Williams Kresimir
IEEE Trans Image Process. 2016 Apr;25(4):1862-72. doi: 10.1109/TIP.2016.2535342. Epub 2016 Feb 26.
Live fish recognition is one of the most crucial elements of fisheries survey applications where the vast amount of data is rapidly acquired. Different from general scenarios, challenges to underwater image recognition are posted by poor image quality, uncontrolled objects and environment, and difficulty in acquiring representative samples. In addition, most existing feature extraction techniques are hindered from automation due to involving human supervision. Toward this end, we propose an underwater fish recognition framework that consists of a fully unsupervised feature learning technique and an error-resilient classifier. Object parts are initialized based on saliency and relaxation labeling to match object parts correctly. A non-rigid part model is then learned based on fitness, separation, and discrimination criteria. For the classifier, an unsupervised clustering approach generates a binary class hierarchy, where each node is a classifier. To exploit information from ambiguous images, the notion of partial classification is introduced to assign coarse labels by optimizing the benefit of indecision made by the classifier. Experiments show that the proposed framework achieves high accuracy on both public and self-collected underwater fish images with high uncertainty and class imbalance.
活鱼识别是渔业调查应用中最关键的要素之一，在这些应用中需要快速获取大量数据。与一般场景不同，水下图像识别面临着图像质量差、物体和环境不受控制以及获取代表性样本困难等挑战。此外，由于需要人工监督，大多数现有的特征提取技术难以实现自动化。为此，我们提出了一种水下鱼类识别框架，该框架由完全无监督的特征学习技术和抗错误分类器组成。基于显著性和松弛标记对物体部分进行初始化，以正确匹配物体部分。然后根据适应性、分离性和区分标准学习非刚性部分模型。对于分类器，一种无监督聚类方法生成一个二元类层次结构，其中每个节点都是一个分类器。为了利用模糊图像中的信息，引入了部分分类的概念，通过优化分类器做出的不确定决策的益处来分配粗略标签。实验表明，所提出的框架在具有高度不确定性和类别不平衡的公共和自采集水下鱼类图像上均取得了高精度。
