基于函数变换的水下图像目标分割和特征提取

Target segmentation and feature extraction for undersea image base on function transformation

针对海水信道的特殊性以及成像环境的复杂性，对视觉系统的图像处理和特征提取带来的影响，提出了一种基于模糊变换的图像分割和基于函数变换的特征提取方法，以克服水下不确定因素给目标识别带来的困难，并对其进行了仿真试验。试验结果表明，此方法在对深海烟囱图像的分割和特征提取上能够取得好的效果，可有效地克服水下图像灰度分布不均匀和环境不确定因素的干扰，实现了难于分类判别的深海热液喷口目标的区分。

An image segmentation method based on fuzzy transformation and a feature extraction method based on function transformation are presented in this paper in order to eliminate the effects, which are brought by the particularity of undersea channels and complexity of image obtaining environment, on image processing and feature extraction of vision system. The methods are emulated in the experiment to get over with the trouble brought by uncertain factors in the undersea environment during the process of target-identification. The experimental results have demonstrated that, the approach is valid for target segmentation and feature extraction of undersea hydrothermal vent image. The vision system can be effectively protected from gray-level asymmetric distributing and uncertain environmental interference. The nondescript target differentiation of undersea hydrothermal vent can be achieved.