The IUPR Dataset of Camera-Captured Document Images

Major challenges in camera-base document analysis are dealing with uneven shadows, high degree of curl and perspective distortions. In CBDAR 2007, we introduced the first dataset (DFKI-I) of camera-captured document images in conjunction with a page dewarping contest. One of the main limitations of this dataset is that it contains images only from technical books with simple layouts and moderate curl/skew. Moreover, it does not contain information about camera’s specifications and settings, imaging environment, and document contents. This kind of information would be more helpful for understanding the results of the experimental evaluation of camera-based document image processing (binarization, page segmentation, dewarping, etc.). In this paper, we introduce a new dataset (the IUPR dataset) of camera-captured document images. As compared to the previous dataset, the new dataset contains images from different varieties of technical and nontechnical books with more challenging problems, like different types of layouts, large variety of curl, wide range of perspective distortions, and high to low resolutions. Additionally, the document images in the new dataset are provided with detailed information about thickness of books, imaging environment and camera’s viewing angle and its internal settings. The new dataset will help research community to develop robust cameracaptured document processing algorithms in order to solve the challenging problems in the dataset and to compare different methods on a common ground. Keywords-Dataset, Camera-Captured Document Processing, Performance Evaluation