马晓丹,刘刚,周薇,冯娟.基于量子遗传模糊神经网络的苹果果实识别[J].农业机械学报,2013,44(12):227-232,251.
Ma Xiaodan,Liu Gang,Zhou Wei,Feng Juan.Apple Recognition Based on Fuzzy Neural Network and Quantum Genetic Algorithm[J].Transactions of the Chinese Society for Agricultural Machinery,2013,44(12):227-232,251.
摘要点击次数: 3830
全文下载次数: 1868
基于量子遗传模糊神经网络的苹果果实识别   [下载全文]
Apple Recognition Based on Fuzzy Neural Network and Quantum Genetic Algorithm   [Download Pdf][in English]
  
DOI:10.6041/j.issn.1000-1298.2013.12.038
中文关键词:  苹果  量子遗传算法  模糊神经网络  颜色空间
基金项目:国家自然科学基金资助项目(31071333)和中央高校基本科研业务费专项资金资助项目(2013YJ008)
作者单位
马晓丹 中国农业大学
黑龙江八一农垦大学 
刘刚 中国农业大学 
周薇 中国农业大学 
冯娟 中国农业大学 
中文摘要:针对田间苹果采摘机器人视觉系统中彩色图像边界像素的模糊性和不确定性影响苹果果实识别精度和速度问题,提出了一种将量子遗传算法的全局搜索能力和模糊推理神经网络的自适应性相结合的算法来识别苹果果实。利用量子遗传算法对模糊神经网络的可调整参数初始值进行了全局优化,加快了网络学习速度,避免了传统BP误差反向传播学习算法易陷入局部极小值、迭代次数多等弊端。实验表明:该识别模型高速且稳定,鲁棒性好,对于果实本身颜色不均匀样本正确识别率为100%,对自然光照引起颜色不均匀样本正确识别率为96.86%,对邻接图像正确识别率为94.29%,对重叠图像正确识别率为92.31%。
Ma Xiaodan  Liu Gang  Zhou Wei  Feng Juan
China Agricultural University; Heilongjiang Bayi Agricultural University;China Agricultural University;China Agricultural University;China Agricultural University
Key Words:Apple  Quantum genetic algorithm  Fuzzy neural network  Color space
Abstract:The apple images were hard to be identified at a faster speed and a higher accuracy because of fuzzy and uncertain factors existing in the color image boundary pixels, so in order to overcome the disadvantages above, a model combined quantum genetic algorithm and fuzzy neural network was built up which showed the capability of global search capability and adaptation. In the proposed model, quantum genetic algorithm was used to optimize the initial value of adjustable parameter in fuzzy neural network, which avoided redundant iteration and the incline to fall into the local minimum value of traditional BP algorithm. The experimental results showed that the proposed model achieved accuracy of 100% for the uneven color samples, 96.86% for sunlight influenced samples, 94.29% for the adjacent samples, and 92.31% for the overlapping samples.

Transactions of the Chinese Society for Agriculture Machinery (CSAM), in charged of China Association for Science and Technology (CAST), sponsored by CSAM and Chinese Academy of Agricultural Mechanization Science(CAAMS), started publication in 1957. It is the earliest interdisciplinary journal in Chinese which combines agricultural and engineering. It always closely grasps the development direction of agriculture engineering disciplines and the published papers represent the highest academic level of agriculture engineering in China. Currently, nearly 8,000 papers have been already published. There are around 3,000 papers contributed to the journal each year, but only around 600 of them will be accepted. Transactions of CSAM focuses on a wide range of agricultural machinery, irrigation, electronics, robotics, agro-products engineering, biological energy, agricultural structures and environment and more. Subjects in Transactions of the CSAM have been embodied by many internationally well-known index systems, such as: EI Compendex, CA, CSA, etc.

   下载PDF阅读器