An adaptive technique for the extraction of object region and boundary from images with complex environment

Abstract

A faster and accurate method for the extraction of object region and boundary from images with complex background environment is presented in this paper. The segmentation procedure begins with the computation of an optimum threshold to distinguish the darker regions in the image. It is an automatic thresholding algorithm that would work under all lighting conditions, where prefixing of threshold value is considered ineffective. The centre of mass of this thresholded region acts as a seed for further processing. Then the object region is obtained by using a region growing technique called integrated neighbourhood search. A quad-structure based technique is used to enhance the speed of region search significantly. A back projection algorithm is used to optimise the search for the pixels belonging to the object region.. A boundary thinning and connecting algorithm based on the application of a novel search window on the preliminary boundary is used to obtain a connected single pixel width boundary. The new method does not need a priori knowledge about the image characteristics. The main advantage of the proposed technique is its high-speed response, which brought an average of 36% decrease in the processing time involved that facilitates real-time analysis of the images.