Anomaly detection of potato, maize and apple leaf diseases based on color moments

doi:10.3969/j.issn.1004-1524.2022.10.17

Acta Agriculturae Zhejiangensis ›› 2022, Vol. 34 ›› Issue (10): 2230-2239.DOI: 10.3969/j.issn.1004-1524.2022.10.17

• Plant Protection • Previous Articles Next Articles

Anomaly detection of potato, maize and apple leaf diseases based on color moments

ZHANG Ziting¹(), HAN Jinyu¹, ZHANG Donghui¹, LI Han¹, LI Mingyuan¹, DENG Zhiping², SUN Xiaoyong¹^,^*()

1. College of Information Science and Engineering, Shandong Agricultural University, Tai’an 271000, Shandong, China
2. Institute of Virology and Biotechnology, Zhejiang Academy of Agricultural Sciences, Hangzhou 310021, China

Received:2021-08-07 Online:2022-10-25 Published:2022-10-26
Contact: SUN Xiaoyong

Abstract

Abstract:

Crop diseases are one of the important factors on crop yield. At present, most researches use traditional machine learning and deep learning methods to identify and classify known diseases. However, this kind of model requires a lot of disease data, and it is not suitable for detection of new diseases. To overcome this problem, this work aims to detect the abnormal leaf diseases by using only the healthy leaf data sets as the training data. Specifically, a method of anomaly detection of crop leaf diseases based on k-means++clustering and image blocking is proposed. After image denoising, segmentation, interception and other preprocessing operations, the color moment features of the image are extracted, k-means++clustering is performed on the training set, and the comparison models are constructed and the threshold is set to determine whether the test set is abnormal or not. The datasets of potato, maize and apple leaves used in this experiment are downloaded from Kaggle website. By adjusting the cluster number and block number, the accuracy rate of potato, maize and apple leaf on test set is higher than 89%, 95% and 95%, respectively, and the missing alarm rates on maize and apple are 0.

Key words: leaf diseases, anomaly detection, image blocking

CLC Number:

S431.9
TP391

ZHANG Ziting, HAN Jinyu, ZHANG Donghui, LI Han, LI Mingyuan, DENG Zhiping, SUN Xiaoyong. Anomaly detection of potato, maize and apple leaf diseases based on color moments[J]. Acta Agriculturae Zhejiangensis, 2022, 34(10): 2230-2239.

Figures/Tables 16

References 24

[1]	刘慧, 朱莉, 赵守歧, 等. 警惕番茄褐色皱果病毒传入我国[J]. 中国植保导刊, 2019, 39(8): 73-76.
	LIU H, ZHU L, ZHAO S Q, et al. Watch out for introduction of Tomato brown rugose fruit virus to China[J]. China Plant Protection, 2019, 39(8): 73-76. (in Chinese with English abstract)
[2]	OPPENHEIM D, SHANI G. Potato disease classification using convolution neural networks[J]. Advances in Animal Biosciences, 2017, 8(2): 244-249. DOI URL
[3]	SRAVAN V, SWARAJ K, MEENAKSHI K, et al. A deep learning based crop disease classification using transfer learning[J]. Materials Today: Proceedings, 2021.
[4]	王志国, 章毓晋. 监控视频异常检测: 综述[J]. 清华大学学报(自然科学版), 2020, 60(6): 518-529.
	WANG Z G, ZHANG Y J. Anomaly detection in surveillance videos: a survey[J]. Journal of Tsinghua University (Science and Technology), 2020, 60(6): 518-529. (in Chinese with English abstract)
[5]	SMITI A. A critical overview of outlier detection methods[J]. Computer Science Review, 2020, 38: 100306. DOI URL
[6]	张勇东, 陈思洋, 彭雨荷, 等. 基于深度学习的网络入侵检测研究综述[J]. 广州大学学报(自然科学版), 2019, 18(3): 17-26.
	ZHANG Y D, CHEN S Y, PENG Y H, et al. A survey of deep learning based network intrusion detection[J]. Journal of Guangzhou University (Natural Science Edition), 2019, 18(3): 17-26. (in Chinese with English abstract)
[7]	WEST J, BHATTACHARYA M. Intelligent financial fraud detection: a comprehensive review[J]. Computers & Security, 2016, 57: 47-66. DOI URL
[8]	FERNANDO T, DENMAN S, AHMEDT-ARISTIZABAL D, et al. Neural memory plasticity for medical anomaly detection[J]. Neural Networks, 2020, 127: 67-81. DOI PMID
[9]	BAUR C, DENNER S, WIESTLER B, et al. Autoencoders for unsupervised anomaly segmentation in brain MR images: a comparative study[J]. Medical Image Analysis, 2021, 69: 101952. DOI URL
[10]	TOGO R, WATANABE H, OGAWA T, et al. Deep convolutional neural network-based anomaly detection for organ classification in gastric X-ray examination[J]. Computers in Biology and Medicine, 2020, 123: 103903. DOI URL
[11]	RUBINSTEIN E, SALHOV M, NIDAM-LESHEM M, et al. Unsupervised tumor detection in dynamic PET/CT imaging of the prostate[J]. Medical Image Analysis, 2019, 55: 27-40. DOI PMID
[12]	DONG L, LIU S L, ZHANG H L. A method of anomaly detection and fault diagnosis with online adaptive learning under small training samples[J]. Pattern Recognition, 2017, 64: 374-385. DOI URL
[13]	PURARJOMANDLANGRUDI A, GHAPANCHI A H, ESMALIFALAK M. A data mining approach for fault diagnosis: an application of anomaly detection algorithm[J]. Measurement, 2014, 55: 343-352. DOI URL
[14]	AYDIN I, KARAKOSE M, AKIN E. A multi-objective artificial immune algorithm for parameter optimization in support vector machine[J]. Applied Soft Computing, 2011, 11(1): 120-129. DOI URL
[15]	WU Y T, LI D L, LI Z B, et al. Fast processing of foreign fiber images by image blocking[J]. Information Processing in Agriculture, 2014, 1(1): 2-13. DOI URL
[16]	袁渊, 丁胜, 徐新. 基于颜色与纹理特征的安防视频遮挡树叶检测[J]. 计算机工程与设计, 2016, 37(6): 1549-1554.
	YUAN Y, DING S, XU X. Color and texture feature based approach for leaf occlusion detection in security surveillance video[J]. Computer Engineering and Design, 2016, 37(6): 1549-1554. (in Chinese with English abstract)
[17]	苗荣慧, 杨华, 武锦龙, 等. 基于图像分块及重构的菠菜重叠叶片与杂草识别[J]. 农业工程学报, 2020, 36(4): 178-184.
	MIAO R H, YANG H, WU J L, et al. Weed identification of overlapping spinach leaves based on image sub-block and reconstruction[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(4): 178-184. (in Chinese with English abstract)
[18]	王国屹, 孙永荣, 张怡, 等. 背景对齐差分的机场跑道异物分块检测与跟踪算法[J]. 计算机辅助设计与图形学学报, 2021, 33(3): 413-423.
	WANG G Y, SUN Y R, ZHANG Y, et al. Block detection and tracking algorithm of foreign objects debris in airport runway based on background alignment and difference[J]. Journal of Computer-Aided Design & Computer Graphics, 2021, 33(3): 413-423. (in Chinese with English abstract)
[19]	ROTHER C, KOLMOGOROV V, BLAKE A. GrabCut: interactive foreground extraction using iterated graph cuts[J]. ACM Transactions on Graphics, 2004, 23(3): 309-314. DOI URL
[20]	BOYKOV Y Y, JOLLY M P. Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images[C]// Proceedings of Eighth IEEE International Conference on Computer Vision. ICCV 2001. Vancouver, BC, Canada: IEEE, 2001: 105-112.
[21]	STRICKER M A, ORENGO M. Similarity of color images[J]. Proceedings of SPIE, 1995, 2420: 381-392.
[22]	POYNTON C A. A guided tour of colour space[C]// The SMPTE Advanced Television and Electronic Imaging Conference, February 10-11, 1995. San Francisco, CA, USA:. IEEE, 1995: 167-180.
[23]	CHERNOV V, ALANDER J, BOCHKO V. Integer-based accurate conversion between RGB and HSV color spaces[J]. Computers & Electrical Engineering, 2015, 46: 328-337.
[24]	STEMMER U. Locally private k-means clustering[M]//Proceedings of the Fourteenth Annual ACM-SIAM Symposium on Discrete Algorithms, Philadelphia, PA: Society for Industrial and Applied Mathematics, 2020: 548-559.

植物种类 Plant species	样本情况 Sample status		样本数量 Sample quantity
土豆Potato	正常Normal	健康Healthy	152
	异常Abnormal	早疫病Early blight	1 000
		晚疫病Late blight	1 000
玉米Maize	正常Normal	健康Healthy	1 162
	异常Abnormal	普通锈病Common rust	1 142
		灰斑病Gray spot	463
		叶枯病Leaf blight	935
苹果Apple	正常Normal	健康Healthy	1 638
	异常Abnormal	黑腐病Black rot	621
		雪松锈病Cedar rust	275
		黑星病Black-spot	630

植物种类 Plant species	样本情况 Sample status		样本数量 Sample quantity
土豆Potato	正常Normal	健康Healthy	152
	异常Abnormal	早疫病Early blight	1 000
		晚疫病Late blight	1 000
玉米Maize	正常Normal	健康Healthy	1 162
	异常Abnormal	普通锈病Common rust	1 142
		灰斑病Gray spot	463
		叶枯病Leaf blight	935
苹果Apple	正常Normal	健康Healthy	1 638
	异常Abnormal	黑腐病Black rot	621
		雪松锈病Cedar rust	275
		黑星病Black-spot	630

植物种类 Plant species	数据集类型 Dataset type	正常样本数 Quantity of normal samples	异常样本数 Quantity of abnormal samples
土豆Potato	训练集Training set	120	0
	测试集Testing set	30	20
玉米Maize	训练集Training set	928	0
	测试集Testing set	232	150
苹果Apple	训练集Training set	1 232	0
	测试集Testing set	308	211

植物种类 Plant species	数据集类型 Dataset type	正常样本数 Quantity of normal samples	异常样本数 Quantity of abnormal samples
土豆Potato	训练集Training set	120	0
	测试集Testing set	30	20
玉米Maize	训练集Training set	928	0
	测试集Testing set	232	150
苹果Apple	训练集Training set	1 232	0
	测试集Testing set	308	211

颜色矩 Color moment	聚类数 Cluster number	A		MAR
颜色矩 Color moment	聚类数 Cluster number	1×1	2×2	1×1	2×2
RGB	0	80.8	67.2	43.0	82.0
	2	85.2	82.0	13.0	38.0
	3	74.4	81.2	21.0	34.0
HSV	0	64.4	67.2	31.0	79.0
	2	72.0	66.8	45.0	80.0
	3	72.0	67.2	54.0	75.0

Anomaly detection of potato, maize and apple leaf diseases based on color moments

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 16

References 24

Related Articles 1

Recommended Articles

Metrics

Comments

聚类数 Cluster number	A		MAR
聚类数 Cluster number	1×1	2×2	1×1	2×2
0	82.8	74.8	18.0	61.0
2	89.2	78.8	7.0	22.0
3	80.0	82.8	14.0	37.0

模型 Model	A			MAR
模型 Model	土豆Potato	玉米Maize	苹果Apple	土豆Potato	玉米Maize	苹果Apple
KNN	92.0	89.8	79.2	5.0	10.4	36.8
ABOD	92.4	92.2	75.4	3.0	4.2	47.4
HBOS	76.4	85.6	60.8	48.0	20.0	80.6
COF	79.6	59.0	58.8	47.0	89.6	89.2
CBLOF	90.8	81.6	79.6	4.0	29.4	33.6
Iforest	81.2	83.0	62.4	31.0	26.8	77.2
CMAD	89.2	98.7	96.4	7.0	0	0

颜色矩 Color moment	聚类数 Cluster number	A		MAR
颜色矩 Color moment	聚类数 Cluster number	1×1	2×2	1×1	2×2
RGB	0	60.7	60.7	100.0	100.0
	2	68.1	77.1	44.9	40.9
	3	68.6	73.8	38.7	46.0
HSV	0	80.9	83.3	1.2	1.2
	2	87.7	84.2	24.8	37.0
	3	89.7	92.3	8.0	11.0

颜色矩 Color moment	聚类数 Cluster number	A		MAR
颜色矩 Color moment	聚类数 Cluster number	1×1	2×2	1×1	2×2
RGB	0	60.7	60.7	100.0	100.0
	2	68.1	77.1	44.9	40.9
	3	68.6	73.8	38.7	46.0
HSV	0	80.9	83.3	1.2	1.2
	2	87.7	84.2	24.8	37.0
	3	89.7	92.3	8.0	11.0

颜色矩 Color moment	聚类数 Cluster number	A		MAR
颜色矩 Color moment	聚类数 Cluster number	1×1	2×2	1×1	2×2
RGB	0	59.3	59.5	100	100.0
	2	57.9	58.7	63.8	91.1
	3	60.2	65.7	42.2	42.2
HSV	0	54.3	69.7	6.4	27.6
	2	71.4	69.4	49.1	71.0
	3	76.2	70.0	46.7	60.6

颜色矩 Color moment	聚类数 Cluster number	A		MAR
颜色矩 Color moment	聚类数 Cluster number	1×1	2×2	1×1	2×2
RGB	0	59.3	59.5	100	100.0
	2	57.9	58.7	63.8	91.1
	3	60.2	65.7	42.2	42.2
HSV	0	54.3	69.7	6.4	27.6
	2	71.4	69.4	49.1	71.0
	3	76.2	70.0	46.7	60.6