Automatic detection and recognition of signs from natural scenes
Automatic detection and recognition of signs from natural scenes
复制标题
DOI：
10.1109/tip.2003.819223
复制
发表时间：
2004-01-01
影响因子：
10.6
通讯作者：
Waibel, A
中科院分区：
文献类型：
--
作者：
Chen, XL;Yang, J;Waibel, A
在本文中，我们提出了一种自然场景中迹象的自动检测和识别方法，以及其应用于标志翻译任务的方法。所提出的方法嵌入了多个解决方案和多尺度边缘检测，自适应搜索，颜色分析和仿射矫正中，以用于符号检测的层次结构框架，每个阶段都有不同的重点以处理不同尺寸，方向，颜色分布和背景的文本。我们使用仿射矫正来恢复由不适当的相机视角引起的文本区域的变形。该过程可以显着提高文本检测率和光学特征识别（OCR）精度。我们直接从强度图像中提取特征，而不是将二进制信息用于OCR。我们提出了一种局部强度归一化方法，以有效处理照明变化，然后进行Gabor变换以获得局部特征，最后是线性判别分析（LDA）方法以进行特征选择。我们已经在开发中文符号翻译系统中采用了这种方法，该系统可以自动检测并识别中文标志是相机的输入，并将公认的文本转换为英语。
In this paper, we present an approach to automatic detection and recognition of signs from natural scenes, and its application to a sign translation task. The proposed approach embeds multiresolution and multiscale edge detection, adaptive searching, color analysis, and affine rectification in a hierarchical framework for sign detection, with,different emphases at each phase to handle the text in different sizes, orientations, color distributions and backgrounds. We use affine rectification to recover deformation of the text regions caused by an inappropriate camera view angle. The procedure can significantly improve text detection rate and optical character recognition (OCR) accuracy. Instead of using binary information for OCR, we extract features from an intensity image directly. We propose a local intensity normalization method to effectively handle lighting variations, followed by a Gabor transform to obtain local features, and finally a linear discriminant analysis (LDA) method for feature selection. We have applied the approach in developing a Chinese sign translation system, which can automatically detect and recognize Chinese signs as input from a camera, and translate the recognized text into English.