An Inventive Marker based Section Assimilation Technique using Concept of Seeding.

Efficient and effective object extraction of image in image segmentation is an important task in pattern recognition and computer vision. It is very hard to find a fully automatic object extraction method in practical applications for natural images, interactive schemes. Schemes with a few simple user inputs are good solutions. However, they are tedious and not effective in some situations like extracting object from complex background. Therefore, this paper proposes a novel unsupervised image segmentation framework to deal with the above problem. A still image is divided into many small regions by some low level segmentation methods (mean shift in this case) at first, then the users needs to roughly indicate the location and region of the object and background by using strokes, which are called markers. A novel maximum-correlation based section assimilation mechanism is proposed to guide the merging process with the help of markers. A region R is merged with its adjacent region Q if Q has the highest similarity with Q among all Q's adjacent regions. The proposed method automatically merges the regions that are initially segmented by mean shift segmentation, and then effectively extracts the object contour by labeling all the non-marker regions as either background or object. The section assimilation process is adaptive to the image content and it does not need to set the similarity threshold in advance. The extensive experiments demonstrate the efficiency and effectiveness of the proposed method.