Hand-drawn sketch recognition with a double-channel convolutional neural network
Abstract In hand-drawn sketch recognition, the traditional deep learning method has the problems of insufficient feature extraction and low recognition rate. To solve this problem, a new algorithm based on a dual-channel convolutional neural network is proposed. Firstly, the sketch is preprocessed t...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2021-08-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13634-021-00752-4 |
| _version_ | 1830516574605279232 |
|---|---|
| author | Lei Zhang |
| author_facet | Lei Zhang |
| author_sort | Lei Zhang |
| collection | DOAJ |
| description | Abstract In hand-drawn sketch recognition, the traditional deep learning method has the problems of insufficient feature extraction and low recognition rate. To solve this problem, a new algorithm based on a dual-channel convolutional neural network is proposed. Firstly, the sketch is preprocessed to get a smooth sketch. The contour of the sketch is obtained by the contour extraction algorithm. Then, the sketch and contour are used as the input image of CNN. Finally, feature fusion is carried out in the full connection layer, and the classification results are obtained by using a softmax classifier. Experimental results show that this method can effectively improve the recognition rate of a hand-drawn sketch. |
| first_indexed | 2024-12-22T03:45:15Z |
| format | Article |
| id | doaj.art-4a13b53f2b634ed79c7a9bd98b6f7baa |
| institution | Directory Open Access Journal |
| issn | 1687-6180 |
| language | English |
| last_indexed | 2024-12-22T03:45:15Z |
| publishDate | 2021-08-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-4a13b53f2b634ed79c7a9bd98b6f7baa2022-12-21T18:40:09ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61802021-08-012021111210.1186/s13634-021-00752-4Hand-drawn sketch recognition with a double-channel convolutional neural networkLei Zhang0Digital Media College of Chongqing College of Electronic EngineeringAbstract In hand-drawn sketch recognition, the traditional deep learning method has the problems of insufficient feature extraction and low recognition rate. To solve this problem, a new algorithm based on a dual-channel convolutional neural network is proposed. Firstly, the sketch is preprocessed to get a smooth sketch. The contour of the sketch is obtained by the contour extraction algorithm. Then, the sketch and contour are used as the input image of CNN. Finally, feature fusion is carried out in the full connection layer, and the classification results are obtained by using a softmax classifier. Experimental results show that this method can effectively improve the recognition rate of a hand-drawn sketch.https://doi.org/10.1186/s13634-021-00752-4Hand-drawn sketch recognitionMulti-channelConvolution neural networkDeep learningDouble-channel CNN |
| spellingShingle | Lei Zhang Hand-drawn sketch recognition with a double-channel convolutional neural network EURASIP Journal on Advances in Signal Processing Hand-drawn sketch recognition Multi-channel Convolution neural network Deep learning Double-channel CNN |
| title | Hand-drawn sketch recognition with a double-channel convolutional neural network |
| title_full | Hand-drawn sketch recognition with a double-channel convolutional neural network |
| title_fullStr | Hand-drawn sketch recognition with a double-channel convolutional neural network |
| title_full_unstemmed | Hand-drawn sketch recognition with a double-channel convolutional neural network |
| title_short | Hand-drawn sketch recognition with a double-channel convolutional neural network |
| title_sort | hand drawn sketch recognition with a double channel convolutional neural network |
| topic | Hand-drawn sketch recognition Multi-channel Convolution neural network Deep learning Double-channel CNN |
| url | https://doi.org/10.1186/s13634-021-00752-4 |
| work_keys_str_mv | AT leizhang handdrawnsketchrecognitionwithadoublechannelconvolutionalneuralnetwork |