，Unfolder的平均运行时间仅为0.25秒/张。