ContourCNN: convolutional neural network for contour data classification
This addresses shape classification for contour data, but it is incremental as it adapts existing CNN techniques to a specific representation.
The paper tackles shape classification from contour data by proposing ContourCNN, which uses circular convolution and priority pooling layers to handle cyclical and sparse representations, achieving high classification accuracy on EMNIST letters and digits.
This paper proposes a novel Convolutional Neural Network model for contour data analysis (ContourCNN) and shape classification. A contour is a circular sequence of points representing a closed shape. For handling the cyclical property of the contour representation, we employ circular convolution layers. Contours are often represented sparsely. To address information sparsity, we introduce priority pooling layers that select features based on their magnitudes. Priority pooling layers pool features with low magnitudes while leaving the rest unchanged. We evaluated the proposed model using letters and digits shapes extracted from the EMNIST dataset and obtained a high classification accuracy.