Research on the Recognition Method of Wheat Ears Based on Image Color and Classical Model

Shugang  Liu; Yihui  Chen

doi:10.54097/4q2nq026

Authors

Shugang Liu
Yihui Chen

DOI:

https://doi.org/10.54097/4q2nq026

Keywords:

Digital image processing, edge contour detection, model structure analysis, model training method, constructive dataset.

Abstract

In this paper, we study wheat images during the grouting period, and construct a dataset by extracting wheat spike features through image preprocessing, color space conversion and edge detection. CNN and AlexNet models are used to train and optimize the parameters and structure to improve the recognition accuracy. By adjusting the batch size, learning rate and training rounds, CNN performs optimally with Batch size=64, Epoch=5, and learning rate=0.0001; AlexNet also performs well with similar settings, but the training cost is larger. This study verifies the effectiveness of image processing combined with the classical model CNN for recognizing wheat sheaves, providing data and theoretical support for wheat yield prediction.

References

Jahui Zhang. Research on the model of jujube yield estimation based on image processing [D]. Hebei Agricultural University, 2019.

MorenoLucio Mireyaetal. Extraction of Pest Insect Characteristics Present in a Mirasol Pepper (Capsicum annuum L.) Crop by Digital Image Processing[J]. Applied Sciences, 2021, 11(23):11166-11166.

Fangzheng Tianetal. Automatic coronary artery segmentation algorithm based on deep learning and digital image processing[J]. Applied Intelligence, 2021:51(12):1-15.

Hasan Aetal. Quantitative assessment of mosaic disease severity based on digital image processing[J]. IOP Conference Series: Earth and Environmental Science, 2021, 694(1):012043-.

Samadzadegan Farhadetal. Detection and Recognition of Drones Based on a Deep Convolutional Neural Network Using Visible Imagery[J]. Aerospace, 2022, 9(1) : 31-31.

JU Wenhui. Research on visual counting method based on deep learning [D]. Shandong Normal University, 2021.

Cheng-Cheng Huang,Hua-Mei Huang. Architecture and application development of convolutional neural networks[J]. Information and Computer (Theoretical Edition), 2019(07):143-144.

Zhang Chen. Face recognition method and application based on AlexNet convolutional neural network model[J]. Journal of Ezhou University, 2022, 29(01):102-104.

Kong Yunchen and Ma Xue and Wen Chenglin. A New Method of Deep Convolutional Neural Network Image Classification Based on Knowledge Transfer in Small Label Sample Environment[J]. Sensors, 2022, 22(3):898-898.

WANG Xin, PAN He, ZHAO Ying. Research on corn kernel shape feature detection technology - based on image processing[J]. Agricultural Mechanization Research, 2015, 37(06):46-48+52.

MA Xiaodan, ZHU Kexin, GUAN Haiou, FENG Jiarui, LIU Meng, ZHENG Ming. Crop image feature extraction technology and its application in disease diagnosis[J]. Journal of Heilongjiang Bayi Agricultural Reclamation University, 2019, 31(02):93-99.

LI Yi-Nian, DU Shi-Wei, YAO Min, YI Ying-Wu, YANG Jian-Feng, DING Qi-Shuo, HE Rui-Yin. A method for counting wheat ears and yield prediction in the field based on wheat population images[J]. Journal of Agricultural Engineering, 2018, 34(21):185-194.

ZHAO Xiaoyu, CHEN Jianjun, ZHANG Kaiqi, QIN Qiaoting, YOU Huotian, HAN Xiaowen. Automatic extraction of vegetation coverage from UAV images based on HSV color space and Otsu algorithm[J]. Science, Technology and Engineering, 2021, 21(35):15160-15166.

Haiqiong Wen,Jiancheng Li. Adaptive thresholding image enhancement algorithm based on histogram equalization[J]. China Integrated Circuit, 2022, 31(03):38-42.

LIU Jun,YU Qing.Research on K-Means clustering algorithm and its performance optimization[J]. Specialized Equipment for Electronic Industry, 2020, 49(05):46-49.

BAO Zhiqiang, ZHAO Yuanyuan, HU Xiaotian, ZHAO Yan. A new K-Means clustering algorithm insensitive to isolated points[J]. Modern Electronic Technology, 2020, 43(05):109-112.

Zhu Xiaoqian. Research on bubble feature extraction based on image processing [D]. Central China Normal University, 2021.

LI Zongnan, CHEN Zhongxin, WANG Limin, LIU Jia, ZHOU Qingbo. Extraction of corn downed area based on small UAV remote sensing[J]. Journal of Agricultural Engineering, 2014, 30(19):207-213.

Hao Wu. Research on deep learning method for image processing based on synthetic dataset [D]. Lanzhou University, 2021.

ZANG Jing, GUO Qianqian, LI Chenghua, FU Lidong. Research on identification and statistical methods of multiple corn kernels under complex conditions[J]. Journal of Shenyang Agricultural University, 2014, 45(5):633-636.

DU Shi-Wei, LI Yi-Nian, YAO Min, LI Ling, DING Qi-Shuo, HE Rui-Yin. Seed counting method based on spikelet image segmentation in wheat spike[J]. Journal of Nanjing Agricultural University, 2018, 41(4):742-751.

Li Haiyang. Recognition and counting of wheat ears based on image processing and deep learning [D]. Zhengzhou: Henan Agricultural University, 2021.

LIU Changhua, HU Linlong, YANG Kang, WU Xiaoming. Segmentation of aerial rape flower images based on color space[J]. Journal of Wuhan Light Industry University, 2020, 39(01):13-21.

JI Sweet, LI Zebin, ZHAO Jiangdong, YAO Youfeng, HUANG Ji. Segmentation method of plant leaf disease image based on color variability[J]. Hubei Agricultural Science, 2018, 57(18):94-97.