生猪虹膜快速定位算法研究

doi:10.3969/j.issn.1004-1524.20231274

浙江农业学报 ›› 2024, Vol. 36 ›› Issue (11): 2617-2626.DOI: 10.3969/j.issn.1004-1524.20231274

生猪虹膜快速定位算法研究

刘伟东^a(), 周素茵^a^,^*(), 徐爱俊^a, 叶俊华^b

a.数学与计算机科学学院, 浙江农林大学, 浙江杭州 311300
b.环境与资源学院,浙江农林大学, 浙江杭州 311300

收稿日期:2023-11-13 出版日期:2024-11-25 发布日期:2024-11-27
作者简介:刘伟东(1999—),男,江苏扬州人,硕士研究生,研究方向为农业信息化。E-mail:liuweidong@ztt.cn
通讯作者: *周素茵,E-mail:zsy197733@163.com
基金资助:
浙江省“领雁”研发攻关计划(2022C02050);浙江省“三农九方”科技协作计划(2022SNJF057)

Research on fast localization algorithm of pig iris

LIU Weidong^a(), ZHOU Suyin^a^,^*(), XU Aijun^a, YE Junhua^b

a. College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China
b. College of Environment and Resources, Zhejiang A&F University, Hangzhou 311300, China

Received:2023-11-13 Online:2024-11-25 Published:2024-11-27

摘要/Abstract

摘要：

虹膜定位是实现虹膜识别的前提与关键,当前主流虹膜采集设备普遍价格昂贵,且现有虹膜定位算法应用于猪眼虹膜定位时存在精度低、耗时长等问题。本文提出一种基于低成本采集设备的生猪虹膜快速高精度定位算法。首先对猪眼虹膜图像去噪和二值化,再对Canny算法进行改进,用于提取猪眼虹膜图像边缘信息,然后分别使用改进的Hough圆变换和迭代加权最小二乘法定位虹膜内、外边缘,进而完成生猪虹膜定位。对3 100张猪眼虹膜图像进行试验,结果表明,虹膜的正确检测率为96.19%,平均定位时间为342.50 ms。与DAUGMAN、WILDES和单位扇环灰度算法相比,正确检测率分别提升了10.49、8.67、3.61百分点,平均定位时间分别减少了70.90、81.50、98.00 ms。本文方法能在保证生猪虹膜正确检测率的基础上缩短定位时间,有效改善传统虹膜定位算法应用于猪眼虹膜时效果较差的问题,能为后续基于虹膜的生猪身份识别奠定基础。

关键词: 生猪, 虹膜定位, Canny算法, Hough圆变换, 正确检测率

Abstract:

Iris localization is the prerequisite and key link to realize iris recognition, the current mainstream iris capture devices are generally expensive, and the existing iris localization algorithm have problems such as low accuracy and long time consumption when applied to pig eye iris localization, so this paper proposes a fast and high accuracy iris localization algorithm for pigs based on low-cost acquisition equipment. Firstly, the pig iris image was denoised and binarized, then the Canny algorithm was improved to extract the edge information of the pig iris image, and then the inner and outer edges of the iris were located using the improved Hough circle transform and iterative reweighted least square method, so as to complete the localization of the pig iris. Experiments on 3 100 pig eye iris images showed that the accuracy rate of the iris was 96.19% and the average localization time was 342.50 ms. Compared with the DAUGMAN, WILDES and unit sector ring grey scale algorithms, the accuracy rate was improved by 10.49 percentage points, 8.67 percentage points and 3.61 percentage points, respectively, and the average localization time was reduced by 70.90, 81.50, 98.00 ms. This method could shorten the localization time while ensuring accuracy rate, and effectively improve the problem of poor effect of traditional iris positioning algorithm applied to pig iris, so as to lay an important foundation for the subsequent iris-based pig identification.

Key words: pig, iris localization, Canny algorithm, Hough circle transform, accuracy rate

中图分类号:

S818.9

刘伟东, 周素茵, 徐爱俊, 叶俊华. 生猪虹膜快速定位算法研究[J]. 浙江农业学报, 2024, 36(11): 2617-2626.

LIU Weidong, ZHOU Suyin, XU Aijun, YE Junhua. Research on fast localization algorithm of pig iris[J]. Acta Agriculturae Zhejiangensis, 2024, 36(11): 2617-2626.

图/表 11

图1 虹膜采集示意图

Fig.1 Schematic diagram of iris capture

图2 部分生猪的虹膜图像

Fig.2 Iris images of some pigs

图3 预处理结果 A,原图;B,中值滤波去噪;C,形态学开运算;D,形态学闭运算;E,自适应阈值二值化处理。

Fig.3 Pretreatment results A, Original figure; B, Median filter denoising; C, Morphological opening calculation; D, Morphological closed calculation; E, Adaptive threshold binarization process.

图4 改进的Hough圆变换取点原理图

Fig.4 Schematic diagram of the improved Hough circle transform to fetch points

图5 改进前后Canny算法边缘检测结果对比 A,改进前Canny算法边缘检测结果;B,改进后Canny算法边缘检测结果。

Fig.5 Comparison of edge detection results of Canny algorithm before and after improvement A, Edge detection results of Canny algorithm before improvement; B, Edge detection results of Canny algorithm after improvement.

图6 不同算法的定位试验结果 A,DAUGMAN算法定位结果;B,WILDES算法定位结果;C,单位扇环灰度算法定位结果;D,本文算法定位结果。

Fig.6 Localization test results of different algorithms A, DAUGMAN algorithm localization result; B, WILDES algorithm localization result; C, Gray value of unit sector area algorithm localization result; D, The algorithms of this paper localization result.

表1 各算法性能对比

Table 1 Performance comparison of algorithms %

算法 Algorithm	正确检测率 Accuracy rate	漏检率 Omissive rate	误检率 False rate
DAUGMAN	85.70	8.39	5.91
WILDES	87.52	7.84	4.64
单位扇环灰度算法	92.58	2.23	5.19
Gray value of unit sector area algorithm
本文算法	96.19	1.23	2.28
The algorithm in this paper

图7 本文方法与其他算法的定位时间对比

Fig.7 Comparison of the locating time of this paper’s method with other algorithms

表2 对比试验结果

Table 2 Results of comparative tests

算法名称 Algorithm name	正确检测率 Correct detection rate/%	内边缘平均定位时间 Average localization time for inner edges/ms	外边缘平均定位时间 Average localization time for outer edges/ms
最小二乘法The least squares method	86.29	203.91	215.83
Hough圆变换Hough’s circular transform	88.58	210.96	217.12
本文算法The algorithms in this paper	96.19	168.34	174.16

图8 部分非理想猪眼虹膜图像示例 A,光斑影响;B,睫毛遮挡;C,图像模糊。

Fig.8 Examples of some non-ideal pig iris images A, Spot effects; B, Eyelash masking; C, Blurred image.

图9 定位失败的猪眼虹膜图像示例

Fig.9 Example of a pig iris image with failed localization

参考文献 30

[1]	王荣, 高荣华, 李奇峰, 等. 融合注意力机制的开集猪脸识别方法[J]. 农业机械学报, 2023, 54(2): 256-264.
	WANG R, GAO R H, LI Q F, et al. Open-set pig face recognition method combining attention mechanism[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(2): 256-264. (in Chinese with English abstract)
[2]	黄志杰, 徐爱俊, 周素茵, 等. 融合重参数化和注意力机制的猪脸关键点检测方法[J]. 农业工程学报, 2023, 39(12): 141-149.
	HUANG Z J, XU A J, ZHOU S Y, et al. Key point detection method for pig face fusing reparameterization and attention mechanisms[J]. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(12): 141-149. (in Chinese with English abstract)
[3]	李斌, 刘东阳, 时国龙, 等. 基于改进YOLOv4模型的群养生猪姿态检测[J]. 浙江农业学报, 2023, 35(1): 215-225.
	LI B, LIU D Y, SHI G L, et al. Pig posture detection based on improved YOLOv4 model[J]. Acta Agriculturae Zhejiangensis, 2023, 35(1): 215-225. (in Chinese with English abstract)
[4]	HE Z F, TAN T N, SUN Z N, et al. Toward accurate and fast iris segmentation for iris biometrics[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(9): 1670-1684.
[5]	李星光, 孙哲南, 谭铁牛. 虹膜图像质量评价综述[J]. 中国图象图形学报, 2014, 19(6): 813-824.
	LI X G, SUN Z N, TAN T N. Overview of iris image quality-assessment[J]. Journal of Image and Graphics, 2014, 19(6): 813-824. (in Chinese with English abstract)
[6]	李超, 赵林度. 牛眼虹膜定位算法研究及其在肉食品追溯系统中的应用[J]. 中国安全科学学报, 2011, 21(3): 124-130.
	LI C, ZHAO L D. Research on cattle iris localization algorithm and its application in meat food tracking and traceability system[J]. China Safety Science Journal, 2011, 21(3): 124-130. (in Chinese with English abstract)
[7]	朱立军, 苑玮琦. 基于并查集和边缘检测模板的非理想虹膜定位[J]. 计算机应用研究, 2018, 35(6): 1879-1882.
	ZHU L J, YUAN W Q. Non-ideal iris localization method based on union-find-set and edge detection template[J]. Application Research of Computers, 2018, 35(6): 1879-1882. (in Chinese with English abstract)
[8]	李奇峰, 王文婷, 余礼根, 等. 信息技术在畜禽养殖中的应用进展[J]. 中国农业信息, 2018, 30(2): 15-23.
	LI Q F, WANG W T, YU L G, et al. Research review of information technologies for livestock[J]. China Agricultural Informatics, 2018, 30(2): 15-23. (in Chinese with English abstract)
[9]	杨亮, 熊本海, 王辉, 等. 家畜饲喂机器人研究进展与发展展望[J]. 智慧农业(中英文), 2022, 4(2): 86-98.
	YANG L, XIONG B H, WANG H, et al. Research progress and outlook of livestock feeding robot[J]. Smart Agriculture, 2022, 4(2): 86-98. (in Chinese with English abstract)
[10]	赵春江. 农业知识智能服务技术综述[J]. 智慧农业(中英文), 2023, 5(2): 126-148.
	ZHAO C J. Agricultural knowledge intelligent service technology: a review[J]. Smart Agriculture, 2023, 5(2): 126-148. (in Chinese with English abstract)
[11]	张哲, 王楚端, 王立贤, 等. 计算机视觉技术在猪眼肌肌内脂肪含量测定中的应用[J]. 猪业科学, 2006, 23(2): 24-25.
	ZHANG Z, WANG C D, WANG L X, et al. Application of computer vision technology in the determination of intramuscular fat content of pig eye muscle[J]. Swine Industry Science, 2006, 23(2): 24-25. (in Chinese)
[12]	冷碧滨, 吉雪强, 曾颢, 等. 中国大规模生猪养殖技术效率研究[J]. 浙江农业学报, 2018, 30(6): 1082-1088.
	LENG B B, JI X Q, ZENG H, et al. Study on technical efficiency of large-scale pig breeding in China[J]. Acta Agriculturae Zhejiangensis, 2018, 30(6): 1082-1088. (in Chinese with English abstract)
[13]	陈涛, 曾勇庆, 陈伟. 智能化设备在规模化猪场中的应用[J]. 中国猪业, 2020, 15(2): 89-92.
	CHEN T, ZENG Y Q, CHEN W. Application of intelligent equipment in large-scale pig farms[J]. China Swine Industry, 2020, 15(2): 89-92. (in Chinese)
[14]	刘同海, 滕光辉, 付为森, 等. 基于机器视觉的猪体体尺测点提取算法与应用[J]. 农业工程学报, 2013, 29(2): 161-168.
	LIU T H, TENG G H, FU W S, et al. Extraction algorithms and applications of pig body size measurement points based on computer vision[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(2): 161-168. (in Chinese with English abstract)
[15]	李卓, 杜晓冬, 毛涛涛, 等. 基于深度图像的猪体尺检测系统[J]. 农业机械学报, 2016, 47(3): 311-318.
	LI Z, DU X D, MAO T T, et al. Pig dimension detection system based on depth image[J]. Transactions of the Chinese Society for Agricultural Machinery, 2016, 47(3): 311-318. (in Chinese with English abstract)
[16]	刘增金. 基于质量安全的中国猪肉可追溯体系运行机制研究: 以北京市为例[D]. 北京: 中国农业大学, 2015.
	LIU Z J. Study on operating mechanism of pork traceability system in China based on food safety[D]. Beijing: China Agricultural University, 2015. (in Chinese with English abstract)
[17]	DAUGMAN J G. High confidence visual recognition of persons by a test of statistical independence[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(11): 1148-1161.
[18]	DAUGMAN J. The importance of being random: statistical principles of iris recognition[J]. Pattern Recognition, 2003, 36(2): 279-291.
[19]	DAUGMAN J. New methods in iris recognition[J]. IEEE Transactions on Systems, Man, and Cybernetics Part B, Cybernetics, 2007, 37(5): 1167-1175.
[20]	WILDES R P, ASMUTH J C, GREEN G L, et al. A system for automated iris recognition[C]// Proceedings of 1994 IEEE Workshop on Applications of Computer Vision. Sarasota, FL, USA. IEEE Comput. Soc. Press, 1994: 121-128.
[21]	WILDES R P, ASMUTH J C, GREEN G L, et al. A machine-vision system for iris recognition[J]. Machine Vision and Applications, 1996, 9(1): 1-8.
[22]	王琪, 张铁, 张晓梦, 等. 基于SIFT和SDM的虹膜定位方法[J]. 东北大学学报(自然科学版), 2017, 38(2): 180-184.
	WANG Q, ZHANG T, ZHANG X M, et al. Iris localization method based on SIFT and SDM[J]. Journal of Northeastern University(Natural Science), 2017, 38(2): 180-184. (in Chinese with English abstract)
[23]	刘帅, 刘元宁, 朱晓冬, 等. 基于分块搜索的虹膜定位算法[J]. 计算机工程与应用, 2018, 54(18): 212-217.
	LIU S, LIU Y N, ZHU X D, et al. Iris location algorithm based on partitioning search[J]. Computer Engineering and Applications, 2018, 54(18): 212-217. (in Chinese with English abstract)
[24]	孙正, 陈兆学, 李晓萌. 基于单位扇环灰度的虹膜定位算法[J]. 光学技术, 2019, 45(2): 228-233.
	SUN Z, CHEN Z X, LI X M. Iris location algorithm based on method of gray value of unit sector area[J]. Optical Technique, 2019, 45(2): 228-233. (in Chinese with English abstract)
[25]	SUZAKI M, YAMAKITA O, HORIKAWA S I, et al. A horse identification system using biometrics[J]. Systems and Computers in Japan, 2001, 32(14): 12-23.
[26]	LU Y, HE X F, WEN Y, et al. A new cow identification system based on iris analysis and recognition[J]. International Journal of Biometrics, 2014, 6(1): 18.
[27]	盛大玮, 何孝富, 吕岳. 基于最小二乘原理的牛眼虹膜分割方法[J]. 中国图象图形学报, 2009, 14(10): 2132-2136.
	SHENG D W, HE X F, LU Y. A cattle iris segmentation method based on least square principle[J]. Journal of Image and Graphics, 2009, 14(10): 2132-2136. (in Chinese with English abstract)
[28]	孔强, 赵林度. 虹膜识别在肉类食品安全追溯系统中的应用及关键技术研究[J]. 中国安全科学学报, 2009, 19(3): 155-160.
	KONG Q, ZHAO L D. Research on the application of iris recognition in meat-food supply chain management[J]. China Safety Science Journal(CSSJ), 2009, 19(3): 155-160. (in Chinese with English abstract)
[29]	夏胜吾. 林麝虹膜识别关键技术研究[D]. 成都: 电子科技大学, 2015.
	XIA S W. The research on key technique of iris recognition on Moschus berezovskii[D]. Chengdu: University of Electronic Science and Technology of China, 2015. (in Chinese with English abstract)
[30]	IBRAHIM M T, KHAN T M, KHAN S A, et al. Iris localization using local histogram and other image statistics[J]. Optics and Lasers in Engineering, 2012, 50(5): 645-654.

编辑推荐

Metrics

阅读次数

全文

311

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	9	0	0	302

来源	本网站	其他网站

次数	262	49
比例	84%	16%

摘要

117

最新录用	在线预览	正式出版

0	0	116

	来源	本网站

	次数	117
	比例	100%

生猪虹膜快速定位算法研究

Research on fast localization algorithm of pig iris

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 30

相关文章 7

编辑推荐

Metrics

本文评价

[1]	刘苇, 陶建平. 畜禽禁养区政策何以影响中国生猪市场稳定?[J]. 浙江农业学报, 2023, 35(5): 1195-1210.
[2]	李斌, 刘东阳, 时国龙, 慕京生, 徐浩然, 辜丽川, 焦俊. 基于改进YOLOv4模型的群养生猪姿态检测[J]. 浙江农业学报, 2023, 35(1): 215-225.
[3]	李小刚, 熊涛. 中国规模生猪养殖效率测度及其补贴政策效益评价研究[J]. 浙江农业学报, 2019, 31(7): 1184-1192.
[4]	冷碧滨, 吉雪强, 曾颢, 涂国平. 中国大规模生猪养殖技术效率研究[J]. 浙江农业学报, 2018, 30(6): 1082-1088.
[5]	付莲莲, 翁贞林, 张雅燕. 江西省生猪价格波动的成因及其预警分析——基于灰色关联和LS-SVM模型[J]. 浙江农业学报, 2016, 28(9): 1624-1630.
[6]	王德鑫1，黄珂2，郑炎成1，*，李谷成1. 中国规模生猪养殖效率测度及其区域差异性研究——基于DEAMalmquist指数方法[J]. 浙江农业学报, 2016, 28(7): 1262-.
[7]	黄莉莉;朱奇彪;米松华. 浙江省生猪产业带头人知识更新需求实证研究[J]. , 2013, 25(3): 0-678.