Multiscale fully convolutional network with application to industrial inspection
Authors:
- 1 March 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
In recent years, deep learning, particularly Convolutional Neural Network (CNN), has shown great efficacy for solving various vision tasks. In image segmentation, it has been demonstrated that a CNN can greatly outperform other approaches. However, special attention has to be paid towards setting various parameters in the CNN that affects the scale of the feature map generated at the last convolutional layer, where scale here refers to the ratio of the number of pixels in the original input image that correspond to each pixel in the feature map. Quite often, the optimal settings are tied to the specific problem on hand and can be fairly challenging to determine. To overcome such an issue, this paper proposes a multiscale Fully Convolutional Network (FCN) that combines networks trained at various scales, thereby allowing for conducting segmentation more generically. Moreover, such a multiscale architecture allows for incremental fine-tuning as more training images become available later on and new networks can be trained and added to the combined network. Such flexibility has great utility in applications such as industrial inspection, where training images may not be readily available initially, but yet requires a high level of accuracy. This paper will validate our findings by reporting the results that we have obtained by applying multiscale FCN to the inspection of aircraft engine part.Keywords
This publication has 8 references indexed in Scilit:
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Part-Based R-CNNs for Fine-Grained Category Detection2014
- Learning Rich Features from RGB-D Images for Object Detection and Segmentation2014
- Learning Hierarchical Features for Scene LabelingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- ImageNet: A large-scale hierarchical image database2009
- Linear spatial pyramid matching using sparse coding for image classification2009
- Sampling Strategies for Bag-of-Features Image Classification2006
- Toward automatic phenotyping of developing embryos from videosIEEE Transactions on Image Processing, 2005