Abstract | ||
---|---|---|
Contour detection plays an important role in a wide range of applications such as image segmentation, object detection, shape matching, scene understanding, etc. In this study, we conduct a comprehensive analysis of contour detection using existing convolutional neural network (CNN) architectures. Given that contour detection can be considered as a classification task (e.g., contour or non-contour), six types of pretrained CNN (trained on ImageNet dataset) are individually used for domain-specific fine-tuning on contour dataset. The contour detection can then be achieved by sliding-window strategy, in which each image window (corresponding to a local patch) is used to extract features followed by classification. The features extraction is implemented by extracting the activation vectors from the fully-connected layers (except for the classification layer) of a fine-tuned CNN. Random forest classifier is adopted to predict whether the central pixel of a local patch is passed by contour or not. Experiments on a widely-used dataset called Berkeley Segmentation Data Set (BSDS500) demonstrate that fine-tuning technique can significantly improve the performance of contour detection. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1145/3195106.3195145 | PROCEEDINGS OF 2018 10TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND COMPUTING (ICMLC 2018) |
Keywords | Field | DocType |
Contour detection, convolutional neural network, fine-tuning | Object detection,Pattern recognition,Computer science,Segmentation,Convolutional neural network,Fine-tuning,Image segmentation,Pixel,Artificial intelligence,Random forest | Conference |
Citations | PageRank | References |
0 | 0.34 | 15 |
Authors | ||
5 |