A System Towards Indian Postal Automation
Abstract
In this paper, we present a system towards Indian postal automation. In the proposed system, at first, using RLSA, we decompose the image into smaller blocks. Based on the black pixel density and number of components inside a block, non-text block (postal stamp, postal seal, etc.) are detected. Using heuristic and positional information, the destination address block (DAB) is identified from text block. Next, pin-code box from DAB is detected and numerals from the pin-code box extracted. Since India is a multi-lingual multi-script country, the address part may be written in English and a local language. For the sorting of postaldocuments written in English and a local language Bangla, a two-stage MLP based classifier is discussed to recognise Bangla and English numerals. At present the accuracy of the numeral recognition module is 92,00%.