- 期刊
The Research Review of Target Object Recognition Method
摘要
Object recognition is to separate the object to be recognized from the background environment in the original image obtained by the visual system. The common methods mainly include threshold segmentation, K-means clustering algorithm, artificial neural network and K-nearest neighbor method (KNN). In order to improve the accuracy and efficiency of object recognition, the method of optimization algorithm is often adopted, that is, a combination of various algorithms, using their respective advantages to achieve the purpose. This paper mainly introduces the optimal neural network K-means clustering and the combined application of neural network and K-means clustering.
參考文獻
JIN Baohua, YIN Changkui, ZHANG Weizheng, ZHANG Weiwei, etc.A review of apple orchard fruit recognition based on machine vision, (Chinese Journal of Light Industry)(2)34,2019,p71-81.
Application of machine learning in intrusion detection
MA Xiaodan, LIU Gang, ZHOU Wei, FENG Juan. Apple fruit recognition based on quantum genetic fuzzy neural network (Transactions of the Chinese Society for Agricultural Machinery) (12) 44, 2013. p227-232,251.
Jiang Mei, Sun Yingshuang, He Jiandong, Song Huaibo.An occluded apple target identification and location method based on K-means clustering segmentation algorithm and convex hull principle (intelligent agriculture), (2) 1,2019,p45-54.
JIA Weikuan, ZHAO De-an, LIU Xiaoyang, etc al .Identification of robot picking apple fruit by K-means and GA-RBF-LMS neural network (Transactions of the Chinese Society of Agricultural Engineering), (18) 31,2015,p175-183.