Region Merging Method Research Articles

Unsupervised Method of Object Retrieval Using Similar Region Merging and Flood Fill

In this work; we address a novel interactive framework for object retrieval using unsupervised similar region merging and flood fill method which models the spatial and appearance relations among image pixels. Efficient and effective image segmentation is usually very hard for natural and complex images. This paper presents a new technique for similar region merging and objects retrieval. The users only need to roughly indicate the after which steps desired objects boundary is obtained during merging of similar regions. A novel similarity based region merging mechanism is proposed to guide the merging process with the help of mean shift technique. A region R is merged with its adjacent regions Q if Q has highest similarity with R among all Q’s adjacent regions. The proposed method automatically merges the regions that are initially segmented through mean shift technique, and then effectively extracts the object contour by merging all similar regions. Extensive experiments are performed on 22 object classes (524 images total) show promising results.

画像処理・符号化とアプリケーション アフィン動きパラメータのロバスト推定に基づく動領域の統合

Moving object extraction in video sequences has been studied from various technical viewpoints. We propose a region-merging method for moving object extraction based on robust motion estimation. An over-segmented image is obtained by means of morphological watershed algorithm, and a robust motion estimation method using feature points and an evaluation function composed of motion estimation errors is then applied. Computer simulations demonstrated the merging precision of the proposed method.

Brain MR images segmentation using statistical ratio: Mapping between watershed and competitive Hopfield clustering network algorithms

Conventional watershed segmentation methods invariably produce over-segmented images due to the presence of noise or local irregularities in the source images. In this paper, a robust medical image segmentation technique is proposed, which combines watershed segmentation and the competitive Hopfield clustering network (CHCN) algorithm to minimize undesirable over-segmentation. In the proposed method, a region merging method is presented, which is based on employing the region adjacency graph (RAG) to improve the quality of watershed segmentation. The relation of inter-region similarities is then investigated using image mapping in the watershed and CHCN images to determine more appropriate region merging. The performance of the proposed technique is presented through quantitative and qualitative validation experiments on benchmark images. Significant and promising segmentation results were achieved on brain phantom simulated data.

Real-time object segmentation using disparity map of stereo matching

This paper presents algorithms for the real-time object segmentation of the noisy disparity map obtained by stereo matching algorithm and its verification test using hardware architectures. The disparity map contains lots of noise from various causes, and it has to be refined by some noise filtering methods to make it useful for the object segmentation. Therefore refinement process is a necessary process prior to segmentation process. In our approach, refinement method based on noise removal technique is adopted for improvement of the disparity map quality. And the projection-based region merging method is used for object segmentation. The proposed algorithms are implemented in FPGA board. Results of the test show that our approach works precisely and its performance fits in conditions of real-time application. The developed real-time object segmentation system could be useful for various applications such as face recognition, object tracking, and other applications with the support of proper embedded software.

Improving image segmentation quality through effective region merging using a hierarchical social metaheuristic

This paper proposes a new evolutionary region merging method in order to efficiently improve segmentation quality results. Our approach starts from an oversegmented image, which is obtained by applying a standard morphological watershed transformation on the original image. Next, each resulting region is represented by its centroid. The oversegmented image is described by a simplified undirected weighted graph, where each node represents one region and weighted edges measure the dissimilarity between pairs of regions (adjacent and non-adjacent) according to their intensities, spatial locations and original sizes. Finally, the resulting graph is iteratively partitioned in a hierarchical fashion into two subgraphs, corresponding to the two most significant components of the actual image, until a termination condition is met. This graph-partitioning task is solved by a variant of the min-cut problem (normalized cut) using a hierarchical social (HS) metaheuristic. We have efficiently applied the proposed approach to brightness segmentation on different standard test images, with good visual and objective segmentation quality results.

The flat zone approach: A general low-level region merging segmentation method

This paper presents a segmentation method, the flat zone approach, that avoids some limitations of the watershed-plus-markers method. The watershed-plus-markers approach, which is the traditional segmentation technique in mathematical morphology, has two inherent problems: (1) the possible separation of a piecewise-constant region of the input image into several regions in the output partition, and (2) the problem of obtaining markers (connected components of pixels signaling significant regions) for features that are one or two pixels wide. These problems are related to the limited resolution power (for feature extraction) of gradient operators. The flat zone approach extends the region marker concept (to contain the entire (and not part of) regions) and requires neither the computation of a gradient function nor the modification of the support of the input image in order to increase the size of the features. Our approach works on the graph formed by the image flat zones (or piecewise-constant regions). This fact ensures that the input image regions are not broken and can consider all input flat zones regardless their size. An inclusion relationship between the flat zones of the input image and the regions of the output partition is imposed. That is, a flat zone segmentation method is a region (flat zone) merging method and behaves like a connected operator. Our method is robust (in the sense that it is invariant under certain intensity value transformations) and uses a hierarchical waiting queue algorithm that makes it extremely efficient.