Image Classification based on CBIR

Abstract

In this paper, we present a new way to classify four types of images (Car accidents, Fire, Abnormal objects in street and Digs) which will be sent to four government places; Civil Defence, police station and Municipal. The classification method depends on the Content-Based Image Retrieval (CBIR), where we use a new method. In this method, we use a combination of three methods to extract features from an image; Single Value Decomposition (SVD), Edge Histogram Descriptor (EHD) and Color Auto-Correlogram for Extraction Features. You will use these features to find the closest similarities to the query image from the database images by selecting the closest 3 images, then choosing the class to which the closest two images belong to the retrieved. The combined method showed 100% accuracy in training phase and 100% test phase accuracy.