基于视觉图形轮廓显著化的目标对象检测方法

摘要

Object detection method is a key technology in digital image processing.In the paper we present an object detection algorithm for visual significant image,which detects the object in significant image through using enhanced image area description and maximised regional differences description.The proposed method makes smoothing pre-process on the image,which greatly reduces the complexity of the algorithm.Experimental results show that the method can be successfully applied to the detection of significant object in visual significant image,and its implementation efficiency is high,the proposed method can be applied to image segmentation,tracking and positioning.%目标检测是数字图像处理中的一项关键技术。提出针对视觉显著性图像中的目标检测算法，通过使用增强图像区域描述，区域差异性最大化描述来检测显著性图像中的目标。所提出的方法对图像进行平滑预处理，大大减少了算法的复杂度。实验结果表明，该方法能够成功用于对视觉显著性图像中的显著目标进行检测，并且其执行效率很高。所提出的方法可以应用于图像的分割、追踪与定位。