VML-MOC: Segmenting a multiply oriented and curved handwritten text lines dataset
This addresses the challenge of processing complex handwritten documents with multiply oriented and curved text lines, which is an incremental improvement over single-oriented methods.
The paper tackles the problem of segmenting handwritten text lines that appear at various orientations (0-180 degrees) and curvilinear forms in document margins, achieving a mean pixel Intersection over Union score of 80.96% on their test dataset using a multi-oriented Gaussian-based method.
This paper publishes a natural and very complicated dataset of handwritten documents with multiply oriented and curved text lines, namely VML-MOC dataset. These text lines were written as remarks on the page margins by different writers over the years. They appear at different locations within the orientations that range between 0 and 180 or as curvilinear forms. We evaluate a multi-oriented Gaussian based method to segment these handwritten text lines that are skewed or curved in any orientation. It achieves a mean pixel Intersection over Union score of 80.96% on the test documents. The results are compared with the results of a single-oriented Gaussian based text line segmentation method.