Accurate object recognition in the underwater images using learning algorithms and texture features
Accurate object recognition in the underwater images using learning algorithms and texture features
复制标题
DOI：
10.1007/s11042-017-4459-6
复制
发表时间：
2017-02
影响因子：
3.6
通讯作者：
K. Srividhya;M. Ramya
中科院分区：
文献类型：
--
作者：
K. Srividhya;M. Ramya
水下图像处理由于其环境条件和光照不足而非常具有挑战性。使用自动驾驶车辆从海洋捕获的图像通常是不均匀照明的，并且由于底层环境而包含噪声。由于环境、目标形状和方向的变化，水下目标识别是一项具有挑战性的任务。传统的基于空间信息的分割算法在水下图像中往往由于灰度变化较小而不能得到精确的分割。需要表示对象特性的纹理信息。提取了自相关、和平均、和方差、和熵等统计特征。这些被作为学习算法的输入，并进行训练以有效地对感兴趣的对象和背景进行分类。链编码进一步应用于物体识别。所提出的方法实现了96%的最大分类准确率。
Underwater image processing is very challenging due to its environmental conditions and poor sunlight. Images captured from the ocean using autonomous vehicles are often non-uniformly illuminated and contain noise due to the underlying environment. Object recognition is a challenging task under water due to the variation in the environment, target shape and orientation. Traditional algorithms based on spatial information may not lead to accurate segmentation as the intensity variation is often less in underwater images. Texture information representing the characteristics of the object is needed. Statistical features like autocorrelation, sum average, sum variance and sum entropy were extracted. These were fed as input to learning algorithms and training was done to effectively classify the object of interest and background. Chain coding was further applied for object recognition. The proposed methodology achieved a maximum classification accuracy of 96%.