基于SSA—SVM算法的成熟黄花菜图像分割

doi:10.13733/j.jcam.issn.2095-5553.2025.06.013

摘要/Abstract

摘要：

自然环境下，由于光照不均，黄花菜与茎叶、土壤等背景对比度低，图像分割准确率低、定位困难，基于此，提出一种基于麻雀搜索算法（SSA）融合支持向量机（SVM）的成熟黄花菜图像分割方法。首先，采用RGB、HSV颜色模型构造样本特征数据集，对成熟黄花菜分割模型进行训练。其次，基于SSA优化SVM中的高斯径向基核函数参数和惩罚项系数，获得最优分类模型，经过二值化、形态学开运算及填充孔洞、去除噪声等图像形态学操作，完成图像分割。最后，针对光照较弱的黄花菜图像欠分割状况，对分类结果实施HSV模型阈值分割操作。试验结果表明：基于SSA—SVM算法的图像分割方法平均分割精度达到97.057%，处理时间为1.822 s。

关键词: 黄花菜, 麻雀搜索法, 支持向量机, 图像分割, 颜色模型

Abstract:

Due to uneven lighting and low contrast with backgrounds such as stems, leaves, and soil in natural environments, the image segmentation accuracy is low and localization is difficult, a mature daylily image segmentation method based on sparrow search algorithm (SSA) and support vector machine (SVM) was proposed. Firstly, the sample feature dataset was construct by using RGB and HSV color models, which was used to train the mature daylily segmentation model. Based on SSA optimization of SVM Gaussian radial basis kernel function parameters and penalty coefficients, the optimal classification model was obtained. After binarization, morphological opening, hole filling, noise removal and other image morphological operations, image segmentation was finally completed. Aiming at the under segmentation of daylily images with weak lighting, the HSV model threshold segmentation operation to the classification results was implemented. The experimental results show that the average segmentation accuracy of the image segmentation method based on SSA—SVM algorithm reaches 97.057%, and the processing time reaches 1.822 s.

Key words: daylily, sparrow search algorithm, support vector machine, image segmentation, color models

中图分类号:

S644.3
TP399

姚涛, 谈志鹏, 程娥, 武晔秋, 吴利刚. 基于SSA—SVM算法的成熟黄花菜图像分割[J]. 中国农机化学报, 2025, 46(6): 85-90.

Yao Tao, Tan Zhipeng, Cheng E, Wu Yeqiu, Wu Ligang. Mature yellow daylily image segmentation based on SSA—SVM algorithm[J]. Journal of Chinese Agricultural Mechanization, 2025, 46(6): 85-90.

参考文献

[ 1 ] 杨帆, 李鹏飞, 刘庚, 等. 橘子采摘机器人目标识别定位方法与实验研究[J]. 西安理工大学学报, 2018, 34(4): 460-467.

Yang Fan, Li Pengfei, Liu Geng, et al. A new identification and location method and experiment research on a kind of orange harvesting robots [J]. Journal of Xi'an University of Technology, 2018, 34(4): 460-467.

[ 2 ] 董娅兰, 胡国玉, 刘广, 等. 基于Mask R—CNN模型的葡萄藤关键结构分割方法[J]. 中国农机化学报, 2024, 45(2): 207-214.

Dong Yalan, Hu Guoyu, Liu Guang, et al. Segmentation method for grapevine critical structure based on Mask R—CNN model [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(2): 207-214.

[ 3 ] 初广丽, 张伟, 王延杰, 等. 基于机器视觉的水果采摘机器人目标识别方法[J]. 中国农机化学报, 2018, 39(2): 83-88.

Chu Guangli, Zhang Wei, Wang Yanjie, et al. A method of fruit picking robot target identification based on machine vision [J]. Journal of Chinese Agricultural Mechanization, 2018, 39(2): 83-88.

[ 4 ] Otsu N. A threshold selection method from gray‑level histograms [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.

[ 5 ] Nock R, Nielsen F. Statistical region merging [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(11): 1452-1458.

[ 6 ] Najman L, Schmitt M. Watershed of a continuous function [J]. Signal Processing, 1994, 38(1): 99-112..

[ 7 ] Kirk K, Andersen H J, Thomsen A G, et al. Estimation of leaf area index in cereal crops using red‑green images [J]. Biosystems Engineering, 2009, 104(3): 308-317.

[ 8 ] Ruiz‑Ruiz G, Gómez‑Gil J, Navas‑Gracia L M. Testing different color spaces based on hue for the environmentally adaptive segmentation algorithm (EASA) [J]. Computers and Electronics in Agriculture, 2009, 68(1): 88-96.

[ 9 ] 程晓龙, 刘立波. 基于SVM的棉田冠层图像分割方法研究[J]. 农业科学研究, 2017, 38(3): 7-10.

[10] 王春雷, 卢彩云, 李洪文. 基于支持向量机的玉米根茬行图像分割[J]. 农业工程学报, 2021, 37(16): 117-126.

Wang Chunlei, Lu Caiyun, Li Hongwen. Image segmentation of maize stubble row based on SVM [J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(16): 117-126.

[11] 肖美欣. 基于HIS颜色阈值的油菜花图像自动分割[D]. 武汉：武汉轻工大学， 2023.

[12] 肖美欣, 梅杰, 孙开琼. 颜色阈值与聚类结合的自动油菜花图像分割[J]. 武汉轻工大学学报, 2021, 40(5): 28-46.

[13] 齐锐丽, 陈曼龙, 杨宗浩, 等. 基于HSV模型与改进的OTSU算法花椒图像分割[J]. 中国农机化学报, 2019, 40(11): 155-160.

Qi Ruili, Chen Manlong, Yang Zonghao, et al. Image segmentation of Sichuan pepper based on HSV model and improved OTSU algorithm [J]. Journal of Chinese Agricultural Mechanization, 2019, 40(11): 155-160.

[14] 刘可心, 赵爽, 苗玉彬. 基于SSA—Kmeans聚类算法的青菜杂质图像分割[J]. 中国农机化学报, 2024, 45(2): 151-156.

Liu Kexin, Zhao Shuang, Miao Yubin. Image segmentation of green vegetable based on SSA—Kmeans clustering algorithm [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(2): 151-156.

[15] 沈中华, 夏爱强, 董志康, 等. 复杂环境下蔗梢图像分割方法研究[J]. 中国农机化学报, 2023, 44 (12): 113-118.

Shen Zhonghua,Xia Aiqiang, Dong Zhikang, et al. Study on image segmentation method of sugarcane tip in complex environment [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(12): 113-118.

[16] 周文静, 赵康, 马晓晓, 等. 基于改进红绿色差和Otsu的葡萄果穗图像分割[J]. 中国农机化学报, 2023, 44(1): 172-177.

Zhou Wenjing, Zhao Kang, Ma Xiaoxiao, et al. Image segmentation of grape cluster based on improved red‑green difference and Otsu [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(1): 172-177.

[17] Minaee S, Boykov Y, Porikli F, et al. Image segmentation using deep learning: A survey [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(7): 3523-3542.

[18] 姚涛, 谈志鹏, 程娥, 等. 基于改进YOLOv7—seg的黄花菜检测与分割方法[J]. 农业工程学报, 2024, 40(9):146-153.

Yao Tao, Tan Zhipeng, Cheng E, et al. Method for daylily detection and segmentation based on improved YOLOv7—seg [J]. Transactions of the Chinese Society of Agricultural Engineering, 2024, 40(9): 146-153.

[1]	刘宇平, 刘程飞, 赵平伟. 基于DeepLabv3—Faster R—CNN的水稻叶片病害检测方法#br#[J]. 中国农机化学报, 2025, 46(4): 108-113.
[2]	沈伟杰, 肖茂华, 宋新民, 项腾飞. 基于连续小波变换的CNN—SVM农机滚动轴承故障诊断#br#[J]. 中国农机化学报, 2025, 46(4): 254-264.
[3]	杨玉超, 籍颖, 李敬蕊, 宫彬彬, 高洪波. 基于热成像处理技术的生菜水分胁迫检测模型研究[J]. 中国农机化学报, 2025, 46(1): 131-137.
[4]	王雷, 钟康生, 郭小宝, 盛斌, 肖波, 荆磊. 基于机器视觉的陈皮热泵干燥含水率预测模型研究[J]. 中国农机化学报, 2024, 45(7): 97-103.
[5]	张延军, 赵建鑫, . 基于多路神经网络的黄花菜关节点检测算法研究[J]. 中国农机化学报, 2024, 45(7): 228-234.
[6]	张巍, 赵帮泰, 杨昌敏, 程方平, 王义鹏, 宋乐见. 名优茶智能化采摘关键技术研究进展[J]. 中国农机化学报, 2024, 45(5): 202-209.
[7]	陈鲁威, , 曾锦, , 袁全春, , 夏烨, , 潘健, 吕晓兰, , . 基于改进DeepLabV3+的梨树冠层分割方法[J]. 中国农机化学报, 2024, 45(4): 155-161.
[8]	董娅兰, 胡国玉, 刘广, 古丽巴哈尔·托乎提. 基于Mask R-CNN模型的葡萄藤关键结构分割方法[J]. 中国农机化学报, 2024, 45(2): 207-214.
[9]	张伟进, 王福顺, , 孙小华, 王军皓, 刘宏权, 王鑫鑫, . 传统图像分割算法在农作物籽粒考种应用中的研究进展[J]. 中国农机化学报, 2024, 45(2): 280-287.
[10]	孟源, 闫飞. 基于多目标分析的F-T柴油机SOOT和NOX排放物优化研究[J]. 中国农机化学报, 2024, 45(11): 119-124.
[11]	吴鹏, 刘金兰. 基于PCA-LDASVM算法的茶小绿叶蝉识别[J]. 中国农机化学报, 2024, 45(1): 295-300.
[12]	阮承治, 林根深, 陈旭, 孙月平, 杨君, 赵德安. 基于图像处理的蟹塘水草图像导航线拟合方法[J]. 中国农机化学报, 2023, 44(7): 147-153.
[13]	葛翔, 陆军, 曹冬林, 金天澍. 基于轮廓固性与分水岭算法的叶片粘连雾滴图像分割[J]. 中国农机化学报, 2023, 44(6): 182-191.
[14]	沈中华, 夏爱强, 董志康, 陈万委, 曹卫华. 复杂环境下蔗梢图像分割方法研究[J]. 中国农机化学报, 2023, 44(12): 113-118.
[15]	朱路生, 徐敏雅, 王爱臣, 张东凤, 钱伟豪, 李川. 基于改进DeepLabV3+的成熟期水稻生长密度检测研究[J]. 中国农机化学报, 2023, 44(12): 186-192.