基于随机区域扩张算法的多方向文本检测

Multi-orientation text detection based on random area grow algorithm

针对传统文本检测方法只能定位水平文本或近水平文本的问题,提出随机区域扩张算法,定位任意方向文本。使用最稳定极值区域算法对输入图片预处理,得到文本备选区域;设计3个尺度不变、方向鲁棒的特征,通过贝叶斯算法融合多特征生成概率映射,使用条件随机场模型标记文本和非文本区域;提出随机区域扩张算法,将属于相同文本行的字符连接在一起,寻找包围文本行的最小区域,定位多方向文本。实验结果表明,该算法在自然场景文本经典数据集上取得了较好的效果,能够较好定位任意方向的文本。

Tradition text detection methods focus on detecting horizontal texts or near-horizontal texts.A random area grow algorithm was designed to detect arbitrarily direction text.Maximally stable extremal region(MSER)was used to get the text candidates.Three scale invariant,orientation robust features and a Bayesian method were used to get a feature map.A conditional random field(CRF)model was used to label text region and non-text region.Random area grow algorithm was proposed to connect the texts together which belonged to the same word,and the minimum-area encasing rectangle was detected to locate the arbitrarily direction text.Experimental results show that,the proposed algorithm achieves good performance on the classic natural scene text dataset,which is able to locate arbitrarily direction text.