为了进一步提升基于卷积神经网络的文本检测器的检测精度,首先,用具有分散注意力机制的特征提取网络替代原始算法的主干网络,如残差网络,以促进通道间的信息交互,最大化地激活文本特征。其次,在原始特征金字塔网络的基础上增加自底向上的路径,以减少文本特征信息的损耗。实验结果表明,本算法在CTW1500、Total-Text曲线数据集上的平均精度分别为78.7%、79.0%,在多方向数据集和多语言数据集的平均精度分别为82.7%、79.3%,相比其他算法均有一定的提升。

In order to further improve the detection accuracy of the text detector based on convolutional neural networks, first, feature extraction network with split-attention mechanism is used to replace the backbone network of the original algorithm, such as residual network, to promote information exchange between channels and maximize the activation of text features. Second, based on the original feature pyramid network, a bottom-up path is added to reduce the loss of text feature information. Experimental results show that the average accuracy of the algorithm is 78.7% and 79.0% on CTW1500 and Total-Text curve data sets, and 82.7% and 79.3% in multi-directional and multi-language data sets, respectively, which is better than other algorithms.