Reliable and generic methods for skew detection are a necessity for any large-scale digitization projects. As one of the first processing steps, skew detection and correction has...
Iuliu Vasile Konya, Stefan Eickeler, Christoph Sei...
In document image understanding, public datasets with ground-truth are an important part of scientific work. They are not only helpful for developing new methods, but also provid...
Thomas Strecker, Joost van Beusekom, Sahin Albayra...
A fast rate-distortion analytical framework for the PSNR-based optimization of JPEG baseline compression on color images is proposed in this paper. The analysis is conducted in th...
Digital images are increasingly being used as steganographic covers for secret communication. The Least Significant Bit (LSB) encoding is one of the most widely used methods for e...
We describe an unsupervised learning algorithm for extracting sparse and locally shift-invariant features. We also devise a principled procedure for learning hierarchies of invari...