Identification of flowers types
The floral industry has increasingly become one of the most important sectors for export earnings, especially in developing countries. However, during the cultivation process there may be a number of challenges that affect it, one of which is flower disease. This paper presents an automatic identification of of flower dieases based on image processing techniques. We propose an algorithmic model for automatic classification of flowers and we investigate to what extent combinations of features can improve classification performance on a large dataset of similar classes. The proposed algorithm model is based on textural features such as gray level co-occurrence matrix (GLCM: used to give a measure of the variation in intensity at a pixel of internet), and Gaborfilter response (GFR: this falls into the category of frequency based approaches). A flower image is segmented using a statistical region merging method. The data set has different flowers species with similar appearance across different classes and varying appearance within a class. We compute four different features for the flowers, each describing different aspects, namely the logical shape/texture, the shape of the boundary, the overall spatial distribution of petals, and the color. A qualitative comparative analysis of the proposed method with other will known existing flower classification methods is also presented. This project is based on real time application in which the flower capturing is square augmented and corresponding name of the flower is displayed on the screen.
PROJECT OUTPUT VIDEO:
In existing systems the input image of flower will be given and it was comparing with the database and that was displaying the name of the flower. And here we are trying to give a real-time application by using video systems and this technique will highlight the particular flower and displays the name of the flower.
In the proposed method the real time video is converted into frame and the extracted frames are compared with the database and corresponding name of the flower will be displayed to the user. The proposed method has training and classification phases. In training phase, from a given set of training images the texture features (GLCM / Gabor combination) are extracted and used to train the system using the K-nearest neighbor classifier. In classification phase a given test flower image/frame is segmented using statistical region merging (SRM) and then the above mentioned texture features are extracted for classification. These features are queried to K-nearest neighbor classifier and support vector machine (SVM) to label an unknown flower. The block diagram of the proposed method is given in the figure.
System : Pentium Dual Core.
Hard Disk : 120 GB.
Monitor : 15’’ LED
Input Devices : Keyboard, Mouse
Ram : 1GB.
Operating system : Windows 7.
Coding Language : MATLAB
Tool : MATLAB R2013A