Research on Plant Image Recognition based on Deep Learning

Yuhang Feng ； Weichu Liu ； Luyao Qin ； Zicong Li ； Yifan Ma ； Xinyu Li

《International Core Journal of Engineering》 9卷5期 (2023/05) Pp. 314-321

https://doi.org/10.6919/ICJE.202305_9(5).0037

摘要

Based on the mainstream CNN(Tan Qingbo Convolutional Neural Network (CNN) Explanation [EB/OL] [2022‐5‐2]. https://zhuanlan.zhihu.com/p/47184529.) network training model, In order to improve the accuracy and accuracy of plant image recognition, We, before the training images, Using the image processing implemented in opencv with pyqt 5, We have added image rotation to the process of image processing and recognition, Image conversion to a grayscale plot, Smooth the image, Gradient calculation, edge detection, Contour detection, etc., Adding the loss function to the classification function layer, Effectively improve the generalization ability of the model, The datasets found were identified, Effective identification of ten plant species is now achieved, Moreover, the recognition accuracy of plants based on the trained model has reached more than 98%, Compared with the traditional CNN model, substantially improved accuracy, It has great application value in the field of plant image recognition.

關鍵字

pyqt 5 ； Opencv ； Loss Function ； Plant Image Recognition

參考文獻

KUMAR N, BELHUMEUR P N, BISWAS A, et al. Leafsnap: A Computer Vision System for Automatic Plant Species Recognition [C]. Proceedings of the 12th European Conference on Computer Vision. Italy: ACM, 2012:502-516.

Tan Qingbo Convolutional Neural Network (CNN) Explanation [EB/OL] [2022-5-2]. https:// zhuanlan. zhihu. com/p/47184529.

Ian Goodfellow / Yoshua Bengio / Aaron Courville. “Deep learning” [M]. 2016-11-18. MIT Press, 2016-11-18.

Zheng Jiao, Liu Libo. Design and application of an Android based rice disease image recognition system [J]. Computer Engineering and Science, 2015, 37 (7): 1366-1371.

LEVI G, HASSNCER T. Using Convolutional Neural Networks for Age and Gender Classification [C]. Symposium on Computer Vision and Pattern Recognition. USA: IEEE, 2015:34-42.