基于LabVIEW葡萄叶片还原糖含量的测试方法

目前对葡萄叶片营养元素诊断大都利用化学滴定法或者光谱仪器分析法,但此类方法仅适用于实验室小批量作物测试,难以应用至大批量农业生产中。因此本系统以葡萄叶片为测试对象,在LabVIEW软件平台下,提出了一种基于夜间葡萄叶片中还原糖含量的测定系统。具体为利用USB工业摄像头实时采集叶片图像,借助于Vision Development Module模块中的Vision Assistant完成图像处理工作,进而通过LabVIEW中"脚本与公式"模块调用Matlab Script脚本节点编程,提取叶片图像颜色和纹理特征值参数,使用支持向量机(SVM)算法构建分类器模型对487幅葡萄叶片糖分含量进行分类识别。结果表明该系统分类识别准确率高达87.349%,单次测试时长为2~5 min。证明该系统精度高、工作稳定,对提高农业经济效益方面具有重要意义,有实用价值。     

基于多尺度残差神经网络的葡萄叶片病害识别

葡萄叶片不同程度的病害具有一定的相似性,目前对于葡萄叶片病害的识别多为病害种类识别,对不同程度病害识别的研究较少,且传统识别方法对于不同程度病害识别准确率较低。提出一种基于多尺度残差神经网络（Multi-Scale ResNet）的葡萄叶片病害识别方法。对葡萄叶片病害图像进行数据增强与叶片区域标注后,使用Mask R-CNN提取葡萄叶片部位,通过引入多尺度卷积以改变ResNet底层对不同尺度特征的响应,利用加入的SENet提升网络的特征提取能力,并将图像输入Multi-Scale ResNet中进行识别。实验结果表明,该方法的平均识别准确率达到90.83%,相比ResNet18提高了2.87个百分点。     

基于室外图像的天气现象识别方法

为提高室外视频监控的准确率,实现天气现象的自动观测,提出了一种基于室外图像的天气现象识别方法,该方法通过分析天气现象对图像的影响,提取图像功率谱斜率、对比度、噪声和饱和度等特征进行训练与分类,在训练过程中根据类别之间的特征距离建立分类决策树,并为决策树上非叶子节点构造支持向量机（SVM）分类器,并在每个分类器构造过程中通过对特征赋权值实现对特征的选择。通过对WILD图像数据库和采集图像集不同天气800个样本的测试,除了对降雨的识别率较低(75%)外,对晴、阴、雾天气的识别率均高于85%。     

基于D-LLE算法的多特征植物叶片图像识别方法

为了提高植物叶片图像识别的准确率,提出一种基于差异性值监督局部线性嵌入（D-LLE）算法的多特征植物叶片图像识别方法。该方法提取叶片的颜色、形状和纹理作为叶片多特征,在加权局部线性嵌入（WLLE）算法中引入样本的差异性值构成差异性值监督LLE算法（D-LLE）对叶片高维特征进行降维,在低维空间采用最近邻分类器实现叶片的识别。该方法所用的叶片多特征比单一特征像素值更能描述叶片图像,同时差异性值能够充分挖掘样本的类别信息。基于实拍的叶片图像数据库的实验结果表明,该方法有效提高了叶片的识别精度。     

基于多尺度多分类器卷积神经网络的混合失真类型判定方法

针对图像混合失真类型判定难的问题,在深度学习多标签分类思想的基础上,提出了一种基于多尺度多分类器卷积神经网络（CNN）的混合失真类型判定方法。首先,从图像中截取得到含有高频信息的图像块,将该图像块输入到不同感受野的卷积层中以提取图像的浅层特征图;其次,将浅层特征图输入到各子分类器结构中以进行深层次的特征提取和融合,将融合的特征通过Sigmoid分类器得到判定结果;最后,将各子分类器的判定结果进行融合得到图像的混合失真类型。实验结果表明,在自然场景混合失真数据库（NSMDID）上,所提方法对图像中存在的混合失真类型的平均判定准确率可以达到91.4%,且对大部分类型的判定准确率都在96.8%以上,可见所提方法能够对混合失真图像中的失真类型进行有效的判定。     

彩色叶片图像去尘算法

针对户外降尘造成叶片图像中颜色失真、细节信息模糊的问题,提出一种基于光学模型的单幅图像的自动去尘算法.首先根据光线在尘土层和空气中的传播方式建立了一种退化模型;然后结合光学反射成像模型和暗元色原理估计出环境光强及传输量2个模型参数;最后在该退化模型的基础上实现叶片图像尘土的快速去除,并用有尘土层的标准色卡和葡萄叶片图像检验算法的有效性.实验结果表明,文中算法对2种图像均有较好的去尘效果,复原后图像的H和S分量与无尘图像的偏离程度得到了明显改善,重现了图像的颜色和清晰度,获得了满意的视觉效果;该算法对不同天气和照明条件、不同品种的葡萄叶片图像均有较好的颜色恢复效果.     

叶片图像特征提取与识别技术的研究

文章介绍了一种基于叶片图像的形状特征对叶片进行识别的方法。首先对叶片图像进行预处理并且提取出叶片的轮廓,然后利用轮廓计算得到叶片的矩形度、圆形度、偏心率等8项几何特征和7个图像不变矩,同时在文中提出了一种新的移动中心超球分类器,利用其对得到的形状特征进行分类从而实现了对20多种植物叶片的快速识别,并且平均识别率达到了92%。     

基于高斯混合模型的叶片检测分割算法

为解决光照变化、叶片自身表观变化和复杂背景对植物叶片图像准确分割所造成的困扰,提出一种组合式分割方法。该方法在多个尺度上采用滑动窗口扫描方式检测图像中的叶片;对检测到的叶片区域中心区域像素为初始前景,而叶片窗口之外的区域为初始背景,用高斯混合模型(GMM)分别对前景和背景建立初始概率模型;采用迭代法完成叶片分割,在每一轮迭代中,用标准的图割算法和上一轮GMM模型分割前景和背景,根据新的分割结果重新估计前景和背景的GMM;迭代过程在能量函数收敛时结束。叶片检测时,以能描述叶片的外观和形状的HOG特征为检测依据;为了应对实际叶片图像中叶片形态、角度变化较多的挑战,采用多子类分类器策略。以葡萄叶片为例,用该方法进行了分割实验。结果表明,该方法对上述复杂条件下叶片图像的分割具有较好的鲁棒性和较高的精度,能实现分割过程的完全自动化。     

基于奇异值分解和支持向量机的人脸检测

人脸检测在自动人脸鉴别工作中具有重要的意义。由于人脸图像特征的复杂性和多样性，使得人脸模式分类器的训练十分困难。本文提出了一种基于支持向量机（SVM）的人脸检测算法，使用了奇异值分解对训练样本进行特征提取，再由SVM分类器进行分类，有效的降低了训练难度，采用二阶多项式作为SVM分类器的核函数，实验结果表明，该方法是十分有效的。     

基于图像块分类器和条件随机场的显微图像分割

针对花粉显微图像处理提出了一种自动分割方法,将有助于花粉识别系统的开发。使用归一化颜色分量训练图像块分类器,并且结合条件随机场和图割进行建模和优化,利用最大化后验概率(MAP)的方法实现花粉显微图像中花粉区域的分割。对于实验中的133幅图像,自动分割同人工分割的结果相比较,统计得到距离误差均值为7.3像素,准确率的平均值为87%。实验结果表明,使用图像块分类器和条件随机场模型可以用于花粉图像的分割。     

基于图像局部奇异值向量和BP神经网络分类器的道路导航方法

提出以道路图像矩阵的局部奇异值向量作为特征输入,以BP神经网络作为分类器的道路导航方法.首先将图像分割成若干子图像,然后分别对子图像进行奇异值分解,提取子图像的代数特征向量.子图像的特征奇异值组成整个图像的局部奇异值向量,作为分类器的输入.再利用BP神经网络分类器对道路图像进行训练及识别.实验中处理了三类道路图像(偏左、偏右、正确方向),每类用20 幅图像作为训练样本,30幅用作测试.结果表明,这 种道路导航方法的识别率达到了100%.􀁳 􀁨 􀁱     

Plant leaf disease classification and damage detection system using deep learning models

Agriculture is the primary source of livelihood for about 70% of the rural population in India. The crop variety cultivated in India is very diverse. There are more than 500 crop varieties grown in India. Despite the technological advances, the agricultural practices are still manual and involve less automation than western countries. Most of the diseases affecting a plant will reflect the damage in the leaves. The diseases affecting the plant can thus be identified from the leaf images. This paper presents an automatic plant leaf damage detection and disease identification system. The first stage of the proposed method identifies the type of the disease based on the plant leaf image using DenseNet. The DenseNet model is trained on images categorized according to their nature, i.e., healthy and the type of the disease. This model is then used for testing new leaf images. The proposed DenseNet model produced a classification accuracy of 100%, with fewer images used during the training stage. The second stage identifies the damage in the leaf using deep learning-based semantic segmentation. Each RGB pixel value combination in the image is extracted, and supervised training is performed on the pixel values using the 1D Convolutional Neural Network (CNN). The trained model can detect the damage present in the leaves at a pixel level. Evaluation of the proposed semantic segmentation resulted in an accuracy of 97%. The third stage suggests a remedy for the disease based on the disease type and the damage state. The proposed method detects various defects in different plants in the experimental analysis, namely apple, grape, potato, and strawberry. The proposed model is compared with the existing techniques and obtained better performance in comparison with those methods.

     

Deep Learning for Tomato Diseases: Classification and Symptoms Visualization

Several studies have invested in machine learning classifiers to protect plants from diseases by processing leaf images. Most of the proposed classifiers are trained and evaluated with small datasets, focusing on the extraction of hand-crafted features from image to classify the leaves. In this study, we have used a large dataset compared to the state-of-the art. Here, the dataset contains 14,828 images of tomato leaves infected with nine diseases. To train our classifier, we have introduced the Convolutional Neural Network (CNN) as a learning algorithm. One of the biggest advantages of CNN is the automatic extraction of features by processing directly the raw images. To analyze the proposed deep model, we have used visualization methods to understand symptoms and to localize disease regions in leaf. The obtained results are encouraging, reaching 99.18% of accuracy, which ourperforms dramatically shallow models, and they can be used as a practical tool for farmers to protect tomato against disease.     

基于联合训练的分类器的乳腺癌图像分类

利用机器学习的乳腺癌组织病理图像诊断节省了大量的人力物力,因此提高乳腺癌组织病理图像识别准确率有很好的现实意义;针对单一分类器和集成学习分类器模型观测域有限容易陷入局部最优的问题,提出一种基于联合训练的分类器模型;通过单一分类器相互影响扩大观测感知域来寻找损失最小的估计点,根据估计点来迭代优化超参数进而联合训练出拟合性能最好的分类器,这样既汲取不同分类器模型的可取之处来增强泛化能力,又加大了模型观测域在可以更快的得到全局最优的同时提升了识别准确率;实验表明,提出的联合训练的分类器能够提升乳腺癌组织病理学图像的分类性能,在不同放大倍数40×、100×、200×、400×下图像良恶性分类准确率分别为99.67%、98.08%、99.01%、96.34%。     

图像内容感知缩放的检测方法研究

针对可用于图像篡改的内容感知缩放技术,本文提出了一种基于概率Map图统计特征的内容感知缩放检测算法.该算法利用概率Map图来反映图像是否经过内容感知缩放操作,并利用新提出的积分投影与局部统计特征来检测篡改图像.而后利用分类器进行分类训练,从而有效识别基于内容感知缩放操作的图像篡改.实验结果显示,所提算法能够区分出原始图像与篡改图像,并具有较高的正确检测率.     

基于卷积神经网络的多尺度葡萄图像识别方法

葡萄品种质量检测需要识别多类别的葡萄，而葡萄图片中存在多种景深变化、多串等多种场景，单一预处理方法存在局限导致葡萄识别的效果不佳。实验的研究对象是大棚中采集的15个类别的自然场景葡萄图像，并建立相应图像数据集Vitis-15。针对葡萄图像中同一类别的差异较大而不同类别的差异较小的问题，提出一种基于卷积神经网络（CNN）的多尺度葡萄图像识别方法。首先，对Vitis-15数据集中的数据通过三种方法进行预处理：旋转图像的数据扩增方法、中心裁剪的多尺度图像方法以及前两种方法的数据融合方法；然后，采用迁移学习方法和卷积神经网络方法来进行分类识别，迁移学习选取ImageNet上预训练的Inception V3网络模型，卷积神经网络采用AlexNet、ResNet、Inception V3这三类模型；最后，提出适合Vitis-15的多尺度图像数据融合的分类模型MS-EAlexNet。实验结果表明，在同样的学习率和同样的测试集上，数据融合方法在MS-EAlexNet上的测试准确率达到了99.92%，相较扩增和多尺度图像方法提升了近1个百分点，并且所提方法在分类小样本数据集上具有较高的效率。     

Color image segmentation using automatic pixel classification with support vector machine

Automatic segmentation of images is a very challenging fundamental task in computer vision and one of the most crucial steps toward image understanding. In this paper, we present a color image segmentation using automatic pixel classification with support vector machine (SVM). First, the pixel-level color feature is extracted in consideration of human visual sensitivity for color pattern variations, and the image pixel's texture feature is represented via steerable filter. Both the pixel-level color feature and texture feature are used as input of SVM model (classifier). Then, the SVM model (classifier) is trained by using fuzzy c-means clustering (FCM) with the extracted pixel-level features. Finally, the color image is segmented with the trained SVM model (classifier). This image segmentation not only can fully take advantage of the local information of color image, but also the ability of SVM classifier. Experimental evidence shows that the proposed method has a very effective segmentation results and computational behavior, and decreases the time and increases the quality of color image segmentation in compare with the state-of-the-art segmentation methods recently proposed in the literature.     

Color image watermark extraction based on support vector machines

This work proposes a novel watermarking technique called SVM-based Color Image Watermarking (SCIW), based on support vector machines (SVMs) for the authentication of color images. To protect the copyright of a color image, a signature (a watermark), which is represented by a sequence of binary data, is embedded in the color image. The watermark-extraction issue can be treated as a classification problem involving binary classes. The SCIW method constructs a set of training patterns with the use of binary labels by employing three image features, which are the differences between a local image statistic and the luminance value of the center pixel in a sliding window with three distinct shapes. This set of training patterns is gathered from a pair of images, an original image and its corresponding watermarked image in the spatial domain. A quasi-optimal hyperplane (a binary classifier) can be realized by an SVM. The SCIW method utilizes this set of training patterns to train the SVM and then applies the trained SVM to classify a set of testing patterns. Following the results produced by the classifier (the trained SVM), the SCIW method retrieves the hidden signature without the original image during watermark extraction. Experimental results have demonstrated that the SCIW method is sufficiently robust against several color-image manipulations, and that it outperforms other proposed methods considered in this work.