论文标题
一种用于纹理识别的本地模式的蜂窝自动机方法
A cellular automata approach to local patterns for texture recognition
论文作者
论文摘要
纹理识别是计算机视觉中最重要的任务之一，尽管基于学习的方法最近取得了成功，但仍然需要基于模型的解决方案。当可用于培训的数据量不足以大，在几个应用领域或计算资源受到限制时，尤其是这种情况。在这种情况下，我们在这里提出了一种纹理描述符的方法，该方法将复杂对象的表示能力与蜂窝自动机的表示能力与局部描述符在纹理分析中的已知有效性相结合。该方法为局部二进制描述符启发的自动机制定了新的过渡功能。它可以抵消每个单元的新状态与以前的状态，通过这种方式引入了“控制的确定性混乱”的想法。描述符是从细胞态的分布中获得的。提出的描述符应用于基准数据集和现实世界中的纹理图像分类，即基于其叶片表面质地识别植物物种的描述符。我们的建议优于其他经典和最先进的方法，尤其是在现实世界中的问题，因此揭示了其在某个阶段涉及质地识别的许多实际任务中应用的潜力。
Texture recognition is one of the most important tasks in computer vision and, despite the recent success of learning-based approaches, there is still need for model-based solutions. This is especially the case when the amount of data available for training is not sufficiently large, a common situation in several applied areas, or when computational resources are limited. In this context, here we propose a method for texture descriptors that combines the representation power of complex objects by cellular automata with the known effectiveness of local descriptors in texture analysis. The method formulates a new transition function for the automaton inspired on local binary descriptors. It counterbalances the new state of each cell with the previous state, in this way introducing an idea of "controlled deterministic chaos". The descriptors are obtained from the distribution of cell states. The proposed descriptors are applied to the classification of texture images both on benchmark data sets and a real-world problem, i.e., that of identifying plant species based on the texture of their leaf surfaces. Our proposal outperforms other classical and state-of-the-art approaches, especially in the real-world problem, thus revealing its potential to be applied in numerous practical tasks involving texture recognition at some stage.
