Interactive tool to improve the automatic image annotation using MPEG-7 and multi-class SVM

Automatic Image Annotation is a technique or a tool to retrieve content-based and semantic concepts images [1]. In technique, the image content is attached to a set of predefined switches. Content-Based Image Retrieval (CBIR) allows the users to retrieve the images efficiently. The image features are automatically extractable using image processing techniques. In this study, we proposed automatic image annotation using standardized color and texture called MPEG-7. These features include Color Layout Descriptor (CLD) and Scalable Color Descriptor (SCD) for colors and Edge Histogram Descriptor (EHD) for image texture. Moreover, to decrease the scope of color layout descriptor, we used Principal Components Analysis (PCA) and for classification we used Support Vector Machine (SVM). For an input search image, the above mentioned features are extracted and classification by Support Vector Machine and prepared to perform the image annotation. This system also presents the results of the comparison between different features from the MPEG-7 descriptors. The automatic image annotation which is presented in this study is related to TUDarmstadt images. The results confirm that the system is a reliable system which has both short vector length (maximum 400 elements for each image) and high precision of 90 percent.