Spatial Layout Image Retrieval based on Fast Image Segmentation using K-Means Clustering

Abstract

An image retrieval system that takes the input query image and retrieves the similar images according to the spatial coordinates and which uses the k means clustering algorithm for its segmentation. Most existing Content Based Image Retrieval based on the images of color, text documents, informative charts, and shape. This paper aims to search the images with similar spatial layouts and the retrieval process which includes the feature extraction methods and image matching criteria. This paper employs K-Means clustering for image segmentation, and the features of small segments of images are extracted based on the segmentation results. To match the segments of two images, the distance between them can be computed by Eucliedean distance to evaluate the similarity of their spatial layouts.