改进鲸鱼算法的二维最大熵图像分割研究

Research on Two-dimensional Maximum Entropy Image Segmentation Based on Improved Whale Algorithm

图像分割是图像处理中重要的分支,为后续的图像识别奠定了基础。而图像阈值分割的准确性很大程度上由阈值确定。与其它阈值分割方法相比,二维最大熵阈值法具有较好的分割效果,但是需要大量的运算,从而导致效率低、准确度低等问题。为准确高效的分割出图像的感兴区,提出一种改进的鲸鱼优化算法与最大熵算法相结合算法。通过对传统的鲸鱼算法进行改进,提高寻找二维最大熵算法的阈值速度。仿真结果表明,改进算法与传统的二维最大熵算法相比图像分割效果更精确,且提高了运算速度和分割精度。在图像分割应用中具有一定价值。

Image segmentation is an important part of image processing and the foundation of the follow-up image recognition.The accuracy of image threshold segmentation is largely determined by threshold.Compared with other threshold segmentation method,the 2-d maximum entropy threshold segmentation method has better segmentation effect,but needs a lot of operation,leading to low efficiency and accuracy.In order to segment the interested area of the image accurately and efficiently,an improved whale optimization algorithm combined with maximum entropy algorithm is proposed.By improving the traditional whale algorithm,the threshold velocity of searching for 2-d maximum entropy algorithm was increased.The simulation results show that compared with the traditional two-dimensional maximum entropy algorithm,this algorithm can accurately segmentation image,improves the operation speed and accuracy of segmentation.