利用轮廓分解和局部描述的二值图像检索

Binary Image Retrieval Using Contour Decomposition and Description

提出一种面向二值图像检索的形状分解和局部描述方法.对二值图像进行物体轮廓的提取,采用特定的方法对轮廓进行分解,得到轮廓的参考点集.利用轮廓的法线求取每一个参考点的对应弧线段,计算弧线段的特征并作为对应参考点的特征向量,从而原图像就被表示为特征空间中的特征点集.最后,采用点匹配的方法来计算图像之间的距离,实现二值图像的检索.实验结果表明,与目前已有的方法相比该方法具有较高的检索精度.

Proposed a strategy of shape decomposition and local description oriented to retrieving binary images. Firstly, the contour of object is extracted from binary image and decomposed by special method, and then the set of reference points are acquired. For each reference point, the curve to which the point corresponds is gained by the use of normal of the contour. After that, the feature of the curve is computed and is treated as the eigenvector of the reference point. As a result, the image can be represented by a set of feature vectors in feature space. Finally, the distance between two images can be calculated by the method of points matching and the retrieval of binary images can be implemented. Experiments show that this method has higher retrieval precision, compared with some classical methods.