Multimedia data for efficient detection of visual objects

Abstract

The aim of this paper is to present multimedia data for efficient graph-based method to detect visual objects from colour digital images and to extract their colour and geometric features, in order to determine later the contours of the visual objects and to perform syntactic analysis of the determined shapes. The presented method is a general-purpose segmentation algorithm and it produces good results from two different perspectives: (a) from the perspective of perceptual grouping of regions from the natural images, and also (b) from the perspective of determining regions if the input images contain visual objects. We present a unified framework for planar image segmentation and contour extraction that uses a virtual hexagonal structure defined on the set of the image pixels. This method may be extended for volumetric digital images. Despite of the majority of multimedia data for the segmentation methods our method does not require any parameter to be chosen in order to produce a better segmentation and thus our method it is totally adaptive. To investigate the performance of the proposed method, we conduct experiments by comparing our segmentation results with the results produced by other six well known segmentation algorithms.