RGB-D classification using feature selection on the combination of different features
RGB-D classification using feature selection on the combination of different features
复制标题
DOI：
10.1109/ictemsys.2017.7958770
复制
发表时间：
2017-05
期刊：
影响因子：
--
通讯作者：
Wasif Khan;E. Phaisangittisagul;Luqman Ali;D. Gansawat;I. Kumazawa
中科院分区：
文献类型：
--
作者：
Wasif Khan;E. Phaisangittisagul;Luqman Ali;D. Gansawat;I. Kumazawa
为了提高目标识别中的分类性能，已经从各种技术中创建了许多不同的特征。然而，这些特征可能是冗余的或与实现分类模型无关。因此，特征选择被认为是为特定模型选择相关特征子集的重要工具之一。在本文中，我们应用特征选择方法，形成一个新的子集的特征，从不同的特征提取算法，以便我们可以提高目标的分类性能。在实验中，我们展示了过滤器方法和包装器方法的使用RGB-D对象数据集和结果是有前途的。
To improve the classification performance in object recognition, many different features have been created from various techniques. However, these features may be redundant or irrelevant to implement the classification model. So, feature selection is considered one of the important tools that can be employed to select a subset of relevant features for specific model. In this paper, we applied feature selection method to form a new subset of features obtained from different feature extraction algorithms so that we can improve the object's classification performance. In the experiments, we demonstrated the use of filter method and wrapper methods for RGB-D object dataset and the results were promising.