Abstrakt

Partial Feature Based Ensemble of Support Vector Machine for Content based Image Retrieval

Kirti Jain, Dr. Sarita Singh, Dr. Gulab Singh

Ensemble of classifier provides a great versatility of classifier for pattern recognition and classification. The pattern recognition and classification is a new age direction for content based image retrieval. The content based image retrieval depends on lower content feature of image. The lower content of feature extraction of image is colour texture and geometrical dimension of image. The geometrical dimension of image gives the shape structure of image. The partial feature ensemble is process of merging a classifier value according to matched feature of query image and stored image in database. The “ensembling feature” of classifier depends on extraction process of feature of image. The partial feature extraction is basically based on outside boundary value of image. The movement of image varies according to its rotation or length and breadth. The value of rotation of image feature extraction plays a role of ensemble point of classifier for image retrieval. For the classification of feature support vector machine classifier has been used.