Automatic Borders Detection of Camera Document Images

When capturing a document using a digital camera, the resulting document image is often framed by a noisy black border or includes noisy text regions from neighbouring pages. In this paper, we present a novel technique for enhancing the document images captured by a digital camera by automatically detecting the document borders and cutting out noisy black borders as well as noisy text regions appearing from neighbouring pages. Our methodology is based on projection profiles combined with a connected component labelling process. Signal cross-correlation is also used in order to verify the detected noisy text areas. Experimental results on several camera document images, mainly historical, documents indicate the effectiveness of the proposed technique.