CAJ | 학술논문

一些基于熵的阈值图像分割技术考虑了空间信息，从而能够提高阈值分割的性能，但是仍然不能较好地区分边缘和噪声。尽管灰度-梯度（gray-level & gradient-magnitude，GLGM）熵算法能有效地解决以上问题，但是针对多目标和复杂图像却不能有效地分割。为此，提出了一种基于遗传算法（genetic algorithm，GA）的GLGM熵多阈值快速分割方法。该方法应用积分图思想将GLGM熵算法阈值搜索空间从O(9′ L)降到O(L)，并将GLGM熵算法从单阈值拓展到多阈值。最后应用基于实数编码的遗传算法搜索GLGM熵多阈值的最佳阈值。仿真结果表明，该方法能够实现图像的快速多阈值分割，适合复杂图像分割。
일사기우적적역치도상분할기술고필료공간신식，종이능구제고역치분할적성능，단시잉연불능교호지구분변연화조성。진관회도-제도（gray-level & gradient-magnitude，GLGM）적산법능유효지해결이상문제，단시침대다목표화복잡도상각불능유효지분할。위차，제출료일충기우유전산법（genetic algorithm，GA）적GLGM적다역치쾌속분할방법。해방법응용적분도사상장GLGM적산법역치수색공간종O(9′ L)강도O(L)，병장GLGM적산법종단역치탁전도다역치。최후응용기우실수편마적유전산법수색GLGM적다역치적최가역치。방진결과표명，해방법능구실현도상적쾌속다역치분할，괄합복잡도상분할。
Due to considering the gray level spatial distribution information, some image segmentation technologies based on entropy threshold can enhance the thresholding segmentation performance. However, they still cannot dis-tinguish image edges and noise well. Even though GLGM (gray-level&gradient-magnitude) entropy can effectively solve the problem, it cannot segment effectively multi-objective and complex image. So, this paper proposes image segmentation with multi-threshold of GLGM entropy based on genetic algorithm. In the proposed method, integral figure is introduced in order to make threshold searching dimension from original O(9 ′ L) to O(L) , and the single threshold segmentation of GLGM entropy is further extended to multi-threshold segmentation. Lastly, the real-code-GA is used to search the best thresholds. The simulation results show that this method can be effectively applied for the multi-threshold segmentation of complex images.