多语言自然场景文本检测算法研究
Research on Multilingual Natural Scene Text Detection Algorithm
AI总结：
针对自然场景多语言文本检测精度低的问题，提出结合SFM Swin Transformer、AS-HRFPN和全局语义分割分支的多语言文本检测算法，构建真实数据集，F-measure达85.02%，并验证了跨数据集通用性。
摘要：
自然场景文本检测是计算机视觉中的一个重大挑战，在多语言、多样化和复杂的文本场景中具有巨大的应用潜力。为了解决自然场景中多语言文本检测准确率低、难度大的问题，我们提出了一种多语言文本检测模型。针对包含多种字符集和各种字体风格的多语言文本图像带来的挑战，我们引入了SFM Swin Transformer特征提取网络，以增强模型在检测不同语言字符和字体时的鲁棒性。为了处理自然场景文本图像中文本尺度的巨大变化和复杂排列，我们通过结合Adaptive Spatial Feature Fusion模块和Spatial Pyramid Pooling模块，提出了AS-HRFPN特征融合网络。该特征融合网络的改进增强了模型检测文本尺寸和方向的能力。应对多语言场景文本图像中多样的背景和字体变化是现有方法面临的一项挑战。有限的局部感受野阻碍了检测性能。为了克服这一点，我们提出了Global Semantic Segmentation Branch，提取并保留全局特征以实现更有效的文本检测，满足了对全面信息的需求。在本研究中，我们收集并构建了一个真实世界的多语言自然场景文本图像数据集，并进行了全面的实验和分析。实验结果表明，所提出的算法达到了85.02%的F-measure，比基线模型高出4.71%。我们还在MSRA-TD500、ICDAR2017MLT和ICDAR15数据集上进行了广泛的跨数据集验证，以验证我们方法的通用性。代码和数据集可在https://github.com/wangmelon/CEMLT获取。
英文摘要：
Natural scene text detection is a significant challenge in computer vision, with tremendous potential applications in multilingual, diverse, and complex text scenarios. We propose a multilingual text detection model to address the issues of low accuracy and high difficulty in detecting multilingual text in natural scenes. In response to the challenges posed by multilingual text images with multiple character sets and various font styles, we introduce the SFM Swin Transformer feature extraction network to enhance the model's robustness in detecting characters and fonts across different languages. Dealing with the considerable variation in text scales and complex arrangements in natural scene text images, we present the AS-HRFPN feature fusion network by incorporating an Adaptive Spatial Feature Fusion module and a Spatial Pyramid Pooling module. The feature fusion network improvements enhance the model's ability to detect text sizes and orientations. Addressing diverse backgrounds and font variations in multilingual scene text images is a challenge for existing methods. Limited local receptive fields hinder detection performance. To overcome this, we propose a Global Semantic Segmentation Branch, extracting and preserving global features for more effective text detection, aligning with the need for comprehensive information. In this study, we collected and built a real-world multilingual natural scene text image dataset and conducted comprehensive experiments and analyses. The experimental results demonstrate that the proposed algorithm achieves an F-measure of 85.02\%, which is 4.71\% higher than the baseline model. We also conducted extensive cross-dataset validation on MSRA-TD500, ICDAR2017MLT, and ICDAR2015 datasets to verify the generality of our approach. The code and dataset can be found at https://github.com/wangmelon/CEMLT.
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。
