【摘要】 提出一种红外图像阈值分割方法。为了减少计算量,首先给出一种提取包含待分割目标的感兴趣区域方法;然后利用Bezier曲线法平滑感兴趣区域直方图的噪声,利用所提出的判据来确定最佳分割阈值并进行分割。最后结合上述分割结果和目标的边缘信息得到最终的分割效果。实验结果表明,提出的方法能快速有效的将红外目标从复杂的背景中分割出来。更多还原

【Abstract】 A new approach to segment man-made target from infrared image is given based on threshold method. In order to reduce computation cost, a single method to select region of interest(ROI) is put forward so as to extract a piece of region, which contains a target to be segmented. The histogram of ROI is smoothed by Bezier curve method to restrain noise. The ROI is segmented based on threshold method and a new criterion proposed. Final segmentation result is obtained by combining the segmentation result above with edge information of target. Experimental results show that a target can be segmented effectively from complex background in infrared image by the new approach.更多还原