Segmenting printed text and handwritten annotation by Spectral Partitioning
Citations
1 citations
Cites methods from "Segmenting printed text and handwri..."
...The features used to distinguish between them have been adopted from [11] as: field component patch size, foreground density, average stroke width, horizontal and vertical density difference, maximum horizontal and vertical runlength and standard deviation of horizontal and vertical projection of a patch....
[...]
References
9,141 citations
9,043 citations
"Segmenting printed text and handwri..." refers methods in this paper
...The Spectral approach relies on the Eigen structure of a similarity matrix to partition points into disjoint clusters with points in the same cluster having high similarity and points in different clusters having low similarity [12]....
[...]
107 citations
"Segmenting printed text and handwri..." refers background in this paper
...Only few systems are able to handle multi-oriented handwritten annotations [1] [3] [7] in a real environment....
[...]
65 citations
"Segmenting printed text and handwri..." refers background or methods in this paper
...Most of these systems extract annotations in controlled scenario [4] [5] [6] [2]....
[...]
...It commenced by the contribution of Kuhnke et al [4] for printed and hand-written character segmentation using directional and symmetrical features into a neural network....
[...]
48 citations
"Segmenting printed text and handwri..." refers background or methods in this paper
...Most of these systems extract annotations in controlled scenario [4] [5] [6] [2]....
[...]
...Pal and Chaudhuri [5] segmented handwritten and printed text lines of Bangla and Devnagari using a tree-based classification approach....
[...]