Category: Uncategorized

Since documents often are somewhat degraded it is important to be able to efficiently remove the disturbing background from the text. The next step would be to binarise the segmented text, but in our wordspotter we prefer to work on the background removed text. We have published two papers dealing with these problems. Automatic Document … Continue reading Background Removal and Binarisation

We developed a segmentation free word spotter, which means that each word do not have to be extracted from the text. Instead a sliding window (cyan box) is used to traverse the document.  Key point matching was performed on four sets of different key points, using a descriptor based on the Fourier transform followed by … Continue reading Segmentation-free Word Spotting

It is quite a challenging task to make a prefect bounding box for a word by hand. This paper deals with this problem, but the algorithm can also be used in the word spotter for finding a perfectly fitting box of the found word. The image shows how the user has marked the red box, … Continue reading User Annotation and Bounding Text Boxes

The idea proposed in this paper is to use a log polar sampling scheme followed by a FFT in order to obtain a rotation and to some degree scale invariant feature descriptor. The feature vector will be rather short since just the most discriminative part of the FFT is used. A short feature vector for … Continue reading The Log-Polar Magnitude Feature Descriptor

This paper propose an efficient way to combine different spline types for computing first and second order derivatives (please see my video presentation). The following formula is derived, which shows that a spline surface can be rewritten as an outer product and a convolution Note that this equation is differentiable and this fact is used … Continue reading Image Derivatives