arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.07905cs.CVcs.LG
收藏

孟加拉文手写体数字识别与生成

Bangla Handwritten Digit Recognition and Generation

Jahangirnagar University(贾汉吉尔纳加尔大学)

Md Fahim Sikder

摘要:

手写体数字识别是模式识别领域的经典课题之一,并且由于最近计算资源的广泛可用性而取得了巨大的进步。对英文、阿拉伯文、中文、日文手写体的研究已经相当丰富。在孟加拉语方面也做了一些工作,但还有发展的空间。从这个角度出发,本文实现了一种架构,该架构在BHAND数据集上实现了99.44%的验证准确率,并且优于Alexnet和Inception V3架构。除了数字识别之外,数字生成是最近引起研究人员注意的另一个领域,尽管在这一领域特别是在孟加拉语上做的工作并不多。本文将半监督生成对抗网络(SGAN)应用于孟加拉语手写体数字的生成,并成功地生成了孟加拉语数字。

英文摘要:

Handwritten digit or numeral recognition is one of the classical issues in the area of pattern recognition and has seen tremendous advancement because of the recent wide availability of computing resources. Plentiful works have already done on English, Arabic, Chinese, Japanese handwritten script. Some work on Bangla also have been done but there is space for development. From that angle, in this paper, an architecture has been implemented which achieved the validation accuracy of 99.44% on BHAND dataset and outperforms Alexnet and Inception V3 architecture. Beside digit recognition, digit generation is another field which has recently caught the attention of the researchers though not many works have been done in this field especially on Bangla. In this paper, a Semi-Supervised Generative Adversarial Network or SGAN has been applied to generate Bangla handwritten numerals and it successfully generated Bangla digits.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑