Recognition Confidence Analysis of Handwritten Chinese Character with CNN
This work addresses the need for reliable confidence metrics in optical character recognition for Chinese handwriting, though it is incremental as it applies an existing CNN method to a specific domain.
The paper tackled the problem of assessing recognition confidence for handwritten Chinese characters using CNN softmax scores, finding that this metric reliably indicates recognition reliability and can identify confusable character pairs, writing errors, and mislabeled samples across 827,685 test samples from 8,836 classes.
In this paper, we present an effective method to analyze the recognition confidence of handwritten Chinese character, based on the softmax regression score of a high performance convolutional neural networks (CNN). Through careful and thorough statistics of 827,685 testing samples that randomly selected from total 8836 different classes of Chinese characters, we find that the confidence measurement based on CNN is an useful metric to know how reliable the recognition results are. Furthermore, we find by experiments that the recognition confidence can be used to find out similar and confusable character-pairs, to check wrongly or cursively written samples, and even to discover and correct mis-labelled samples. Many interesting observations and statistics are given and analyzed in this study.