不依赖旋转校正的在线手写字符识别，准确率超94%。
Rotation-free Online Handwritten Character Recognition Using Linear Recurrent Units
- 用滑动窗口路径签名捕捉字形局部结构，结合轻量线性循环单元分类
- 在±180°随机旋转下，中文部首识别率达94.33%，全模型平均超96%
- 适合对实时性和鲁棒性要求高的手写输入系统应用
在线手写字符识别利用笔画顺序与动态特征，通常比离线识别更准确、更鲁棒。但实际应用中，旋转变形会破坏笔画的空间布局，显著降低识别精度。提取旋转不变特征仍是开放难题。本文采用滑动窗口路径签名（SW-PS）捕获字符局部结构特征，并引入轻量级线性循环单元（LRU）作为分类器。LRU结合了循环神经网络（RNN）的快速增量处理能力与状态空间模型（SSM）的高效并行训练优势，可靠建模动态笔画特性。我们在CASIA-OLHWDB1.1数据集的三个子集（数字、英文大写字母、中文部首）上进行了带随机旋转角±180°的识别实验。集成学习后，准确率分别达到99.62%、96.67%和94.33%。实验表明，所提SW-PS+LRU框架在收敛速度与测试准确率上均持续优于对比模型。
原文摘要 · Abstract (English)
Online handwritten character recognition leverages stroke order and dynamic features, which generally provide higher accuracy and robustness compared with offline recognition. However, in practical applications, rotational deformations can disrupt the spatial layout of strokes, substantially reducing recognition accuracy. Extracting rotation-invariant features therefore remains a challenging open problem. In this work, we employ the Sliding Window Path Signature (SW-PS) to capture local structural features of characters, and introduce the lightweight Linear Recurrent Units (LRU) as the classifier. The LRU combine the fast incremental processing capability of recurrent neural networks (RNN) with the efficient parallel training of state space models (SSM), while reliably modelling dynamic stroke characteristics. We conducted recognition experiments with random rotation angle up to $\pm 180^{\circ}$ on three subsets of the CASIA-OLHWDB1.1 dataset: digits, English upper letters, and Chinese radicals. The accuracies achieved after ensemble learning were $99.62\%$, $96.67\%$, and $94.33\%$, respectively. Experimental results demonstrate that the proposed SW-PS+LRU framework consistently surpasses competing models in both convergence speed and test accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。