Segmentation of handwritten signature images using the statistics of directional data

/in , , /by
Segmentation of handwritten signature images using the statistics of directional data

Sabourin, Robert and Plamondon, Rejean

Proceedings – International Conference on Pattern Recognition 1988

Abstract : A preliminary design is given for a general image-understanding system for the extraction of a signature representation. A novel version of an algorithm for centroidal-linkage region-growing with merging, using the statistics of directional data is give. It permits the extraction of textured regions characterized by local uniformity in the orientation of the gradient.

You might also like
3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study
Texture CNN for histopathological image classification
Robust spatio-temporal registration of 4D cardiac ultrasound sequences
Using adaptive trackers for video face recognition from a single sample per person
Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth Boxes
Enhanced Single-Shot Detector for Small Object Detection in Remote Sensing Images
Sex in Marriage: Love-Giving, Live-Giving
An automated initialization system for robust model-based segmentation of lungs in CT data