Abstract
This article proposes a novel contour-based mid-level shape description method for shape classification. This method resolves the shortcomings of low-level shape descriptors in dealing with the shapes of objects with large intra-class changes and non-linear deformation (articulation, occlusion and noise), thus improving the accuracy of shape classification. First, we extract the outer contour of an object and sample it. We next describe each sampling point on the shape contour with a triangular feature and regard it as a local feature. Then, a shape codebook is learned, and the Fisher vector encoding method is used to produce a compact mid-level shape feature. Finally, the learned mid-level shape features are sent to the linear support vector machine (SVM) classifier for shape recognition. The proposed method has been extensively tested on several standard shape datasets, and the experimental results show that our approach attains high accuracy of shape classification. Comparisons to other state-of-the-art shape classification approaches further prove the superiority and effectiveness of our method.
Highlights
Shape is an important visual information of a target object, and it is an important basis for the human visual system to recognize and classify the target object
Subsequent experiments showed that the deep learning method is not the most effective method for 2D shape recognition through subsequent experiments, and that our proposed method achieved the best performance in shape classification task, superior to the traditional shape classification method and to the shape classification method based on deep learning
EXPERIMENTAL RESULTS We evaluated the classification performance of our method on several standard shape datasets and compared it with the state-of-the-art shape classification approaches discussed
Summary
Shape is an important visual information of a target object, and it is an important basis for the human visual system to recognize and classify the target object. This article primarily constructs the mid-level representation based on the contour information of a shape. There has been some related work on the construction of mid-level features for shape-based object recognition, such as literature [21]–[23]. The most similar method to the work of this article is literature [22], which is based on the contour information of a shape, and uses the bag of words (BOW) model to construct the mid-level shape representation. Unlike the BOW model used in [22] to construct mid-level features, the proposed method adopts the Fisher Vector (FV) encoding method [24], [25], which can describe the first-order and second-order statistical information of data.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have