Wheat industry is an important constituent of Northern China's overall agricultural economy. Proper disease detection using computer vision and pattern recognition has being investigated to minimize the loss, and finally achieve intelligent healthy farming. This paper proposes a new strategy of Multi-Classifier System based on SVM (support vector machine) for pattern recognition of wheat leaf diseases for higher recognition accuracy. Diseased leaf samples with Powdery Mildew, Rust Puccinia Triticina, Leaf Blight, Puccinia Striiformis were collected in the field and images were captured before a uniform black background. Three feature sets including color feature set, shape feature set and texture feature set were created for classification analysis. The proposed combination strategy was based on stacked generalization and included twolevel structure: base-level was a module of three kinds of SVM-based classifiers trained by three feature sets and meta-level was one module of SVM-based decision classifier trained by meta-feature set which are generated through a new data fusion mechanism. Compared with other single classifiers and other strategy of classifier ensembles for wheat leaf diseases, this approach is more flexible and has higher success rate of recognition.

Virtual education is widely used in many fields including agricultural training and popular science. Modeling technologies and software tools for content making of virtual educations about digital plant is shortages and it is an obvious limitation of relevant applications. We present a fast modeling technology and developed a system of digital plant for virtual education. The method depends on real geometric data of plant collected by three-dimensional device, and a template-based modeling algorithm is employed for rapidly reconstruction of complex plant organs. The system consists of several modules including data processing, knowledge management, geometric modeling, graphics support and user interface. The system supports users to make education content about digital plant. Finally, some typical applications are given and some future works are discussed.

Abstract--This paper proposed an interactive virtual pruning method for fruit tree. In this method, Unity3D -a common game development platform -was used as the implementation tool for the interactive virtual pruning simulation of fruit tree, including integrating 3D fruit tree and scissor into a virtual orchard scene, processing human-computer interaction and providing real-time feedback. Citrus tree was used as an example to test the proposed method. We simulated the pruning in small fruit stage and fruit picking in matured stage respectively. Experiment results show that this method can vividly simulate the pruning process and render the morphologic changes in the 3D tree model after pruning immediately. Combining with pruning rules, Unity3D should be a convenient and easy to implement tool for demonstrating fruit tree pruning techniques, training famers and so on.