FAIR-Net:一个模糊的自动编码器和可解释的基于规则的网络,用于古代中国的字符识别
Yanling Ge1, Yunmeng Zhang2, Seok-Beom Roh3
1School of Information Science and Engineering, Linyi University, Linyi 276000, China.
Sensors (Basel, Switzerland)
|September 27, 2025
概括
新型混合人工智能FAIR-Net通过结合深度自动编码器和模糊逻辑,准确地识别退化的古代中国文字. 这种可解释的系统增强了历史文档数字化和保存工作.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 数字人文学科 数字人文学科
背景情况:
- 古代中国文字面临着退化,阻碍了手动转录和传统的OCR.
- 由于侵蚀,损坏和风格变化,现有的OCR方法与历史文本作斗争.
研究的目的:
- 开发一种可解释和高效的AI模型,用于识别退化的古汉字符.
- 改进中国历史文献的数字化和保存.
主要方法:
- 提出了FAIR-Net,这是一个混合架构,将无监督的深度自动编码器合并为特征学习与模糊的基于规则的分类.
- 使用模糊C-Means (FCM) 进行软集群和代重量最小方程估计 (IRLSE) 与Softmax进行透明预测.
- 限制模型重量作为线性映射以确保可解释性.
主要成果:
- 在基准数据集上获得了97.91%的准确性,显著超过了具有高统计意义的基线CNN.
- 证明了处理效率的提高,与其他模型相比,推断时间减少了高达98.9%.
- 在大型古汉字数据集 (83.25%准确度) 上展示了强度,并通过模糊规则可视化证实了通过模糊规则可视化来增强对字符模糊性的弹性.
结论:
- FAIR-Net为古代中国字符识别提供了一个实用,可解释和高效的解决方案.
- 该模型的透明度和性能有助于数字化和保存宝贵的历史遗迹.
- FAIR-Net的混合方法促进了AI在历史语言学和文化遗产保护方面的应用.
相关概念视频
Design Example
The innovation of touch-tone telephony revolutionized the telecommunications industry by replacing the traditional rotary dial with a dual-tone multi-frequency (DTMF) signaling system. This system uses a matrix-style keypad with buttons arranged in four rows and three columns, creating 12 distinct signals each assigned to a pair of frequencies. Each button press results in a simultaneous generation of two sinusoidal tones – one from a low-frequency group (697 to 941 Hz) and one from a...
Encoding
Information enters the brain through encoding, which is the input of information into the memory system. Once sensory information is received from the environment, the brain labels or codes it. The information is then organized with similar information and connected to existing concepts. Encoding occurs through automatic processing and effortful processing.
Automatic processing involves the encoding of details like time, space, frequency, and the meaning of words, usually done without conscious...
Automatic processing involves the encoding of details like time, space, frequency, and the meaning of words, usually done without conscious...


