Image Mining for Flower Classification by Genetic Association Rule Mining Using GLCM features

( Vol-3,Issue-5,May 2017 )

Author(s): Aswini Kumar Mohanty, Amalendu Bag

Total View : 1102
Downloads : 164
Page No: 516-521
DOI: 10.24001/ijaems.3.5.17

Keywords:

Gray Level Co-occurrence Matrix features, Histogram Intensity, Classification, Genetic Algorithm; Association rule mining, Confusion matrix, Segmentation. Texture features; Color features.

Abstract:

Image mining is concerned with knowledge discovery in image databases. It is the extension of data mining algorithms to image processing domain. Image mining plays a vital role in extracting useful information from images. In computer aided plant identification and classification system the image mining will take a crucial role for the flower classification. The content image based on the low-level features such as color and textures are used to flower image classification. A flower image is segmented using a histogram threshold based method. The data set has different flower species with similar appearance (small inter class variations) across different classes and varying appearance (large intra class variations) within a class. Also the images of flowers are of different pose with cluttered background under varying lighting conditions and climatic conditions. The flower images were collected from World Wide Web in addition to the photographs taken up in a natural scene. The proposed method is based on textural features such as Gray level co-occurrence matrix (GLCM). This paper introduces multi dimensional genetic association rule mining for classification of flowers effectively. The image Data mining approach has four major steps: Preprocessing, Feature Extraction, Preparation of Transactional database and multi dimensional genetic association rule mining and classification. The purpose of our experiments is to explore the feasibility of data mining approach. Results will show that there is promise in image mining based on multi dimensional genetic association rule mining. It is well known that data mining techniques are more suitable to larger databases than the one used for these preliminary tests. Computer-aided method using association rule could assist people and improve the accuracy of flower identification. In particular, a Computer aided method based on association rules becomes more accurate with a larger dataset .Experimental results show that this new method can quickly and effectively mine potential association rules.

Cite This Article:

Share: