基于水平集的多相活动轮廓图像分割模型

提出了一种新型的多相活动轮廓模型，是无边活动轮廓模型的广义形式。该模型具有如下特点：（1）提出了背景填充技术，可以在检测目标内部弱边缘时去除阻碍检测的背景信息；（2）在单次二相水平集收敛的基础上，采用多次收敛方式实现了多相分割模型（n-1次收敛实现n相分割模型，n〉1）；（3）介绍了一种提升算法，进一步增强了模型的计算稳定性。实验结果表明，该模型对弱边缘检测特别有效。     

复杂背景下目标树叶的分割与补缺

为了进一步提高复杂背景下目标树叶分割算法的运行效率和准确性,在超绿算法的基础上结合模糊C聚类算法提高分割的运行效率,利用凸包填充法提高分割的准确性。首先利用超绿算法去除复杂背景中的非绿色部分,然后利用模糊C聚类算法去除与目标树叶颜色差异较大的绿色背景,而对于颜色差异较小的绿色背景,则先利用底帽变换得到目标树叶的边缘信息,再通过腐蚀和比较连通区域的大小进行去除。采用凸包填充法对目标树叶的边缘缺口进行补缺可以提高分割的准确性,从而降低错分率。超绿算法结合模糊C聚类算法可提高分割的运行效率。研究结果表明,与原有算法对比,错分率平均降低了1.05%,分割效率平均提高了13.82%。     

基于C-V主动轮廓模型的“陡峭”边界的微藻图像分割

采用Chan和Vese的C-V主动轮廓模型以及本文中改进的C-V主动轮廓模型对几类典型的海洋微藻图像进行了分割。当微藻图像的主要边界曲率变化较大,即主边界"陡峭"时,直接使用C-V主动轮廓模型难以获得微藻图像的边界。在改进的C-V主动轮廓模型中,通过人机交互绘制粗略的初始边界,并将其设定为初始零水平集,将符号函数引入到初始水平集中定义内外能量,再通过适当的参数调整进行图像边界的演化。将采用两种模型算法获取典型的海洋微藻图像边界的过程进行对比可知,对于带"陡峭"边界的微藻图像,采用C-V主动轮廓模型难以获得或以较慢速度获得图像边界,而采用改进的C-V主动轮廓模型不仅图像边界获取速度快,而且边界信息量大。实验结果验证了改进的C-V主动轮廓模型算法的有效性,为微藻图像的分割提供了新的技术手段。     

木材表面缺陷特征轮廓提取算法研究

虫眼、活节和死节是最常见的木材表面缺陷,是木材分选过程主要的识别目标,精确提取木材表面缺陷轮廓特征能大幅提高木材分选的准确率。本研究提出一种针对木材表面虫眼、活节、死节缺陷轮廓提取方法。针对木材表面常见黑点和纹理等非线性噪声,使用中值滤波方法平滑图像。然后分别应用OTSU算法与全局阈值分割算法分离图像背景与目标,对结果二值图像使用数学形态学方法进行滤除和填充,最终用sobel算子提取缺陷边缘。结果表明,采用OTSU算法分割和数学形态学相结合的方法可以很好地提取木材表面缺陷特征,用sobel算子能够提取到比较完整、准确、连续的木材表面缺陷边缘轮廓,提高了目标图像的可视性和精准性。     

基于多水平集的植物图像分割

依据植物图像中不同目标的区域特征,应用多水平集分割算法分割植物图像.该算法能够将植物的花朵、叶片以及背景有效地分割开.与基于聚类的多尺度Ncut算法的分割效果进行比较,多水平集方法在分割效果上优于多尺度Ncut算法.     

基于分水岭算法的绿色作物与背景分割研究

分水岭算法作为彩色图像分割手段的一种方法,具有运算简单,性能优良,能较好提取运动对象轮廓和准确得到运动物体边缘等优点。应用分水岭算法研究了绿色作物及其背景的分割,首先通过数码相机拍摄的一幅640×480田间青菜真彩色图像,在matlab中采用分水岭分割算法处理图像后提取其绿色分量,再用数学形态学闭运算处理后可以较好地分割绿色作物与背景。针对结果中存在的过分割现象,采用先计算图像的形态学梯度,再用分水岭算法分割可以使结果得到有效改善。     

基于改进随机Hough变换的椭圆形农产品大小分级

针对椭圆形农产品的分级问题,采用最近邻分类算法和随机Hough变换理论,对哈密瓜这类椭圆形农产品的大小分级方法进行研究。结果表明:1)哈密瓜边缘轮廓近似椭圆形,所测出的长短轴半径,可以作为椭圆形哈密瓜大小分级的新标准;2)通过试验测定,对于白色背景的哈密瓜,最近邻分类算法可以提取出较为完整的边缘轮廓;3)随机Hough变换可以在边缘轮廓不完整且有随机噪声干扰的情况下,检测出任意曲率的哈密瓜边缘轮廓的近似椭圆;4)与椭圆形哈密瓜的半径的真实值相比,本改进算法识别值的相对误差小于6%;5)当哈密瓜处在不同倾斜状态时,如0°、45°、90°、135°,本改进算法仍可以准确测得其长短轴半径。本改进算法还可以推广到其他椭圆形和类椭圆形农产品的大小分级中。     

一种快速的视网膜光学相干图像分割方法

在医学领域,黄斑厚度可以用来量化糖尿病黄斑水肿和年龄相关性黄斑变性等疾病,临床上通常使用光学相干断层扫描的影像技术来获取黄斑图像。但现有的黄斑图像分割方法运算速度较慢,阻碍了其临床使用。本文提出一种新的基于多分辨率及水平集的黄斑图像分割方法,首先使用高斯滤波对原始图像按行进行滤波,再运用多分辨率方法获取图像初始局部轮廓,最后使用水平集方法可以快速获取黄斑图像的中间轮廓,得到最终的图像分割结果。通过在311幅黄斑图像的仿真实验对比,本文方法在边缘检测结果和运算速度上比传统方法有很大改进。     

基于改进C-V模型的棉花叶片目标提取方法

为解决自然条件下棉花叶片因其轮廓几何边缘长势不均匀所导致的叶片目标提取不精准问题,提出一种基于改进C-V模型的棉花病害叶部目标提取方法。在传统C-V模型的基础上,将长度惩罚项和符号距离函数的约束能量项引入能量模型中,以达到对演化曲线长度变化的约束目的,从而完成对整幅图像目标特征的提取。本研究算法先对待分割的图像设置初始曲线,并利用高斯滤波算子对待分割图像进行平滑滤波处理,然后根据图像全局灰度信息和局部二值匹配信息建立能量方程,根据其离散化形式,对水平集函数进行演化,并从中提取演化曲线,最后根据水平集函数演化过程所满足的终止条件,输出图像分割结果。按照不同天气条件和不同背景采集了1 200幅棉花叶片样本图像,对本研究算法进行测试。试验结果表明:本研究算法对于晴天、阴天和雨天图像中目标(棉花叶片)轮廓提取准确率分别达到82.23%、82.73%和84.60%。分割结果表明,本研究算法能够对3种天气条件(晴天、阴天、雨天)与4种复杂背景(白地膜、黑地膜、秸秆、土壤)特征混合的棉花叶片图像目标特征轮廓实现准确提取。     

三维轮廓匹配的多尺度技术

采用多尺度分析技术实现三维轮廓曲线匹配.三维轮廓曲线通过不同尺度的Gaussian函数滤波和等距重采样,将曲率和挠率的乘积为局部极大值的点作为轮廓曲线的特征点,利用特征点将轮廓分段,对轮廓曲线进行Fourier变换得到Fourier描述符;选择Fourier描述符的低频分量构成三维轮廓曲线的特征矢量,通过比较特征矢量决定2条轮廓是否相似;在2条轮廓相似的基础上,实现三维物体轮廓曲线的匹配.结果表明本文提出的算法具有快速、准确、效果好等特点.     

Using an image segmentation and support vector machine method for identifying two locust species and instars

Locusts are agricultural pests around the world. To cognize how locust distribution density and community structure are related to the hydrothermal and vegetation growth conditions of their habitats and thereby providing rapid and accurate warning of locust invasions, it is important to develop efficient and accurate techniques for acquiring locust information. In this paper, by analyzing the differences between the morphological features of Locusta migratoria manilensis and Oedaleus decorus asiaticus, we proposed a semi-automatic locust species and instar information detection model based on locust image segmentation, locust feature variable extraction and support vector machine(SVM) classification. And we subsequently examined its applicability and accuracy based on sample image data acquired in the field. Locust image segmentation experiment showed that the proposed GrabCut-based interactive segmentation method can be used to rapidly extract images of various locust body parts and exhibits excellent operability. In a locust feature variable extraction experiment, the textural, color and morphological features of various locust body parts were calculated. Based on the results, eight feature variables were selected to identify locust species and instars using outlier detection, variable function calculation and principal component analysis. An SVM-based locust classification experiment achieved a semi-automatic detection accuracy of 96.16% when a polynomial kernel function with a penalty factor parameter c of 2 040 and a gamma parameter g of 0.5 was used. The proposed detection model exhibits advantages such as high applicability and accuracy when it is used to identify locust instars of L. migratoria manilensis and O. decorus asiaticus, and it can also be used to identify other species of locusts.     

Low and high-level visual feature-based apple detection from multi-modal images

Automated harvesting requires accurate detection and recognition of the fruit within a tree canopy in real-time in uncontrolled environments. However, occlusion, variable illumination, variable appearance and texture make this task a complex challenge. Our research discusses the development of a machine vision system, capable of recognizing occluded green apples within a tree canopy. This involves the detection of “green” apples within scenes of “green leaves”, shadow patterns, branches and other objects found in natural tree canopies. The system uses both thermal infra-red and color image modalities in order to achieve improved performance. Maximization of mutual information is used to find the optimal registration parameters between images from the two modalities. We use two approaches for apple detection based on low and high-level visual features. High-level features are global attributes captured by image processing operations, while low-level features are strong responses to primitive parts-based filters (such as Haar wavelets). These features are then applied separately to color and thermal infra-red images to detect apples from the background. These two approaches are compared and it is shown that the low-level feature-based approach is superior (74% recognition accuracy) over the high-level visual feature approach (53.16% recognition accuracy). Finally, a voting scheme is used to improve the detection results, which drops the false alarms with little effect on the recognition rate. The resulting classifiers acting independently can partially recognize the on-tree apples, however, when combined the recognition accuracy is increased.     

改进的模糊优选多目标优化遗传算法及其应用

提出一种改进的模糊优选多目标优化遗传算法.算法采用个体在总群体中的相对优属度作为适应度值,将总群体中的全部个体按子目标函数的数量平均划分为子群体,对每个子群体分配1个子目标函数,以子目标函数值计算子群体中个体的适应度值.2次选择后满足了整体最优的要求,又尽可能地逼近各子目标最优值.经实例计算,效果显著.     

Passion fruit detection and counting based on multiple scale faster R-CNN using RGB-D images

The accurate and reliable fruit detection in orchards is one of the most crucial tasks for supporting higher level agriculture tasks such as yield mapping and robotic harvesting. However, detecting and counting small fruit is a very challenging task under variable lighting conditions, low-resolutions and heavy occlusion by neighboring fruits or foliage. To robustly detect small fruits, an improved method is proposed based on multiple scale faster region-based convolutional neural networks (MS-FRCNN) approach using the color and depth images acquired with an RGB-D camera. The architecture of MS-FRCNN is improved to detect lower-level features by incorporating feature maps from shallower convolution feature maps for regions of interest (ROI) pooling. The detection framework consists of three phases. Firstly, multiple scale feature extractors are used to extract low and high features from RGB and depth images respectively. Then, RGB-detector and depth-detector are trained separately using MS-FRCNN. Finally, late fusion methods are explored for combining the RGB and depth detector. The detection framework was demonstrated and evaluated on two datasets that include passion fruit images under variable illumination conditions and occlusion. Compared with the faster R-CNN detector of RGB-D images, the recall, the precision and F1-score of MS-FRCNN method increased from 0.922 to 0.962, 0.850 to 0.931 and 0.885 to 0.946, respectively. Furthermore, the MS-FRCNN method effectively improves small passion fruit detection by achieving 0.909 of the F1 score. It is concluded that the detector based on MS-FRCNN can be applied practically in the actual orchard environment.

     

3D Studio MAX下制作齿轮及蜗杆模型的方法

基于3D Studio MAX制作直齿圆柱齿轮模型的方法主要是使用编辑修改器对几何形体的次对象进行编辑修改，从而形成轮齿，过程稍显繁琐。然而，在此模型基础上，利用截面与放样命令却可以很简便地制作其它较复杂的齿轮模型。尤其是使用放样命令，在蜗杆及其类似模型制作方面有着事半功倍的效果。     

“改良橙”变异性状的遗传动态及其嵌合体结构的研究

改良橙是甜橙(印子柑)嫁接在红桔上得到的嫁接嵌合体,有“橙型红肉果”、“怪型红黄肉嵌合果”、“橙型黄肉果”,“嵌合桔变”知“桔变”五种变异类型。在无性繁殖情况下,改良橙的变异性状表现不断分离,而实生繁殖时变异性状则消失。通过解剖各变异类型的果实,得知改良橙的嵌合性状系源自芽顶分生组织的 L—Ⅰ和 L—Ⅲ。根据改良橙的嵌合体结构和变异性状的遗传动态,在生产利用上,既不能采用实生繁殖亦不能采用分离同质体的途径,而必须选择橙型红肉果类型的具高度嵌合的芽条,才能保持改良橙的优良特点。     

瓯江彩鲤酪氨酸酶基因的克隆与序列分析

瓯江彩鲤(Cyprinus carpio var.color)是分布在我国瓯江流域的一种鲤科鱼类,色彩艳丽,体形优美,深受人们喜爱。瓯江彩鲤有5种基本体色:"全红"、"大花"、"麻花"、"粉玉"和"粉花",是研究鱼类体色遗传的良好材料和理想模型。酪氨酸酶(tyrosinase)是影响黑色素合成的关键酶,其转录的提前终止会导致黑色素无法合成。采用RACE技术从瓯江彩鲤皮肤转录本中克隆5种体色酪氨酸酶基因全序列,并对序列进行分析。发现在瓯江彩鲤的5种体色中,酪氨酸酶基因cDNA序列长度存在差异:"全红"为2 100 bp,"麻花"为2 107 bp,"大花"为2 073 bp,"粉玉"为1 976 bp,"粉花"为2 111 bp;且每种体色都存在两种类型酪氨酸酶基因(TYR-1,TYR-2)的转录。这两种酪氨酸酶基因mRNA所翻译成的氨基酸序列仅在一二级结构上有所差异,而在结构域和三级结构上不存在差异。但酪氨酸酶基因的这些差异是否与瓯江彩鲤体色相关还有待后续的证明。研究亮点:在国内外首次克隆了鲤的酪氨酸酶基因,发现不同体色瓯江彩鲤均转录完整的酪氨酸酶基因,且每种体色都存在两种酪氨酸酶的mRNA转录。揭示了5种体色瓯江彩鲤酪氨酸酶基因的序列差异,对进一步研究该基因与体色的关系提供了依据。     

Recent Advances in Color Vision

Until a few years ago it was possible to account for nearly all the aspects of human color perception on the basis of the three-color theory, but such is no longer the case. This is largely due to improvements in the older methods of investigation and to the invention of new ones. Among the latter may be mentioned the microelectrode technique of Granit and the retinal direction effect of Stiles and Crawford. Modern requirements are met by a polychromatic theory, comprising 7 types of receptor, but there is no necessity for these to have such narrow spectral response curves as those exhibited by Granit's modulators. Modifications of the three- and four-color theories have been examined to see to what extent they can be made to fit in with experimental results. Particular notice has been taken of the possibility that there is polychromatism of the retinal receptors, but trichromatism of the nerve paths which connect these to the brain or even of the brain itself. The conclusion arrived at is that there must be polychromatism throughout the entire visual mechanism for color perception if a complete account is to be given of all the known facts.     

水稻抽穗期叶色诊断指标与叶面积指数及结实期光强的关系

叶色是氮素营养诊断最常用的指标,获得准确的叶色诊断指标是水稻精确定量施氮的基础。叶色诊断指标实际上就是稻谷产量最高时的最适叶色。已有报告指出,叶色诊断指标受到群体大小和结实期光照条件的影响。研究的目的是,找出叶色诊断指标随群体大小和光照条件而变化的规律,为精确定量施氮提供理论和技术依据。2004—2005年早季和晚季,在广州以两系杂交稻粤杂122为试材,设置8种不同氮肥处理,进行2年4季田间试验,抽穗期测定叶色(SPAD)和叶面积指数(LAI),成熟期测产。结果表明:(1)不同季节的最适叶色存在明显差异,4季变动于39～45之间。根据产量与叶色的定量关系,可以准确、快速地确定特定条件下的叶色诊断指标。(2)稻谷产量与抽穗期群体指数(SPAD与LAI的乘积)呈开口向下的抛物线关系。抽穗期SPAD、LAI和结实期日照时数,可以解释不同年度、季节和不同氮肥处理的稻谷产量变异的86%。最适群体指数随着结实期日照时数的增加而提高。(3)最适叶色随着日照时数的增加而提高,随着LAI的增加而降低,3者之间存在显著的定量关系。应用这一关系,可根据结实期光照条件,估计出异地异季的叶色诊断指标。