IEEE Trans Image Process. 2016 Dec;25(12):5622-5634. doi: 10.1109/TIP.2016.2607426. Epub 2016 Sep 8.
Text recognition in video/natural scene images has gained significant attention in the field of image processing in many computer vision applications, which is much more challenging than recognition in plain background images. In this paper, we aim to restore complete character contours in video/scene images from gray values, in contrast to the conventional techniques that consider edge images/binary information as inputs for text detection and recognition. We explore and utilize the strengths of zero crossing points given by the Laplacian to identify stroke candidate pixels (SPC). For each SPC pair, we propose new symmetry features based on gradient magnitude and Fourier phase angles to identify probable stroke candidate pairs (PSCP). The same symmetry properties are proposed at the PSCP level to choose seed stroke candidate pairs (SSCP). Finally, an iterative algorithm is proposed for SSCP to restore complete character contours. Experimental results on benchmark databases, namely, the ICDAR family of video and natural scenes, Street View Data, and MSRA data sets, show that the proposed technique outperforms the existing techniques in terms of both quality measures and recognition rate. We also show that character contour restoration is effective for text detection in video and natural scene images.
视频/自然场景图像中的文本识别在许多计算机视觉应用中的图像处理领域引起了广泛关注，这比在纯色背景图像中的识别更具挑战性。在本文中，我们的目标是从灰度值恢复视频/场景图像中的完整字符轮廓，与传统技术不同，传统技术将边缘图像/二进制信息作为文本检测和识别的输入。我们探索并利用拉普拉斯算子给出的过零点的优势来识别笔画候选像素 (SPC)。对于每个 SPC 对，我们提出了新的基于梯度幅度和傅里叶相位角的对称特征来识别可能的笔画候选对 (PSCP)。在 PSCP 级别提出了相同的对称特性来选择种子笔画候选对 (SSCP)。最后，提出了一种用于 SSCP 的迭代算法来恢复完整的字符轮廓。在基准数据库（即 ICDAR 系列视频和自然场景、街景数据和 MSRA 数据集）上的实验结果表明，该技术在质量度量和识别率方面均优于现有技术。我们还表明，字符轮廓恢复对于视频和自然场景图像中的文本检测是有效的。
