一种新型卷积神经网络植物叶片识别方法

为提高植物叶片识别的准确率及减少计算代价,在Pytorch框架下提出一种融合了深度卷积生成式对抗网络(DCGAN)和迁移学习(TL)的新型卷积神经网络叶片识别方法。首先,对植物叶片图像进行预处理,通过DCGAN对样本数据库扩充;其次,利用迁移学习将Inception v3模型应用于图像数据处理上,以提高植物叶片识别的准确率;最后,通过对比实验对该方法的有效性进行验证。结果表明:该方法可以获得96.57%的植物叶片识别精度,同时参数训练的迭代次数由4000次缩短到560次。     

Typical Travel Events and the Reversal of Modern Image of China

In order to open up the Chinese market,Britain sent two missions to China in 1791 and 1816.The most powerful colonial empire in the world met the most powerful feudal empire in the world.The two sides led the negotiations and exchanges with the concepts of "tribute" and "equal diplomacy",and the failure of the missions of Macartney and Amherst to China was inevitable.The travel texts completed by the members of the mission recorded the process of travel to China and their views on China in detail.Two typical travel events in China completely reversed the western image of China.     

Real-time 3D transesophageal echocardiography-guided closure of a complicated patent ductus arteriosus in a dog

Advanced imaging modalities are becoming more widely available in veterinary cardiology, including the use of transesophageal echocardiography (TEE) during occlusion of patent ductus arteriosus (PDA) in dogs. The dog in this report had a complex history of attempted ligation and a large PDA that initially precluded device placement thereby limiting the options for PDA closure. Following a second thoracotomy and partial ligation, the morphology of the PDA was altered and device occlusion was an option. Angiographic assessment of the PDA was limited by the presence of hemoclips, and the direction of ductal flow related to the change in anatomy following ligature placement. Intra-operative TEE, in particular real-time three-dimensional imaging, was pivotal for assessing the PDA morphology, monitoring during the procedure, selecting the device size, and confirming device placement. The TEE images increased operator confidence that the size and location of the device were appropriate before release despite the unusual position. This report highlights the benefit of intra-operative TEE, in particular real-time three-dimensional imaging, for successful PDA occlusion in a complicated case.     

试析凯文·林奇在《城市意象》中是如何显现思维的存在并使之导向真实的

思维与对象的直接联系才能产生真实的发展与研究。为能显现思维的存在并使之导向真实,作者从思维的主体观察者和主体的观察对象环境两方面寻求着解决方法。     

Detecting fruits in natural scenes by using spatial-frequency based texture analysis and multiview geometry

This paper describes a computer vision based model for object detection that can serve as a preliminary step in fruit prognosis, which involves the estimation of the number, diameter and yield of apple fruits. In order to overcome the recognition unreliability in uncontrolled environments caused by uneven illumination conditions, partly occluded surfaces, and similar background features, we rely on a combination of the object's colour, texture and 3D shape properties. In our research, we apply colour segmentation to multiple scene snapshots to separate potential regions from the background and verify them first with texture analysis and second by reconstructing them to 3D space. By analysing all three distinct features (colour, texture and 3D shape) of possible areas, we can safely conclude if they represent fruits we are looking for. Once we detect and verify all areas representing fruits, we can measure their size and model estimated fruit yield.     

Automatic counting of annual rings on Pinus sylvestris end faces in sawmill industry

One of the essential requirements of current agricultural practice is the need to evolve towards crop techniques that make better use of productive factors behaving in sustainable and environmentally respectful ways. Pest control is one of the most important problems to take into account, due to the significant production losses that pests may cause. The Integrated Production for olive crop defines a set of rules that has to be followed in order to ensure a production of higher quality, and promotes an environmentally respectful model of Olive cultivation. This work presents SAIFA (spanish acronym for Sistema de Alerta e Información Fitosanitaria Andaluz - Andalusian Phitosanitary Information and Alert System) a web-based information system which allows monitoring the Integrated Production for the olive crop in Andalusia, Spain. SAIFA has been built as a tool to assist agricultural technicians to comply with the quality standards of Integrated Production, and to help decision makers to choose the actions to be performed in the crop. Also, it assists coordinators to choose an Integrated Production strategy applicable for the whole region with the main objective of ensuring the safety of crops and reporting the current phitosanitary state to the authorities.     

基于图像处理与GUI的大蒜切脐的研究

本课题采用数字图像处理技术,通过研究适合于大蒜切脐定位的专用算法,通过GUI界面编程编写出大蒜切脐软件系统,实现对切脐位置的自动、精确定位。结果表明,该程序能够很好的将大蒜根须与蒜体区分,为大蒜切脐机械化的实现提供了技术支持。     

A morphological assessment system for ‘show quality’ bovine livestock based on image analysis

Morphological assessment is one important parameter considered in conservation and improvement programs for bovine livestock. This assessment process consists of scoring an animal based on its morphology and is normally carried out by highly qualified staff. These animals are all of agreed ‘show quality’ and hence they are morphologically very similar.This paper presents a system designed to provide an assessment based on a lateral image of the cow. The system consists of two main parts: a feature extraction stage, to reduce the information on the cow in the image to a set of parameters, and a neural network stage to provide a score based on that set of parameters. For the image analysis section, a model of the animal is constructed by means of the point distribution model (PDM) technique. Later, that model is used in the searching process within each image, which is implemented using genetic algorithms (GAs). As a result of this stage, the vector of weights that describe the deviation of the given shape from the mean is obtained. This vector is used in the second stage, where a multilayer perceptron is trained to provide the desired assessment, using the scores given by experts for selected cows.The system has been tested with 138 images corresponding to 44 individuals of a special rustic breed, with very promising results, given that the information contained in only one view of the cow can not be considered complete.     

基于GMM的黄瓜病害图像建模

通过对黄瓜病害图像的准确分析,有效提取了图像的底层特征,建立了8种常见黄瓜病害的高斯混合模型（Gaussian Mixture Model,GMM）,并利用最大期望算法（Expectation-Maximization,EM）估计GMM的参数,精确描述了8种黄瓜病害的特征分布,从而提高了对黄瓜病害的正确识别和为害情况的准确把握,为实现黄瓜病害的实时与准确的预测和防治提供了理论依据。