Back to Search
Start Over
Combining CNN with Hand-Crafted Features for Image Classification
- Source :
- 2018 14th IEEE International Conference on Signal Processing (ICSP).
- Publication Year :
- 2018
- Publisher :
- IEEE, 2018.
-
Abstract
- Convolutional neural networks (CNN) have achieved outstanding performance in image recognition tasks, but many hand-crafted features still play important roles in some areas. Hand-crafted features are designed to describe image content from specific aspects, which may provide complementary information for CNN in image classification tasks. This paper explores feature fusion methods and proposes a novel framework for combining CNN with hand-crafted features. The framework has two main advantages. First, feature encoder can encode non-normalized features in CNN, which takes advantage of some good edge, texture and local features. Second, joint training strategy makes features fuse better in CNN. We validate that many handcrafted features help to improve the performance of origin CNN. Experiments show our method outperforms the origin CaffeNet on Cifar10 dataset with 79.16% accuracy.
- Subjects :
- Contextual image classification
business.industry
Computer science
Feature extraction
Pattern recognition
02 engineering and technology
021001 nanoscience & nanotechnology
Convolutional neural network
Feature (computer vision)
Histogram
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Enhanced Data Rates for GSM Evolution
Artificial intelligence
0210 nano-technology
business
Encoder
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2018 14th IEEE International Conference on Signal Processing (ICSP)
- Accession number :
- edsair.doi...........3e3a0534c0a8f1f9552fea69d36f71cc