Correlation Analysis Between AI and Manual Measurement for Morphological Traits of Two Cyprinus carpio L. Strains

doi:10.11924/j.issn.1000-6850.casb2024-0057

Abstract

Abstract:

The morphology of fish is an important population resource for artificial breeding, functional gene localization, as well as aquaculture and ecological research. The common carp (Cyprinus carpio L.) is one of the important freshwater fish species farmed in China. Natural and artificial selection have resulted in a great diversity of phenotypes among different varieties of carp. In recent years, with the rapid development of imaging technology, computational capabilities, and hardware devices, non-destructive measurement methods based on machine vision have rapidly emerged, making it an efficient and repeatable method for batch inspection of fish bodies. In order to test the accuracy of AI measurement for fish phenotypic traits, manual measurement and AI measurement were used in two ways, respectively, for the Cyprinus carpio yuankiang and the Cyprinus carpio var. Jinbei, which have significant differences in phenotypic indices. A total of 204 fish from two carp populations were selected, and 10 linear, circular, and spatial traits including total length, body length, body depth, body thickness, head length, caudal peduncle length, caudal peduncle depth, snout length, eye diameter and interorbital width were measured and compared. The results show: (1) In the two populations of Cyprinus carpio yuankiang and Cyprinus carpio var. Jinbei, for the measurement of 10 phenotypic traits, compared to manual measurement, the AI measurement results are generally larger. In the phenotypic index, there is no significant difference between the two measurement methods in the body width index (body thickness/body length), head length index (head length/body length), and caudal fin index (caudal peduncle length/body length), while the two methods show significant differences in the results of the body depth index (body depth/body length). (2) In the populations of Cyprinus carpio yuankiang and Cyprinus carpio var. Jinbei, a correlation and consistency analysis of the two measurement methods found that for a total of 6 traits including total length, body length, body depth, body thickness, head length, and interorbital width, the two methods show high consistency (r>0.85). (3) In the consistency analysis of the repeatability measurement of the two measurement methods, it was found that both manual measurement and AI measurement show good consistency (r>0.85), but the consistency of manual measurement is slightly higher than that of AI measurement. Overall, the improvement of the accuracy of AI measurement can speed up the work efficiency of measuring linear phenotypic traits such as total length and the speed of selective breeding, but the accuracy of measuring circular and spatial phenotypic traits needs to be further improved.

Key words: manual measurement, AI measurement, Cyprinus carpio yuankiang, Cyprinus carpio var. Jinbei

MA Ziyao, PAN Hong, WANG Kaikuo, CHEN Yingjie, CAO Yiming, SUN Xiaoqing, ZHANG Yan. Correlation Analysis Between AI and Manual Measurement for Morphological Traits of Two Cyprinus carpio L. Strains[J]. Chinese Agricultural Science Bulletin, 2024, 40(14): 157-164.

Figures/Tables 7

References 27

[1]	CHRISTOPHE B, BARANGE M, SUBASINGHE R, et al. Feeding 9 billion by 2050-putting fish back on the menu[J]. Food security, 2015, 7(2):261-274. doi: 10.1007/s12571-015-0427-z URL
[2]	TIAN C, LI L, LIANG X F, et al. Identification of differentially expressed genes associated with differential body size in mandarin fish (Siniperca chuatsi)[J]. Genetica, 2016, 144(4):445-455. doi: 10.1007/s10709-016-9913-2 pmid: 27393605
[3]	MABEE P, BALHOFF J P, DAHDUL W M, et al. 500,000 fish phenotypes: The new informatics landscape for evolutionary and developmental biology of the vertebrate skeleton[J]. Journal of applied ichthyology, 2012, 28(3):300-305. pmid: 22736877
[4]	WALKER J A. A general model of functional constraints on phenotypic evolution[J]. The American naturalist, 2007, 170(5):681-689. pmid: 17926290
[5]	FERNANDES A F A, TURRA E M, ALVARENGA R R D, et al. Deep Learning image segmentation for extraction of fish body measurements and prediction of body weight and carcass traits in Nile tilapia[J]. Computers and electronics in agriculture, 2020, 170:105274. doi: 10.1016/j.compag.2020.105274 URL
[6]	MILLA S, PASQUET A, MOHAJER L E, et al. How domestication alters fish phenotypes[J]. Reviews in aquaculture, 2021, 13(1):388-405. doi: 10.1111/raq.v13.1 URL
[7]	GJEDREM T, ROBINSON N. Advances by selective breeding for aquatic species: a review[J]. Agricultural sciences, 2014, 5(12):1152-1158. doi: 10.4236/as.2014.512125 URL
[8]	MUÑOZ-BENAVENT P, PUIG-PONS V, ANDREU-GARCÍA G, et al. Automatic bluefin tuna sizing with a combined acoustic and optical sensor[J]. Sensors, 2020, 20(18):5294. doi: 10.3390/s20185294 URL
[9]	ALABA S Y, NABI M M, SHAH C, et al. Class-aware fish species recognition using deep learning for an imbalanced dataset[J]. Sensors, 2022, 22(21):8268. doi: 10.3390/s22218268 URL
[10]	MATHIASSEN J R, MISIMI E, STVIK S O, et al. Computer vision in the fish industry-science direct[J]. Computer vision technology in the food and beverage industries, 2012, 81: 352-378.
[11]	ZHANG L, WANG J, DUAN Q. Estimation for fish mass using image analysis and neural network[J]. Computers and electronics in agriculture, 2020, 173:105439. doi: 10.1016/j.compag.2020.105439 URL
[12]	陈子桂, 王培培, 覃俊奇, 等. 广西野生鲤与建鲤的遗传多样性分析[J]. 淡水渔业, 2018, 48(3):3-6.
[13]	李龑, 姜晓娜, 葛彦龙, 等. 温度对两种鲤耗氧率、排氨率及窒息点的影响[J]. 淡水渔业, 2023, 53(2):61-68.
[14]	许艺兰, 陈忠, 覃俊奇, 等. 全州禾花鲤主要生长性状的遗传参数估计[J]. 广西科学, 2022, 29(4):801-808.
[15]	马冬梅, 朱华平, 樊佳佳, 等. 软骨与正常华南鲤肌肉营养成分的比较分析[J]. 大连海洋大学学报, 2019, 34(3):381-386.
[16]	JI D, SU X, YAO J, et al. Genetic diversity and genetic differentiation of populations of Golden-Backed Carp (Cyprinus carpio var.Jinbei) in traditional rice fields in Guizhou, China[J]. Animals, 2022, 12(11):1377. doi: 10.3390/ani12111377 URL
[17]	赵亚辉, 孙智闲. 鲤科鱼类形态学测度和物种描述规范——以鮈亚科鱼类为例[J]. Bio-protocol, 2021:1010622.
[18]	DEEP B V, DASH R. Underwater fish species recognition using deep learning techniques[C]. 2019 6th international conference on signal processing and integrated networks (SPIN). IEEE, 2019:665-669.
[19]	HNIN T T, LYNN K T. Fish classification based on robust features selection using machine learning techniques[C]. Genetic and evolutionary computing: proceedings of the ninth international conference on genetic and evolutionary computing, August 26-28,2015,Yangon, Myanmar-Volume 1.Springer international publishing, 2016:237-245.
[20]	SHORTIS M R, RAVANBAKHSH M, SHAFAIT F, et al. Progress in the automated identification, measurement, and counting of fish in underwater image sequences[J]. Marine technology society journal, 2016, 50(1):4-16.
[21]	IVERSEN M, FINSTAD B, MCKINLEY R S, et al. The efficacy of metomidate, clove oil, Aqui-STM and Benzoak as anaesthetics in Atlantic salmon (Salmo salar L.) smolts, and their potential stress-reducing capacity[J]. Aquaculture, 2003, 221(1-4):549-566. doi: 10.1016/S0044-8486(03)00111-X URL
[22]	HOUSTON R D, BEAN T P, MACQUEEN D J, et al. Harnessing genomics to fast-track genetic improvement in aquaculture[J]. Nature reviews genetics, 2020, 21(7):389-409. doi: 10.1038/s41576-020-0227-y pmid: 32300217
[23]	AL-JUBOURI Q, AL-NUAIMY W, AL-TAEE M, et al. Towards automated length-estimation of free-swimming fish using machine vision[C]. 2017 14th international multi-conference on systems, signals & devices (SSD). IEEE, 2017:469-474.
[24]	HAO M, YU H, LI D. The measurement of fish size by machine vision-a review[C]. Computer and computing technologies in agriculture IX:9th IFIP WG 5.14 international conference, CCTA 2015, Beijing, China, September 27-30, 2015, revised selected papers, Part II 9. Springer international publishing, 2016:15-32.
[25]	HONG H, YANG X, YOU Z, et al. Visual quality detection of aquatic products using machine vision[J]. Aquacultural engineering, 2014, 63(63):62-71. doi: 10.1016/j.aquaeng.2014.10.003 URL
[26]	LIAO Y H, ZHOU C W, LIU W Z, et al. 3Dphenofish: Application for two-and three-dimensional fish morphological phenotype extraction from point cloud analysis[J]. Zoological research, 2021, 42(4):492.
[27]	HU X, LIU Y, ZHAO Z, et al. Real-time detection of uneaten feed pellets in underwater images for aquaculture using an improved YOLO-V4 network[J]. Computers and electronics in agriculture, 2021, 185(8):106135. doi: 10.1016/j.compag.2021.106135 URL

表型性状	测量方法	元江鲤	金背鲤
全长	M	329.62±38.89	235.61±36.83
全长	A	343.06±39.46	244.99±37.97
体长	M	278.97±35.84	194.14±32.26
体长	A	289.87±34.62	200.48±32.94
体高	M	80.05±10.41	59.78±11.15
体高	A	91.96±11.34	68.66±12.06
体厚	M	41.88±5.70	32.38±7.15
体厚	A	44.79±5.75	33.76±6.44
头长	M	69.85±8.27	51.47±10.15
头长	A	71.84±7.59	53.49±8.35
尾柄长	M	49.45±6.52	33.99±6.69
尾柄长	A	51.31±7.23	34.86±6.02
尾柄高	M	29.79±4.75	21.77±4.87
尾柄高	A	43.49±6.01	30.39±5.93
吻长	M	24.79±3.86	17.70±4.40
吻长	A	21.44±2.90	15.91±3.52
眼径	M	9.52±1.49	7.21±1.16
眼径	A	12.56±1.67	10.49±1.20
眼间距	M	33.52±4.29	24.57±5.30
眼间距	A	32.90±4.02	24.59±4.38
体高/体长	M	0.29±0.020	0.31±0.029
体高/体长	A	0.32±0.015	0.34±0.022
体厚/体长	M	0.15±0.013	0.17±0.017
体厚/体长	A	0.15±0.010	0.17±0.012
头长/体长	M	0.25±0.020	0.27±0.025
头长/体长	A	0.25±0.013	0.27±0.017
尾柄长/体长	M	0.18±0.017	0.18±0.018
尾柄长/体长	A	0.18±0.011	0.17±0.015

表型性状	测量方法	元江鲤	金背鲤
全长	M	329.62±38.89	235.61±36.83
全长	A	343.06±39.46	244.99±37.97
体长	M	278.97±35.84	194.14±32.26
体长	A	289.87±34.62	200.48±32.94
体高	M	80.05±10.41	59.78±11.15
体高	A	91.96±11.34	68.66±12.06
体厚	M	41.88±5.70	32.38±7.15
体厚	A	44.79±5.75	33.76±6.44
头长	M	69.85±8.27	51.47±10.15
头长	A	71.84±7.59	53.49±8.35
尾柄长	M	49.45±6.52	33.99±6.69
尾柄长	A	51.31±7.23	34.86±6.02
尾柄高	M	29.79±4.75	21.77±4.87
尾柄高	A	43.49±6.01	30.39±5.93
吻长	M	24.79±3.86	17.70±4.40
吻长	A	21.44±2.90	15.91±3.52
眼径	M	9.52±1.49	7.21±1.16
眼径	A	12.56±1.67	10.49±1.20
眼间距	M	33.52±4.29	24.57±5.30
眼间距	A	32.90±4.02	24.59±4.38
体高/体长	M	0.29±0.020	0.31±0.029
体高/体长	A	0.32±0.015	0.34±0.022
体厚/体长	M	0.15±0.013	0.17±0.017
体厚/体长	A	0.15±0.010	0.17±0.012
头长/体长	M	0.25±0.020	0.27±0.025
头长/体长	A	0.25±0.013	0.27±0.017
尾柄长/体长	M	0.18±0.017	0.18±0.018
尾柄长/体长	A	0.18±0.011	0.17±0.015

表型性状	相关系数		组内相关系数
表型性状	元江鲤	金背鲤	元江鲤	金背鲤
全长	0.957	0.988	0.978	0.994
体长	0.905	0.982	0.950	0.991
体高	0.965	0.907	0.980	0.950
体厚	0.902	0.950	0.948	0.972
头长	0.851	0.908	0.918	0.943
尾柄长	0.726	0.730	0.839	0.841
尾柄高	0.797	0.940	0.873	0.959
吻长	0.592	0.790	0.725	0.870
眼径	0.339	0.523	0.504	0.686
眼间距	0.853	0.907	0.919	0.942

表型性状	相关系数		组内相关系数
表型性状	元江鲤	金背鲤	元江鲤	金背鲤
全长	0.957	0.988	0.978	0.994
体长	0.905	0.982	0.950	0.991
体高	0.965	0.907	0.980	0.950
体厚	0.902	0.950	0.948	0.972
头长	0.851	0.908	0.918	0.943
尾柄长	0.726	0.730	0.839	0.841
尾柄高	0.797	0.940	0.873	0.959
吻长	0.592	0.790	0.725	0.870
眼径	0.339	0.523	0.504	0.686
眼间距	0.853	0.907	0.919	0.942

表型性状	测量方法	第一组	第二组	第三组	组内相关系数
全长	M	7.24±0.40	7.23±0.41	7.12±0.46	1.000
全长	A	7.81±0.62	7.84±0.70	7.81±0.62	0.998
体长	M	5.84±0.29	5.85±0.29	5.84±0.29	1.000
体长	A	6.07±0.35	6.13±0.32	6.18±0.38	0.993
体高	M	1.63±0.057	1.63±0.057	1.63±0.057	1.000
体高	A	1.76±0.070	1.84±0.084	1.81±0.15	0.968
体厚	M	0.75±0.038	0.74±0.038	0.74±0.038	1.000
体厚	A	0.98±0.045	1.07±0.052	1.01±0.070	0.973
头长	M	1.78±0.074	1.77±0.075	1.78±0.074	1.000
头长	A	1.77±0.085	1.82±0.091	1.86±0.13	0.988
尾柄长	M	1.28±0.014	1.28±0.014	1.28±0.013	0.999
尾柄长	A	1.14±0.045	1.22±0.044	1.19±0.075	0.896
尾柄高	M	0.78±0.0091	0.77±0.0091	0.77±0.0091	1.000
尾柄高	A	0.87±0.027	0.91±0.055	0.86±0.054	0.933
吻长	M	0.63±0.026	0.63±0.026	0.62±0.026	1.000
吻长	A	0.61±0.027	0.62±0.032	0.63±0.039	0.987
眼径	M	0.49±0.0084	0.49±0.0084	0.49±0.0084	0.999
眼径	A	0.47±0.024	0.45±0.11	0.46±0.087	0.892
眼间距	M	5.18±2.52	5.17±2.52	5.18±2.51	1.000
眼间距	A	5.35±2.71	5.45±2.66	5.44±2.64	0.998