Color image segmentation based on adaptive local thresholds

Abstract

The goal of still color image segmentation is to divide the image into homogeneous regions.Object extraction, object recognition and object-based compression are typical applications that use still segmentation as a low-level image processing. In this paper we present a new method for color image segmentation. The proposed algorithm divides the image into homogeneous regions by local thresholds. The number of thresholds and their values are adaptively derived by an automatic process, where local information is taken into consideration. First, the watershed algorithm is applied. Its results are used as an initialization for the next step, which is iterative merging process. During the iterative process regions are merged and local thresholds are derived. The thresholds are determined one-by-one at different times during the merging process. Every threshold is calculated by local information on any region and its surroundings. Any statistical information on the input images is not given. The algorithm is found to be reliable and robust to different kind of images.

InfraPhenoGrid: A scientific workflow infrastructure for plant phenomics on the Grid

“…In particular, several variations of subworkflow B can be designed, resulting in the use of several Binarization algorithms (as mentioned in Table 1). The results obtained by such variations Binarization algorithms Time (seconds) Adaptive Threshold [21] 62.1 HSV [22] 85.7 Mean Shift [23] 73.9 Table 1: Execution time of the workflow illustrated in Figure 9 with variations of subworkflow B on one plant measured during one seasonal growth (5 weeks). This experiment gathered 124 images.…”

Segmentation of Road Guidance Sign Symbols and Characters Based on Normalized RGB Chromaticity Diagram

“…On the contrary, the split and merge algorithm subdivide an image initially into a set of arbitrary, disjointed regions and then merge and/or split the regions in attemp to satisfy the predefined criteria [9]. These techniques have two main drawbacks [1]: They are both strongly dependent on global predefined criteria; while the region growing technique depends also on initial segments, which is the first pixel/segment to be scanned, and the order of the process.…”

“…The first step to extract information in an image is image segmentation, which divides the image into non overlapping areas [1]. The area is a collection of pixels having the same characteristic, such as color, gray level, texture, etc.…”

Design of Camouflage Pattern Based on Mathematical Morphology

“…Thinking approach helps morphology based on shape or graphics. Morphological methods in image information is the basic unit of binary pixels [4][5][6][7].…”