Word segmentation in handwritten Korean text lines based on gap clustering techniques

Text line and word segmentation of handwritten documents

“…After comparing this metric with some of the metrics of [22] concluded that the convex hull-based metric performs better than the other ones. Kim et al [24] investigated the problem of word segmentation in handwritten Korean text lines. To this end, they used three well-known metrics in their experiments: the bounding box distance, the run-length/Euclidean distance and the convex hullbased distance.…”

Contour Vs Non-Contour based Word Segmentation from Handwritten Text Lines: an Experimental Analysis

“…Hence, punctuation is a big problem and therefore it causes many errors in accurate word segmentation. Many preprocessing techniques are employed in this regard [1,3,4,10,11,13]. Authors have proposed new technique to detect punctuations as well.…”

“…The words segmentation approaches in printed/handwritten text lines are usually based on various heuristics and assumption that the gaps between words (inter-word gap) are larger than those inside the words (intra-word gap) [2][3][4][5][6][7][8]. Words extraction from handwritten text lines usually involves calculation of threshold for inter-word gap.…”

Segmentation of the Date in Entries of Historical Church Registers

“…Nonetheless, the examined scripts show straight text lines and well separated words. If the script, however, is characterised by gaps of different sizes, methods specialised on differentiating between inter-character gaps and inter-word gaps have been found successfully [5,4]. In old church registers, connections between adjacent words may occur.…”