基于图像识别技术研究不同海区三疣梭子蟹甲壳白色斑纹特征及蜕壳前后斑纹特征的变化

为进行三疣梭子蟹外观特征的研究,本研究通过计算机视觉技术建立三疣梭子蟹背部白色斑纹评估方法,经人工对比验证其准确性达100%。在此基础上,对来自海域的30只三疣梭子蟹平均体质量(2.8±0.56)g]进行跟踪观察,发现蜕壳前后白色斑纹数量和位置保持不变,而白色斑纹面积和斑纹区域面积则会随着蜕壳后蟹壳面积的增加而扩大;蜕壳后,白色斑纹面积增加89.33%±8.61%,斑纹区域面积增加90.51%±7.95%,蟹壳面积增加94.66%±8.26%,均显著正相关。为进一步研究不同海区梭子蟹白色斑纹分布特征,对来自朝鲜、中国辽宁和浙江等不同海区的三疣梭子蟹进行白色斑纹个数(N)、白色斑纹面积(S1)、斑纹区域面积(S2)、白色斑纹面积百分比(R1)、斑纹区域面积百分比(R2)和密度(D)等6项参数分析,结果发现,不同海区三疣梭子蟹斑纹性状存在显著特点,朝鲜海区呈现斑纹小、分布面积少、占蟹壳总面积比例低的特点;辽宁海区呈现斑纹小、分布面积多、占蟹壳总面积比例高的特点;浙江海区呈现斑纹大、分布面积少、占蟹壳总面积比例低的特点。本研究将计算机视觉技术应用于水产养殖研究,通过建立评估参数阐明三疣梭子蟹白色斑纹的生长规律,揭示了不同群体的三疣梭子蟹白色斑纹具有地理多样性的特征。

Development of the recognition method based on computer vision for white spots in the carapace of Portunus trituberculatus and research on its characteristics

To study the morphological characteristics of white spots in the carapace of Portunus trituberculatus, a computer vision-based recognition method was developed in this paper with an accuracy of 100%. The molting process of thirty crabs from sea area (body weight: 2.8±0.56g) was tracked to investigate the growth changes of white spots in the carapace of P. trituberculatus. Results showed that the number and relative position of white spots had no significant changes after molting, however, the white spot area and its distribution area grew with the carapace. After molting, the white spot area increased 89.33±8.61%, the distribution area increased 90.51±7.95%, and the carapace area increased 94.66±8.26%. P. trituberculatus from North Korean, Liaoning and Xiangshan were collected to compare six parameters related to white spot trait in the carapace, results showed significant geographical differences. The white spot trait of North Korean had the feature of small spots, little distribution area and accounted for a low proportion of the carapace area. The trait of Liaoning had the feature of small spots, larger distribution area and accounted for a high proportion of the carapace area. While the trait of Xiangshan had the feature of big spots, little distribution area and accounted for a low proportion of the carapace area. This study developed the recognition method based on computer vision for white spots in the carapace of P. trituberculatus, illustrated the growth feature of this trait, and found significant geographical differences among three populations.