Two-dimensional Otsu’s Zigzag Thresholding Segmentation Method

Abstract

In the two-dimensional histogram thresholding method, the segmentation accuracy could be degraded due to insufficient misclassification. An improved image segmentation method combining a priori knowledge of two-dimensional histogram and fully considering the influence of edges, the two-dimensional Otsu’s zigzag thresholding segmentation method is proposed. We combine a priori information about the edge regions and noisy regions in a two-dimensional histogram, use a zigzag threshold as a segmentation criterion to correct the overall error classification and use small probability events to determine the line equations to achieve segmentation adaptively. Based on extensive experimentation, our method has been observed to significantly outperform comparable techniques.