基于改进谱聚类的重叠绿苹果识别方法（英文）

Overlapping Green Apple Recognition Based on Improved Spectral Clustering

水果的可见光谱目标识别是实现农业自动化采摘至关重要的一步。在水果识别的过程中,由于重叠和遮挡的影响使得目标识别困难,识别率不高。本文针对自然环境中果实重叠的识别问题,利用谱聚类算法对图像进行分割,然后使用随机霍夫变换实现果实的识别和定位。针对传统算法运算复杂度高,运算速度慢的问题,本文提出了基于均值漂移和稀疏矩阵原理的改进谱聚类算法。首先使用均值漂移算法对图像进行预分割,均值漂移是一种用于密度梯度的无参估计法。该算法实质是一种迭代,先计算出偏移量,根据偏移量移动点,如此反复,直到偏移量为零即收敛到一点为止。利用均值漂移算法除去大多数的背景像素,为减少谱聚类算法的计算量做准备。然后提取预分割图像的有用信息即图像中像素对之间相似度的描述,将提取的图像特征信息映射到稀疏矩阵中,并使用K-means算法将其分类。得到最终的分类结果,实现对预处理图像的再次分割。然后恢复图像分割区域的颜色,使用彩色向量梯度提取边缘轮廓,对得到的轮廓图像使用随机霍夫变换,并在检测过程中设置半径参数的范围从而进一步加快算法的运行速度。经过检测可以得到目标的圆心坐标和半径,从而实现重叠绿苹果的识别。降低了谱聚类的数据处理量,提高了算法的运行速度。经过试验分析和算法对比,该算法得到较高的重合度95.41%,较低的误差率4.59%和误检率3.05%。

Fruits target recognition is one of the most important steps to realize agricultural automation. In the process of fruit recognition, because of the influence of overlap and occlusion, the target recognition is difficult, and the rate of recognition is not high. The paper uses spectral clustering algorithm to solve the problem of overlapped fruit in natural environment. Then the identification and location of fruit are realized by randomized hough transform. In view of the large number of computation and the slow operation speed of the traditional algorithm, this paper proposes an improved spectral clustering algorithm based on Mean Shift and sparse matrix principle. Firstly, the image is pre-segmented using the mean shift algorithm. Mean shift is a non-pa rametric estimation method for density gradient. The algorithm is essentially an iteration. Calculate the offset, move the point according to the offset, and re peat the above steps until the offset is zero. Most of the background pixels are removed by mean shift algorithm, and the removing is prepared for reducing the computational complexity of the spectral clustering algorithm. And then the usef ul information is extracted, which is the description of the similarity between the pairs of pixels in the image, and the extracted image feature information is mapped into a sparse matrix. The K-means algorithm is used to classify it into classes, and the final classification result is obtained to realize the re-seg mentation of the reprocessed image. Then the color of the image segmentation are a is restored, the edge contour is extracted by using a color vector gradient and the randomized hough transform is used on the resulting contour image, and the radius parameter range during the detection process is set to further accelerat e the speed of the algorithm. The center coordinates and radius of the target ca n be obtained through the detection. Thereby the overlapped green apples are rec ognized. Finally, the algorithm has the high coincidence degree of 95.41%, the low error rate of 4.59% and the false detection rate of 3.05% through experime ntal analysis and algorithm comparison, and the algorithm meets the practical ap plication requirements.