Data set for Tifinagh handwriting character recognition

Abstract

The Tifinagh alphabet-IRCAM is the official alphabet of the Amazigh language widely used in North Africa [1]. It includes thirty-one basic letter and two letters each composed of a base letter followed by the sign of labialization. Normalized only in 2003 (Unicode) [2], ICRAM-Tifinagh is a young character repertoire. Which needs more work on all levels. In this context we propose a data set for handwritten Tifinagh characters composed of 1376 image; 43 Image For Each character. The dataset can be used to train a Tifinagh character recognition system, or to extract the meaning characteristics of each character.

Handwritten tifinagh character recognition using simple geometric shapes and graphs

“…To evaluate the overall performance of the proposed system, authors used two database sets of handwritten Tifinagh characters. The first database [10] is composed of 1376 images; 43 images for each character. It was created with the help of 30 people and other 13 to take in consideration inclination issues.…”

“…Table 1. comparison of recognition and error rate of the proposed system with other systems First database [10] Second database [12] Local Database Authors proposed system…”

A Semantic Approach for Mathematical Expression Retrieval

“…The dataset elements can be easily converted to MathML or Latex. In this set we have created 6925 mathematical expressions using symbols from five languages Latin, Arabic, Tifinagh [20,21], Hebrew and Japanese (Fig. 4 a, b, c, d, e).…”