| 曹泽卫,欧 阳,林冬婷,李柏林.基于 CNNs 识别反馈的点阵字符检测方法[J].电子测量与仪器学报,2020,34(8):159-166 |
| 基于 CNNs 识别反馈的点阵字符检测方法 |
| Dot matrix character detection method based on CNNs recognition feedback |
| |
| DOI： |
| 中文关键词: 多尺度滑动窗口 卷积神经网络 滑动翻转窗口 反馈定位 点阵字符识别 |
| 英文关键词:multi-scale sliding window convolutional neural networks sliding and flip window feedback and positioning dot matrix
character recognition |
| 基金项目: |
|
|
|
|
| 摘要点击次数: 150 |
| 全文下载次数: 317 |
| 中文摘要: |
| 针对点阵字符因错误分割导致识别准确率较低的问题,提出了一种基于卷积神经网络(CNNs)识别反馈的点阵字符检
测方法。 首先采用多尺度窗口获取多个候选区域并建立 CNNs 对其进行识别,利用投票机制对多个识别结果进行综合决策,然
后根据决策结果反向定位点阵字符并完成字符分割,最后提出一种滑动翻转窗口对所有字符进行分割与识别。 实验结果表明,
该方法在点阵字符的定位准确率和识别率方面都优于传统字符识别方法,分别达到了 97. 53%和 97. 50%。 |
| 英文摘要: |
| The recognition accuracy of dot matrix characters is low due to error segmentation, this paper proposes a dot matrix character
detection method based on convolutional neural network (CNNs) recognition feedback. Firstly, multi-scale windows are used to acquire
multiple candidate regions and CNNs are established to identify them. The voting mechanism is used to make comprehensive decisions on
multiple recognition results, and then the lattice characters are reversed according to the decision result and the character segmentation is
completed. Finally, a sliding flip window is proposed to segment and identify all characters. The experimental results show that the
proposed method outperforms the traditional character recognition method in the segmentation accuracy and recognition rate of dot matrix
characters, reaching 97. 53% and 97. 50% respectively. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
