Nowadays, the capabilities of smartphones rise, they have become an important part of people's lives. It can do many tasks and the advantage is that it is often with us. There are many unsolved problems in document digitalization with smartphones, such as noisy images, blurring, non-uniform light and geometric transforms. The presented methods have tried to fix one or more problems and make it easier or faster to find the document in the image. However, they cannot cover difficult situations such as complicated background. In this paper, we present a new dataset covers almost all the scenarios that may exist on document images that were taken by a smartphone. The collection includes 1111 images. We tested algorithms for finding the documents corners in our dataset and the results also provided. The results indicate that there are still situations that these algorithms fail and it needs more research.
Software And Hardware
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL