[1]冯国富,刘亚蕊,陈明,等.基于DCP算法增强暗纹东方鲀胚胎图像[J].江苏农业学报,2021,(06):1493-1500.[doi:doi:10.3969/j.issn.1000-4440.2021.05.018]
　FENG Guo-fu,LIU Ya-rui,CHEN Ming,et al.Image enhancement of Takifugu obscurus embryos based on DCP algorithm[J].,2021,(06):1493-1500.[doi:doi:10.3969/j.issn.1000-4440.2021.05.018]
点击复制

基于DCP算法增强暗纹东方鲀胚胎图像()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2021年06期
页码:
1493-1500
栏目:
畜牧兽医·水产养殖
出版日期:
2021-12-30

文章信息/Info

Title:
Image enhancement of Takifugu obscurus embryos based on DCP algorithm
作者:
冯国富1; 2; 刘亚蕊1; 2; 陈明1; 2; 翁正1; 2; 王耀辉3
（1.上海海洋大学信息学院，上海201306；2.上海海洋大学，农业农村部渔业信息重点实验室，上海201306；3.南通龙洋水产有限公司，江苏南通226634)
Author(s):
FENG Guo-fu1; 2; LIU Ya-rui1; 2; CHEN Ming1; 2; WENG Zheng1; 2; WANG Yao-hui3
（1. School of Information, Shanghai Ocean University， Shanghai 201306， China；2.Shanghai Ocean University， Key Laboratory of Fishery Information, Ministry of Agriculture and Rural Affairs， Shanghai 201306， China；3.Nantong Longyang Aquatic Products Co., Ltd.， Nantong 226634， China)
关键词:
暗纹东方鲀; 胚胎检测; 暗通道先验; 图像增强; YOLOv5网络
Keywords:
Takifugu obscurus; embryos detection; dark channel prior; image enhancement; YOLOv5 network
分类号:
S961.2
DOI:
doi:10.3969/j.issn.1000-4440.2021.05.018
文献标志码:
A
摘要:
为了能够精准地识别出暗纹东方鲀胚胎发育的各个时期，提高人工繁殖和杂交育种的成活率，采用暗通道先验（DCP）算法和它的2个反演以及推导，对胚胎图像进行增强。推导出4种透射率，再结合像素值的缩小和放大最终生成8种增强效果。其中图像增亮与图像增暗结合的A+X组合算法效果最佳，增强后的图像细节信息更加丰富，各个时期的特征更加清晰。选用多目标检测算法YOLOv5网络对图像中的胚胎进行提取和分类。结果表明，增强后图像分类结果的准确率比原始图像提高4.5%，损失函数降低0.16%。
Abstract:
In order to accurately identify each stage of embryonic development of Takifugu obscurus and improve the survival rate of artificial reproduction and cross breeding, dark channel prior (DCP) algorithm and its two inversions and derivation were used to enhance embryo image. Among them, four kinds of transmittances were derived in this study, and eight kinds of enhancement effects were finally generated by combining the reduction and amplification of pixel values. Through comparative analysis, A+X combination algorithm combining image brightening and image darkening had the best effect. The enhanced image details were more abundant, and the features of each period were clearer. The YOLOv5 network, a multi-target detection algorithm, was selected to extract and classify embryos in the images. The results showed that the classification accuracy of enhanced image was 4.5% higher than that of original image, and the loss function was 0.16% lower.

参考文献/References:

[1]吴剑峰,华元渝. 家化暗纹东方鲀全人工繁殖技术[J].水产养殖,2002(5):7-9.
[2]李子奇,成美玲,吴玉萍,等. 鞍带石斑鱼(♀)×云纹石斑鱼(♂)杂交后代早期发育及正反交后代生长特性[J]. 水产学报, 2020, 44(3): 436-446.
[3]崔文耀,周丽青,杨继辉, 等. 四带小鲃胚胎发育及系统进化分析[J]. 水产学报, 2020, 44(8): 1286-1295.
[4]谢刚,陈焜慈,胡隐昌,等. 倒刺鲃胚胎发育与水温和盐度的关系[J].大连水产学院学报, 2003,18(2):95-98.
[5]杨州,华洁,陈晰. 暗纹东方鲀胚胎发育历期与温度的关系[J].淡水渔业,2004(2):6-8.
[6]JOBSON D J, RAHMAN Z, WOODELL G A. A multiscale retinex for bridging the gap between color images and the human observation of scenes[J]. IEEE Transactions on Image Processing, 2002, 6(7):965-976.
[7]SRINIVASAN S, BALRAM N. Adaptive contrast enhancement using local region stretching[C]//SATYENDRA K, IIT K. Proceedings of the 9th Asian symposium on information display. New Delhi, India：ASID, 2006: 152-155.
[8]赵馨宇,黄福珍. 基于双通道先验和光照图引导滤波的图像增强[J].激光与光电子学进展,2021,58(8):53-62.
[9]徐浩,谭一博,刘博文,等. 基于超像素和暗通道先验的图像去雾复原方法[J].中国海洋大学学报(自然科学版),2020,50(10):118-124.
[10]HE K, SUN J, TANG X. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 33(12): 2341-2353.
[11]HE K, SUN J,TANG X. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013,35(6): 1397-1409.
[12]廖娟,陈民慧,汪鹞,等. 基于双重Gamma校正的秧苗图像增强算法[J].江苏农业学报,2020,36(6):1411-1418.
[13]LEE S, YUN S, NAM J H, et al. A review on dark channel prior based image dehazing algorithms[J]. Eurasip Journal on Image & Video Processing, 2016, 2016(1): 1-23.
[14]刘玲. 基于暗通道先验的图像去雾改进算法研究[D].重庆:重庆大学,2019.
[15]GALDRAN A, ALVAREZ-GILA A, BRIA A, et al. On the duality between retinex and image dehazing[C]//IEEE. 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR). Salt Lake City, UT, USA:IEEE, 2018:8212-8221.
[16]SAVELLI B, BRIA A, GALDRAN A, et al. Illumination Correction by Dehazing for Retinal Vessel Segmentation[C]//IEEE. 2017 IEEE 30th international symposium on computer-based medical systems (CBMS). Greece:IEEE, 2017: 219-224.
[17]GAUDIO A, SMAILAGIC A, AURLIO C. Enhancement of retinal fundus images via pixel color amplification[J]. Lecture Notes in Computer Science, 2020,12132:299-312.
[18]胡亚丽,华元渝. 暗纹东方鲀胚胎发育的观察[J].南京师范大学学报(自然科学版), 1995,18(4):139-144.
[19]刘俊果,宋炜,蒋科技,等. 棘头梅童鱼胚胎发育和仔鱼形态观察[J].海洋渔业,2018,40(6):691-702.
[20]易祖盛,陈湘粦,王春,等. 倒刺鲃胚胎发育的研究[J].中国水产科学,2004(1):65-69.
[21]侯雪宁. 暗纹东方鲀胚胎发育相关miRNA表达差异研究[D].青岛:中国海洋大学,2015.
[22]周立斌,叶卫. 长臀鮠胚胎发育的研究[J].水产科学,2007(1):31-34.
[23]周治,黄若兰,刘文慧,等. 基于暗通道和色彩校正的水下图像增强方法[J].大众标准化,2020(23):168-169.
[24]王红茹,张玲,王佳,等. 基于改进的同态滤波和Retinex的水下图像增强的算法研究[J].电光与控制,2021,28(5):32-35.
[25]KUZNETSOVA A, MALEVA T, SOLOVIEV V. Detecting apples in orchards using YOLOv3 and YOLOv5 in general and close-up images[C]//HAN M, QIN S T, ZHANG N A. International symposium on neural networks. Cham: Springer, 2020: 233-243.

备注/Memo

备注/Memo:
收稿日期：2021-03-13基金项目：江苏省现代农业产业关键技术创新项目[CX（20）2028]作者简介：冯国富(1971-)，男，河南新乡人，博士，副教授，研究方向为嵌入式技术研究。通讯作者：陈明，(E-mail)mchen@shou.edu.cn
更新日期/Last Update: 2022-01-07