Skip to main content
Fig. 5 | SpringerPlus

Fig. 5

From: Urdu Nasta’liq text recognition using implicit segmentation based on multi-dimensional long short term memory neural networks

Fig. 5

Assignment of labels for creating a single class for various shapes of a basic character. The characters 1 and 2 are example of non-joiner characters having two shapes which split the word into sub-word/ligatures. The characters 3 and 4 are examples of joiner characters having more than 2 shapes which join its preceding or proceeding character. The shape/glyph of a character with content in ligatures is shown in the last column

Back to article page