A Self-Learing Chinese Character Recognition System     

Volker Muller  Zhang Ping 《保鲜与加工》1996,(1):40-45

A method using possibility theory and fuzzy logic is introduced. Possibility functions of each feature are determined during training. Methods of fuzzy logic are used to combine the possibility of different features. This Chinese character recognition system consists of a pre-classifier and a two-level fine classifier. In order to handle deviations of the characters,a fuzzification of features is introduced. This method is used to develop single-font classifiers. The whole system consists of a font-classifiers and four single-font-classifiers.  相似文献   

BP Neural Networks and Its Application in Lung Cancer Intelligent Diagnosis System     

HUANG Xue-mei  TANG Zhi-de  ZHAO Yi-fan  SHU Zhi-qiang 《保鲜与加工》2005,(1):42-44

The learning algorithm of networks is discussed. The programming example of 3 layer BP networks is given with Visual C++6.0 program langue. Based on this model, a lung cancer intelligent diagnosis system is successfully implemented. Furthermore, the paper introduces network's structure design, preferencesand the source of stylebookdatum in factual applications. The ameliorative arithmetic is applied to the study of networks and BP dynamic evolving process is designed. The experiments indicatecell images are recognized and classified by the trained neural network. The study illustrates the system has feasibility and clinical value in lung cancer diagnosis.  相似文献   

图象处理技术在蔬菜栽培中的应用     

陈晓光  周云山  卢贤继 《农业工程学报》1994,10(4):131-136

应用图象处理技术对蔬菜苗的生长阶段进行分析与判断,为蔬菜栽培中的移栽、间苗等作业提供必要的信息。结果表明,采用图象处理技术可以方便地计算出蔬菜苗茎叶面积的大小和叶子的数量等特征参数,能够对其生长阶段作出准确的判断。  相似文献   

基于Radarsat-2影像的复杂种植结构下旱地作物识别   总被引：3，自引：5，他引：3  

田海峰  邬明权  牛铮  王长耀  赵昕 《农业工程学报》2015,31(23):154-159

为提高基于Radarsat-2旱地作物识别的精度,该文研究了一种复杂种植结构背景下具有共同生长期作物的识别方法。研究区为一个12 km×12 km的样方,位于内蒙古上库力农场额很队,以春小麦、油菜2种共同生长期作物为识别对象,利用Spot-6影像和Radarsat-2影像,在数据预处理的基础上分析研究区内典型地物样本的后向散射系数在不同极化波段上的变化特征,根据该变化特征设计图像增强算法,然后基于图像增强后的影像设定合理的阈值实现作物识别提取。结果表明：该方法准确识别并有效提取了共同生长期作物春小麦和油菜的种植面积,总体精度达到97%,Kappa系数为0.96。该方法简便、快捷、可靠,为春小麦、油菜等旱地共同生长期作物种植面积提取提供重要的科学技术支撑。  相似文献   

基于偏好免疫网络和SVM算法的油茶果多特征识别     

李昕  陈泽君  李立君  谭季秋  吴发展 《农业工程学报》2020,36(22):205-213

针对油茶果采摘脱壳后存在的果壳籽粒分选效率较低的问题，该研究提出了一种结合人工免疫网络（aiNet）与支持向量机（Support Vector Machine）的多特征智能分选算法。该方法利用了免疫算法的多特征聚类特点与支持向量机的二分性特点，对油茶果壳与籽粒的延伸率、圆形度、圆满度、色差分量等6个特征进行分选。试验结果表明，该研究提出的方法在分选效率上达到了97.4%，时间平均值为600 ms，证明了这种方法在油茶果壳籽粒分选作业中的实时性与有效性。通过与其他智能分选算法的效率对比分析证明，该研究提出的方法在效率上更优，更加适合油茶脱壳生产线的实时性要求。  相似文献   

基于RAdam卷积神经网络的水稻生育期图像识别     

徐建鹏  王杰  徐祥  琚书存 《农业工程学报》2021,37(8):143-150

为了解决现阶段水稻发育期信息的获取主要依靠人工观测的效率低、主观性强等问题,该研究提出一种基于Rectified Adam(RAdam)优化器的ResNet50卷积神经网络图像识别方法,开展水稻关键生育期的自动识别。连续2a对12块试验田的水稻物候特征进行持续自动拍摄,对采集的水稻图像进行预处理,得到水稻各发育期分类图像数据集;采用ExG因子和大津法(Otsu)算法相结合的方法对水稻图像分割,减小稻田背景干扰;对比分析了VGG16、VGG19、ResNet50和Inception v3四种模型下水稻生育期图像分级识别的性能,选取性能较优网络模型并进行了网络参数调优;对比试验了不同优化器下模型准确率和损失值的变化,选取了RAdam优化器。结果表明,采取基于RAdam优化器卷积神经网络构建的模型,在真实场景下分类识别准确率达到97.33%,网络稳定性高、收敛速度快,为水稻生育期自动化观测提供了有效方法。  相似文献   

A multispectral vision system to evaluate enzymatic browning in fresh-cut apple slices     

Loredana Lunadei  Pamela Galleguillos  Beln Diezma  Lourdes Lle  Luis Ruiz-Garcia 《Postharvest Biology and Technology》2011,60(3):225-234

Increased regulation of chemical fumigants has forced the almond industry to seek alternatives for postharvest control of insect pests in raw almonds. This paper reports developments of non-chemical treatment for postharvest disinfestation of almonds using radio frequency (RF) energy. A pilot-scale 27 MHz RF unit was used to evaluate effects of a RF treatment protocol on quality attributes in treated in-shell and shelled almond samples. The RF treatment protocol used 0.75 kW RF power, a forced hot air at 63 °C, back and forth movements on the conveyor at 0.56 m/min, and single mixing, which all improved the final heating uniformity. RF treatments sharply reduced the heating time from 86 and 137 min for hot air heating to only 6.4 and 8.8 min for the center of 1.5 kg in-shell and 2.4 kg shelled almond samples to reach 63 °C, respectively. Almond quality was not affected by the RF treatments because peroxide values, fatty acid and kernel color of treated almonds were better than or similar to untreated controls after 20 d at 35 °C, simulating 2 years of storage at 4 °C. RF treatments did not significantly affect the kernel moisture content of both types of almonds but reduced the moisture content in the shell. RF treatments may hold great potential to replace chemical fumigation for disinfesting almonds.  相似文献   

Feature extraction and recognition technique for human pulse signals     

CAI Kun bao  CAO Ding  DUAN Yun zi  LUO De cheng  LIU Zong xing 《保鲜与加工》2011,(10):119-123

In Chinese traditional medicine, the pulse signal plays an important role for diagnosis. To investigate the effective technique for identifying heroin druggers through the pulse signal, the feature extraction algorithm based on the biocepstrum and the third-order cepstrum entropy of the pulse signal is studied. On the basis of concise and rigorous discussion for the algorithm, the biocepstrum-based diagonal slice components are estimated for human pulse signals of 20 heroin druggers and 20 healthy normal subjects. The magnitude of the sample value of diagonal slice at m=n=1 and the third-order cepstrum entropy of magnitudes of sample values of the diagonal slice within a particular region are used as two feature parameters for every human pulse signal to form a feature vector. A classifier based on the criterion of squared Mahalanobis distance is successfully designed. Applying the designed classifier to 40 feature vectors, the correct identification rate reaches 87.5%. The research result shows that the method of the feature extraction and classifier design presented in is valuable for identifying the human pulse signals of heroin druggers.  相似文献   

基于中巴资源卫星数据的森林郁闭度估测研究     

蔡学成  杨永彰 《安徽农业科学》2007,35(34):10961-10962

森林资源分布具有辽阔性、复杂性、通达性差等特点,而遥感技术具有宏观、动态、便捷、可周期重复和成本低等优点,成为研究森林资源状况的理想手段。目前,在森林遥感应用中,多源遥感数据的提供能力越来越强。但由于遥感信息的综合性、复杂性,遥感信息处理技术相对落后。基于不同区域、不同季相和不同背景特征的森林遥感分类技术远未成熟。利用中巴资源卫星遥感数据,经过图像处理(包括图像的校正、图像的增强和图像的分类等),获取样地的灰度值,结合少量地面实测样地资料,通过线性回归建立森林郁闭度的数学模型,并进行检验以确保估测的精度,为林业生产和建设提供依据。  相似文献   

测度贴近度及其集值统计估值     

顾凤岐  赵连盛 《东北林业大学学报》1995,23(2):153-157

在定义模糊集上的测度的基础上，通过对随机集测度均值的讨论，定义了一个无穷论域上的贴近度－测度贴近度，为贴近度的计算提供了新方法，充实了贴近度的定义开式。又根据模糊集与随机集落影响的理论，给出了有严格理论基础和应用性较强的对贴近度进行集值统计的方法，并且证明了这种估计的一致性。  相似文献