Competition Task
Given a set of Indic word images, the task of the competition is to recognize each and every word image of this set. For example
Evaluation Metrics
Two popular evaluation metrics such as Character Recognition Rate (CRR) (alternatively Character Error Rate, CER) and Word Recognition Rate (WRR) (alternatively Word Error Rate, WER) are used to evaluate the performance of recognizers. Error Rate (ER) is defined as
$$ { ER= \frac{S+D+I}{N} (1) } $$
Where S indicates number of substitutions, D indicates number of deletions, I indicates number of insertions and N number of instances in reference text. In case of CER, Eq. (1) operates on character level and in case of WER, Eq. (1) operates on word level. Recognition Rate (RR) is defined as
$$ { RR = 1-ER (2) } $$
In case of CRR, Eq. (2) operates on character level and in case of WRR, Eq. (2) operates on word level
Input: Set of word images
Output: Text file (bengali_result.txt) containing image names and corresponding predicted text, separated by tab. For example
