一种基于图像特征和神经网络的苹果图像分割算法

张亚静; 李民赞; 乔军; 刘刚

光学学报, 2008, 28 (11): 2104, 网络出版: 2008-11-17

一种基于图像特征和神经网络的苹果图像分割算法

Segmentation Algorithm for Apple Recognition using Image Features and Artificial Neural Network

论文大纲

张亚静 ^*李民赞乔军刘刚

作者单位

中国农业大学现代精细农业系统集成研究教育部重点实验室, 北京 100083

机器视觉图像分割纹理特征灰度共生矩阵神经网络 machine vision image segmentation texture feature gray level co-ocurrence matrix(GLCM) neural network

摘要

苹果识别是开发苹果采摘机器人的关键环节, 利用图像处理技术和神经网络分类器探索苹果图像分割算法。从苹果树图片中选取苹果图像样本和背景图像样本, 分别计算这两类图像样本的颜色特征和纹理特征。颜色特征的计算基于RGB色彩模型, 纹理特征的计算基于灰度共生矩阵。选取适当的颜色特征(R/B值)和纹理特征(对比度值和相关性值)作为输入节点, 利用反向传播神经网络分类器建模, 输出值是一个0～1之间的计算值。通过阈值将输出结果分类为苹果或背景。试验结果表明, 该算法正确率大于87.6%, 对光照的影响不敏感, 是一种较为实用的苹果分割算法。

Abstract

To improve the accuracy of the automatic detection and classification of apples on the tree, image features and artificial neural network classifier are applied to segment the apple images. First, apple image samples and background image samples are chosen. Then the color feature and the texture features of the samples are calculated. The color feature (R/B ratio) is calculated based on RGB color model, and the texture features (contrast and correlation) are calculated by gray level co-occurrence matrix (GLCM). These three parameters are used as the input to the back-propagation neural network (BPNN) classifier. The result of the output layer is a numerical value in the runge of 0~1. It is classified into fruit and background based on a certain threshold value. The results of the segmentation show that the success rate is over 87.6%, and the influence of light is neglectable. It is feasible to use the algorithm in practical recognition of apple.

参考文献

[1] 郭海涛,田坦,王连玉等. 利用二维属性直方图的最大熵的图像分割方法[J]. 光学学报, 2006, 26(4): 506～509

Guo Haitao, Tian Tan, Wang Lianyu et al.. Image segmentation using the maximum entropy of the two-dimensional bound histogram[J]. Acta Optica Sinica, 2006, 26(4): 506～509

[2] 郭平,卢汉清. 贝叶斯概率图像自动分割研究[J]. 光学学报, 2002, 22(12): 1479～1483

Guo Ping, Lu Hanqing. A study on Bayesian probabilistic image automatic segmentation[J]. Acta Optica Sinica, 2002, 22(12): 1479～1483

[3] 聂守平,王鸣,刘峰. 低对比度图像分割算法研究[J]. 中国激光, 2004, 31(1): 89～91

Nie Shouping, Wang Ming, Liu Feng. Image segmentation algorithm study for low contrast image[J]. Chin. J. Lasers, 2004, 31(1): 89～91

[4] A. L. Tabb, D. L. Peterson, J. Park. Segmentation of apple fruit from video via background modeling[C]. ASABE Meeting, 2006. 063060

[5] . M. Bulanon, T. Kataoka, Y. Ota. A segmentation algorithm for the automatic recognition of Fuji apples at harvest[J]. Biosystems Engineering, 2002, 83(4): 405-412.

[6] T. Takahashi, S. Zhang, H. Fukuchi. Measurement of 3-D locations of fruit by binocular stereo vision for apple harvesting in an orchard[C]. ASAE Meeting, 2002. 021102

[7] 刘德连, 张建奇. 基于纹理分割的遥感图像的变化探测[J]. 光学学报, 2006, 26(8):1177～1181

Liu Delian, Zhang Jianqi. New texture segmentation-based approach for change detection in remote sensing image[J]. Acta Optica Sinica, 2006, 26(8): 1177～1181

[8] 薄华, 马缚龙,焦李成. 图像纹理的灰度共生矩阵计算问题的分析[J]. 电子学报, 2006, 1(1): 155～158

Bo Hua, Ma Fulong, Jiao Licheng. Research on computation of GLCM of image texture[J]. Acta Electronica Sinica, 2006, 1(1): 155～158

[9] 张志安, 冯宏伟. 一种新的基于纹理和空间分布特征的图像检索[J].光子学报, 2008, 37(2): 400～404

Zhang Zhian, Feng Hongwei. A new retrieval algorithm based on the texture-spatial feature[J]. Acta Photonica Sinica, 2008, 37(2): 400～404

[10] . C. Kim, T. J. Kang. Texture classification and segmentation using wavelet packet frame and Gaussian mixture model[J]. Pattern Recognition, 2007, 40: 1207-1221.

张亚静, 李民赞, 乔军, 刘刚. 一种基于图像特征和神经网络的苹果图像分割算法[J]. 光学学报, 2008, 28(11): 2104. Zhang Yajing, Li Minzan, Qiao Jun, Liu Gang. Segmentation Algorithm for Apple Recognition using Image Features and Artificial Neural Network[J]. Acta Optica Sinica, 2008, 28(11): 2104.

一种基于图像特征和神经网络的苹果图像分割算法

关于本站 Cookie 的使用提示

全站搜索

一种基于图像特征和神经网络的苹果图像分割算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索