Pixel-wise Deep Learning for Contour Detection
This is an incremental improvement for computer vision tasks like image segmentation.
The paper tackles contour detection by using DenseNet to extract per-pixel features and an SVM classifier, achieving performance verified on the BSDS500 dataset.
We address the problem of contour detection via per-pixel classifications of edge point. To facilitate the process, the proposed approach leverages with DenseNet, an efficient implementation of multiscale convolutional neural networks (CNNs), to extract an informative feature vector for each pixel and uses an SVM classifier to accomplish contour detection. In the experiment of contour detection, we look into the effectiveness of combining per-pixel features from different CNN layers and verify their performance on BSDS500.