A novel nondestructive detection approach for seed cotton lint percentage using deep learning

Background The lint percentage of seed cotton is one of the most important parameters for evaluating seed cotton quality and affects its price.The traditional measuring method of lint percentage is labor-intensive and time-consuming;thus,an efficient and accurate measurement method is needed.In recent years,classification-based deep learning and computer vision have shown promise in solving various classification tasks.Results In this study,we propose a new approach for detecting the lint percentage using MobileNetV2 and transfer learning.The model is deployed on a lint percentage detection instrument,which can rapidly and accurately determine the lint percentage of seed cotton.We evaluated the performance of the proposed approach using a dataset comprising 66924 seed cotton images from different regions of China.The results of the experiments showed that the model with transfer learning achieved an average classification accuracy of 98.43%,with an average precision of 94.97%,an average recall of 95.26%,and an average F1-score of 95.20%.Furthermore,the proposed classification model achieved an average accuracy of 97.22%in calculating the lint percentage,showing no significant difference from the performance of experts(independent-sample t-test,t=0.019,P=0.860).Conclusion This study demonstrated the effectiveness of the MobileNetV2 model and transfer learning in calculating the lint percentage of seed cotton.The proposed approach is a promising alternative to traditional methods,providing a rapid and accurate solution for the industry.

Fiber damage of machine-harvested cotton before ginning and after lint cleaning

Machine harvesting increases the foreign matter content of seed cotton. Excessive cleaning causes fiber damage and economic loss. Most trading companies in the Xinjiang Uygur Autonomous Region, China have indicated reluctance to use machine-harvested cotton. The first objective was to determine how the fiber quality was affected by the ginning and lint cleaning and how the fiber damage during levels of lint cleaning changed. The second objective was to determine the optimum number of lint cleaners for machine-harvested cotton based on fiber damage. Cotton samples were collected from 13 fields and processed in seven ginneries between 2013 and 2015. The results indicated that ginning and lint cleaning didn＇t have significant effect on fiber strength and significantly affected both fiber length and short fiber index. Fiber length was reduced by more than 1.00 mm from six of 13 fields after lint cleaning, then the damage rate on short fiber index from 11 of 13 fields was more than 20%. The third lint cleaning caused great fiber damage, reducing fiber length by 0.35 mm and increasing short fiber index by 0.65%. So, the lint should be cleaned by one lint cleaner in the Xinjiang, however, the stage of lint cleaning was sometimes omitted when the foreign matter content of lint was little.

Genetics and Expression of the Brown Lint Gene in Colored Cotton

The major cotton grown commercially in the world is white lint,but recently many people prefer to have garments made by natural colored cotton.This can be used directly in textile industries,avoiding the complicated and unsafe processes of bleaching and dying,and thus it is eco-friendly.However,little is known about the heredity of the colored lint gene in colored cotton.In the present study,

Assembly and phylogenomic analysis of cotton mitochondrial genomes provide insights into the history of cotton evolution

Cotton is a major crop that provides the most important renewable textile fibers in the world.Studies of the taxonomy and evolution of cotton species have received wide attentions,not only due to cotton’s economic value but also due to the fact that Gossypium is an ideal model system to study the origin,evolution,and cultivation of polyploid species.Previous studies suggested the involvement of mitochondrial genome editing sites and copy number as well as mitochondrial functions in cotton fiber elongation.Whereas,with only a few mitogenomes assembled in the cotton genus Gossypium,our knowledge about their roles in cotton evolution and speciation is still scarce.To close this gap,here we assembled 20 mitogenomes from 15 cotton species spanning all the cotton clades(A–G,K,and AD genomes)and 5 cotton relatives using short and long sequencing reads.Systematic analyses uncovered a high level of mitochondrial gene sequence conservation,abundant sequence repeats and many insertions of foreign sequences,as well as extensive structural variations in cotton mitogenomes.The sequence repeats and foreign sequences caused significant mitogenome size inflation in Gossypium and its close relative Kokia in general,while there is no significant difference between the lint and fuzz cotton mitogenomes in terms of gene content,RNA editing,and gene expression level.Interestingly,we further revealed the specific presence and expression of two novel mitochondrial open reading frames(ORFs)in lint-fiber cotton species.Finally,these structural features and novel ORFs help us gain valuable insights into the history of cotton evolution and polyploidization and the origin of species producing long lint fibers from a mitogenomic perspective.

Study of Cotton Seeds as a Processing Material

The purpose of this research is to improve the qualitative and quantitative indicators of fiber, lint and seeds by improving the technology of preparing cotton seeds for processing. The state of the seeds after the gin was studied and their division into fractions according to the degree of pubescence was recommended, the probabilities of the seeds emerging from the gin with varying degrees of pubescence were investigated, the geometric sizes and shapes of cotton seeds were studied. It has been established that when seeds come out of gin, they have different pubescence. The conditional movement of seeds without separation from the surface has been determined;found a formula describing the movement of seeds without detaching from the surface;the movement of seeds in a micro-flight is determined;the sizes of the cells of the mesh surface were determined as a function of d_c, α and on the speed of seed movement. The aim of the research work is to increase the yield of cotton fiber by improving the processing technology of germinated seeds, to improve the quality indicators of seeds and lint. In order to achieve this goal, a mesh surface device was created to sort the seeds into fractions. Sorting technology was developed on this device and operating modes were determined. In addition, the law of surface distribution of the fractions separated from the cotton stream moving along the surface of the net was determined, and based on the results of practical and theoretical research, a mode of sorting of cotton seeds was developed.

海陆杂交长绒棉棉铃、纤维品质性状及相关性分析

【目的】明确海陆杂交长绒棉的棉铃、纤维品质性状及相关性,为选育高产海陆杂交长绒棉提供参考依据。【方法】以自主选育的抗虫陆地棉种质系为母本、生产上推广应用的新疆长绒海岛棉品种为父本,配制海陆杂交棉新组合,分析23个海陆杂交棉组合F1代的棉铃、纤维品质性状以及相关性。【结果】23个海陆杂交棉组合F1代单铃重变幅为3.7~5.0 g,单铃重超过4.2 g的组合有12个,变异系数为9.0%;衣分变幅为20.1%~36.7%,衣分超过30.0%的组合有5个,变异系数为10.7%。不同组合F1代纤维长度变幅为34.5~38.5 mm,纤维长度在35.0 mm以上的组合有22个,变异系数为2.6%;纤维比强度变幅为34.8~41.8 cN/tex,纤维比强度超过39.0 cN/tex的组合有9个,变异系数为5.3%;马克隆值变幅为2.8~4.2,马克隆值A级的组合有10个,变异系数为11.8%。海陆杂交棉的单铃重与不孕籽率呈极显著负相关(r=-0.683**)、与每囊粒数呈极显著正相关(r=0.660**)、与每铃囊数呈显著正相关(r=0.495*);海陆杂交棉的纤维整齐度与纤维长度、纤维比强度呈极显著正相关(r=0.578**、r=0.639**),与伸长率呈显著正相关(r=0.506*);衣分与纤维长度呈显著负相关(r=-0.475*)。在23个海陆杂交棉组合中,W042×新海53号、W046×新海54号、W047×新海54号的棉铃性状与纤维品质性状已呈现同步改良。【结论】利用陆地棉与长绒海岛棉的杂交互补优势,可以实现长绒棉产量性状与纤维品质性状的同步改良。

Spatial distribution of bolls affects yield formation in different genotypes of Bt cotton varieties

To optimize the spatial distribution of cotton bolls and to increase the yield,the relationship between yield components and boll spatial distribution was investigated among different Bt(Bacillus thuringensis)cotton varieties.A five-year field experiment was conducted to reveal the reasons for the differences in lint yield and fiber quality across three Bt cotton varieties with different yield formations from 2013 to 2017.The lint yield of Jiman 169(the average yield from 2013-2017 was 42.2 g/plant)was the highest,i.e.,16.3 and 36.9%higher than Lumianyan 21(L21)and Daizimian 99B(99B),respectively.And the differences in boll weight among the three cultivars were similar to the lint yield,while the others yield components were not.So the increase in lint yield was mainly attributed to the enlargement in boll weight.However,the change in fiber quality was inconsistent with the lint yield,and the quality of L21 was significantly better than that of Jimian 169(J169)and 99B,which was caused by the diversity of boll spatial distribution.Compared with 99B,the loose-type J169 had the highest number of large bolls in inner positions;the tight-type L21 had a few large bolls and the highest number of lower and middle bolls.And approximately 80.72%of the lint yield was concentrated on the inner nodes in Jiman 169,compared with 77.44%of L21 and 66.73%of 99B during the five-year experiment.Although lint yield was significantly affected by the interannual changes,the lint yield of J169 was the highest and the most stable,as well as its yield components.These observations demonstrated the increase in lint yield was due to the increase in boll weight,and the large bolls and high fiber quality were attributed to the optimal distribution of bolls within the canopies.

Multi-Location Investigation of Optimum Planting Density and Boll Distribution of High-Yielding Cotton (G.hirsutum L.) in Hubei Province,China

Cotton yield per unit ground area has stagnated for a dozen years in Hubei Province, China, although a series of new high- yielding varieties have been commercialized. A multi-location investigation was carried out in 2008 and 2009 in 13 counties to determine if increased planting population density （PPD） would break the stagnant yield. The results showed that significant differences among the fields existed in theoretical yield, PPD, and bolls per square meter （BPM）. The lowest yield of 1 641.1 kg ha-I was resulted from the lowest PPD of 1.7 plants m-2 and the lowest BPM of 71.8 bolls m-2, while the highest yield of 2 779.7 kg ha-~ was resulted from the highest PPD of 2.5 plants m-2, and the highest BPM of 129.4 bolls m-z. Plant mapping revealed that boll retention rate （BRR） was maintained over 30 or 40% for the first 17-18 fruiting branches （FBs） and decreased dramatically thereafter, rotten boll rate （RBR） decreased, but open boll rate （OBR） rose first and dropped later with rising FB from the bottom to the top. But BRR, RBR, and OBR were all dropped with the fruiting positions （FPs） extending outwards. The optimum range of plant density would be 2-3 plants m-2 and the proper individual plant structure would be 16-19 FBs with 5-7 FPs for cotton production in Hubei Province.

Investigation of Working Bodies of the Device for Separation of Fibers Suitable for Spinning from Cotton Waste

It is known that fiber wastes (lint, down and seeds) produced at ginneries contain fibers that are suitable for spinning and can be used in industry, and their separation significantly increases the level of fiber production (1.9% - 2.5%). Based on these analyzes, the study aimed to create a new device that separates long fibers from lint and down. As a result, the amount of fiber output in the enterprise will increase and the enterprise will have significant economic benefits. In addition, the introduction of the device will prevent the addition of long fibers (longer than 16 mm) that can be used in the textile industry to the waste. This article focuses on the creation of a fiber separation device suitable for the treatment and spinning of fibrous waste produced in ginneries. The study theoretically examined the main working bodies of the fiber separation device from waste. Theoretical research is devoted to the study of the strength of the main working body of the fiber separation device−the separating saw drum and its shaft. In the study, the sawdust drum is a more stressed steel coating, and it was found that the strength reserve of this drum is [δТ] = 2.03 (where δТ = 0.8 - 2.5) was found to be. As a result of calculating the resistance of the saw drum shaft to stiffness and vibration, it was determined that the shafts are resistant to vibration under periodic loading and that the oscillation frequency along its axis through the critical rotation frequency is vcr=10.3 Gts.

Investigation of the Properties of Fibrous Cotton Seeds, for Sorting on a Mesh Surface

In the article the research of cotton seeds for the purpose of increasing the fiber in the enterprise is investigated, separated from the mass of the derivatives of ginning of fibrous seeds by means of effective cleaning and sorting on the mesh surface.

Determination of Technological Parameters of Fiber Separation Device from Cotton Waste

This article examines the technological parameters of the device for the separation of fibers suitable for spinning by processing fibrous waste from the technological processes of ginneries. Technological processes in the cotton ginning industry include a complex of physical and mechanical advantages, the successful study of which is possible only with the use of modern achievements in science and technology. Therefore, it is advisable to conduct scientific research based on mathematical modeling. To justify the effective operation of the selected design of the cotton fiber separation device, it is necessary to select its optimal technological parameters. Improving the efficiency of the process of separation of spinning fibers from the composition of fibrous waste depends directly on technological parameters. The application of mathematical methods in the planning and conduct of research allows for determining the individual effects of the interaction of several factors that characterize the combined parameters of the optimization parameters, in contrast to traditional computational methods of research. As a result, it will be possible to obtain a mathematical model of the object understudy in a relatively small number of tests, which will simultaneously serve to obtain optimal solutions.

转1174AALdico-2+CTP耐草甘膦优异棉花种质系的创制及其特性

【目的】棉田杂草是限制棉花生长的因素之一,与棉花争夺营养、水分和光照,不仅影响棉花的生长发育,还影响棉花的产量和品质。通过基因工程途径培育高耐草甘膦优异棉花种质,实现棉田间化学除草,提高植棉的经济效益。【方法】将来源于耐辐射奇球菌(Deinococcus radiodurans)的EPSPS基因1174AALdico-2连接叶绿体转运肽,以35S为启动子,将2个目的基因串联后构建棉花转化载体。运用农杆菌活体转化技术,将目的基因导入棉花品种中棉所49,获得阳性转化体植株。以受体材料中棉所49和转化体自交分离得到的非转基因NON为对照,对转化体植株进行分子特征检测、草甘膦耐受性鉴定、农艺性状和经济性状等综合评价,以筛选出优良的转基因耐草甘膦棉花材料。【结果】通过农杆菌活体转化方法获得138个阳性转化体,对转化体植株进行目的基因PCR检测、Southern blot、Western blot分析和ELISA检测,从中筛选出17个分子特征明确、外源基因表达量高的阳性转化体。Southern blot和核苷酸测序结果表明,转化体插入位点和拷贝数各不相同,其中,ZD131、ZD185和ZD207等3个转化体为单拷贝插入位点,外源基因插入位点分别位于棉花D亚组第7染色体、D亚组第13染色体和A亚组第12染色体。草甘膦耐受性鉴定结果表明,17个阳性转化体均高耐草甘膦,其中ZD131、ZD185和ZD207等3个转化体的耐受性在3个世代之间稳定遗传,可耐4倍的田间草甘膦推荐剂量。农艺性状和经济性状评估结果表明,ZD131、ZD185和ZD207等3个转化体植株生长发育正常,表现出铃大、衣分高、结铃性强等特点,皮棉产量超过对照,纤维品质达到优质棉水平。【结论】将来源于耐辐射奇球菌的EPSPS基因1174AALdico-2与叶绿体转运肽连接,多基因串联后构建转化载体,农杆菌活体转化技术转入中棉所49,通过一系列筛选后获得3份优良的转基因耐草甘膦材料ZD131、ZD185和ZD207,该方法在提高棉花耐草甘膦水平的同时,也提高了转基因材料的农艺和经济性状。

长绒棉皮棉清理机的试验与应用

新疆长绒棉是我国高端纺织市场中的主要原材料,近年来长绒棉种植面积因人工采收成本的增加而逐渐减少。长绒棉机械采收含杂率较高,现有棉花清理设备多为细绒棉清理设备,不能直接用于长绒棉清理。因此本文提出了一款适用于长绒棉的皮棉清理机,介绍了结构组成、工作原理、技术特点,并通过试验测量了皮棉清理机的清杂效率以及对纤维长度的损耗,提升了机采长绒棉清杂后的品质,为实现精品长绒棉全程机械化生产奠定基础。

北疆早熟机采棉不同品种区域试验

为了早熟机采棉花品种和品系优良品质的传承,在北疆10个地区选取12个早熟机采棉品种进行区域试验。结果表明,12个品种出苗-吐絮期平均121.1~125.2 d,标准偏差±1.5 d,早熟属性明显;10个试验区棉花全生育期113.9~141.7 d,标准偏差±8.1 d。吐絮期整齐度B10表现最佳;B07籽棉产量最高,比B00(CK)增产4.8%;B09皮棉与霜前皮棉优于其他品种,比B00分别增产10.0%和9.7%;品种间皮棉产量经方差分析及t检验达到极显著水平。皮棉产量排名为B09>B06>B05>B10>B03>B07>B08>B11>B00>B04>B02>B01。与B00相比,B05、B06在10个试验区中全部增产,其余10个品种在不同区域的产量有增有减。纤维品质检测综合评比,B04和B00为优质棉Ⅰ型标准,B02、B11、B05、B10、B06、B08、B09、B01和B03为普通优质Ⅱ型标准;B07为品质Ⅲ型标准。区域试验结果表明,B09、B06和B05品种可在北疆地区推广栽培。

不同播期对辽宁豌豆后直播特早熟棉生长发育及产量的影响

[目的]探讨辽宁省特早熟棉区豌豆后直播特早熟棉的可行性及不同播期对直播特早熟棉生长发育及产量构成因素的影响。[方法]以特早熟棉新品种(系)辽7140、辽3971、辽6270、辽6358为材料,研究不同播期对棉花生长发育、产量构成因素及农艺性状的影响。[结果]随着播种时间的推迟,生育期加长,出苗时间缩短,株高增高,第1果枝高度、单株果枝数、单株结铃数和铃重逐渐降低;随着播期推迟,籽棉产量、皮棉产量、衣分均显著降低。[结论]可为辽宁地区豌豆后直播特早熟棉种植模式提供参考依据。

基于可见光机器视觉的棉花伪异性纤维识别方法

为提高皮棉质量和皮棉中异纤的检测精度,提出了一种基于机器视觉的棉花伪异性纤维识别方法。皮棉经过开松装置被制成薄棉层,检测通道两侧的相机对棉层进行拍摄,并将采集到的棉层及异纤和伪异纤图像保存到工控机,通过图像分块及阈值分割等算法,提取伪异纤目标区域,统计获取区域的数个颜色、形状和纹理特征,基于特征数据,分别使用BP神经网络、一对一有向无环图策略线性核函数支持向量机和径向基核函数支持向量机对两大类棉花杂质进行分类识别。实验结果表明,99.15%的伪异纤目标可被准确识别,径向基核函数支持向量机在棉花异纤和伪异纤分类识别中,总分类正确率为95.60%,能够满足在线检测的要求。

微弱棉花异性纤维图像的多通道小波分割方法研究

针对皮棉异性纤维快速检测过程中产生的微弱异性纤维目标,提出一种基于多通道色彩分量小波分解、重构的异性纤维分割方法。将原始异性纤维图像分解成3幅单通道图像,分别对每幅单通道图像进行小波分解,并对小波分解后的3幅小波图像进行两两做差处理,将做差处理后得到的图像进行小波逆变换图像灰度重构。试验结果表明,该方法能将微弱异性纤维目标准确地分割出来,解决现有分割方法无法直接分割的难题。

棉花产量育种的数量性状分析

产量是棉花育种的主要目标之一，为提高棉花产量育种效率，本文从产量结构模式、产量与其构成因素的相关关系两方面，分析了与棉花产量育种有关的数量性状。

天然有色棉纤维和短绒色泽遗传分析(英文)

利用不同纤维色泽材料及其 F1和 F2 代对有色棉纤维和短绒色泽遗传进行了综合分析 ,结果表明 :棕色和绿色纤维各由一对非同源染色体上的主效基因控制 ,表现不完全显性 ,棕色和绿色短绒也各由一对非同源染色体上的一对基因控制。绿色纤维和短绒相对棕色为显性 ,棕色纤维和短绒相对白色纤维为显性。

陆地棉衣分QTL的形态和RAPD分子标记筛选

本研究以陆地棉遗传标准系 TM- 1(衣分 31.4 % )和 T5 86(衣分 7.64% )为亲本构建衣分QTL s的作图群体。根据 F2 单株衣分表现 ,以 BSA法筛选获得 4个与控制陆地棉衣分 QTL s连锁的RAPD分子标记。其中 ,OPD1394 7,OPAD0 2 50 0 ,OPAO1694 73个标记位于同一连锁群 ,且与茸毛基因(T1)连锁 ,位于棉花的第 6染色体上。该衣分 QTL来自 T5 86,标记位点可解释 6.6%的表型变异。OPAK0 5 94 0 与另一衣分 QTL连锁 ,其供体基因来自 TM- 1,可解释 7.6%的表型变异。此外鉴定出影响衣分表达的 3个形态标记 ,植株被茸毛 (T1)对衣分具有增益作用 ,可解释表型变异的 3.5 7% ;棕色纤维 (LC1)对衣分具有减效作用 ,可解释表型变异的 3.85 % ;光籽 (N1)对衣分具有巨大的负作用 ,该 F2群体约 4 3.2