一种基于图像分层的标牌压印字符分割方法

A novel segmentation method for characters pressed on label based on layered images

由于标牌图像的低质量特点,经典的图像分割算法无法达到理想的分割效果。为此,本文提出了一种适用于标牌图像特点的分割算法。首先根据标牌图像灰度分布的特点将图像从最暗层到最亮层进行分层;对最暗层图像进行自适应二值化可得到标牌图像中的印刷文本图像;继而,基于连通域对印刷文本图像进行分析确定其所在区域;最后将确定的印刷字符区域从原始图像中去除,可得到目标区域,即仅含有压印凹凸字符区域的目标图像。经过对大量标牌图像进行分割实验证明,本算法是一种适用于标牌压印凹凸字符分割的有效算法。

The traditional segmentation methods can not segment the characters successfully. A novel segmentation method to separate the pressed characters from the Label image is proposed. The algorithm classifies the Label image into several planes：from the darkest to the brightest. The printed text on the label is extracted from the adaptively binary image of the darkest plane. Then,the block of printed text is defined based on connect components analysis. Finally, by removing the block of the printed text from the original image,the pressed characters are picked up successfully. Experiments are carried out with a large number of label images. Experiment results show that the proposed segmentation method can be reliably used in the label images.