一种基于极坐标下分块的商标图像检索新方法

商标图像的分块检索是将图像分块后利用全局和局部图像特征来检索商标图像.针对现有的四叉树分块方法的不足,提出了一种极坐标下的分块检索方法.首先对商标图像进行归一化处理,以目标对象的最小外接圆作为目标区域;在极坐标下将图像分块,计算形状直方图;最后采用新的相似性度量方法计算图像间距离,实现商标图像的准确检索.实验证明,该方法具有良好的平移、缩放、旋转和镜像不变性,得到的检索结果能很好地符合人的视觉感受.

New Method for Retrieving Trademark Image Based on Sub-Block Under Polar Coordinate

The subblock-based image retrieval uses global and local image features to retrieve trademark image. This paper proposes a subblock-based image retrieval method under the polar coordinate system for retrieving trademark image. After normalizing the trademark image, the minimum circumscribed circle of the object is used to be the object region. The object region is divided into some blocks in the polar coordinate and the shape histograms is computed. Finally, a new image similarity measure is used to compute the distance between the images. Experiment results show that this method can keep good invariance under translation, rotation, scale and mirror, and the retrieved results match human visual perception very well.