A Study on Applying the SRCNN Model and Bicubic Interpolation to Enhance Low-Resolution Weeds Images for Weeds Classification
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In the image object classification problem, low-resolution images may have a negative impact on the classification result, especially when the classification method, such as a convolutional neural network (CNN) model, is trained on a high-resolution (HR) image dataset. In this paper, we analyze the behavior of applying a classical super-resolution (SR) method such as bicubic interpolation, and a deep CNN model such as SRCNN to enhance low-resolution (LR) weeds images used for classification. Using an HR dataset, we first train a CNN model for weeds image classification with a default input size of 128×128. Then, given an LR weeds image, we rescale to default input size by applying the bicubic interpolation or the SRCNN model. We analyze these two approaches on the Chonnam National University (CNU) weeds dataset and find that SRCNN is suitable for the image size is smaller than 80×80, while bicubic interpolation is convenient for a larger image.
Abstract
In the image object classification problem, low-resolution images may have a negative impact on the classification result, especially when the classification method, such as a convolutional neural network (CNN) model, is trained on a high-resolution (HR) image dataset. In this paper, we analyze the behavior of applying a classical super-resolution (SR) method such as bicubic interpolation, and a deep CNN model such as SRCNN to enhance low-resolution (LR) weeds images used for classification. Using an HR dataset, we first train a CNN model for weeds image classification with a default input size of 128×128. Then, given an LR weeds image, we rescale to default input size by applying the bicubic interpolation or the SRCNN model. We analyze these two approaches on the Chonnam National University (CNU) weeds dataset and find that SRCNN is suitable for the image size is smaller than 80×80, while bicubic interpolation is convenient for a larger image.
참고문헌 (18)
- 노순국, "인공지능 기반 구글넷 딥러닝과 IoT를 이용한 의류 분류", 스마트미디어저널, 9(3), pp.41~45 (2020), (사)한국스마트미디어학회[DOI]
- 전소연, "딥러닝 기반 영상 분석 알고리즘을 이용한 실시간 작업자 안전관리 시스템 개발", 스마트미디어저널, 9(3), pp.25~30 (2020), (사)한국스마트미디어학회[DOI]
- Minh-Trieu Tran, "Super-resolution in Music Score Images by Instance Normalization", 스마트미디어저널, 8(4), pp.64~71 (2019), (사)한국스마트미디어학회[DOI]
- Gholamreza Anbarjafari, "Image Super Resolution Based on Interpolation of Wavelet Domain High Frequency Subbands and the Spatial Domain Input Image", ETRI Journal, 32(3), pp.390~394 (2010), 한국전자통신연구원
- J. W. Hwang, "Adaptive image interpolation based on local gradient features", IEEE signal processing letters, 11(3), pp.359~362 (2004)
- H. Demirel, "Discrete wavelet transform-based satellite image resolution enhancement", IEEE transactions on geoscience and remote sensing, 49(6), pp.1997~2004 (2011)
- N. Reddy, "Multi-frame super resolution for ocular biometrics", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2018)
- P. D. Sawant, "Resolution enhancement and quality assessment of MRI images using different interpolation techniques", 2017International Conference on Intelligent Computing and Control (I2C2) (2017), IEEE
- C. Ledig, "Photo-realistic single image superresolution using a generative adversarial network", Proceedings of the IEEE conference on computer vision and pattern recognition (2017)
- B. Lim, "Enhanced deep residual networks for single image super-resolution", Proceedings of the IEEE conference on computer vision and pattern recognition workshops (2017)
- C. Dong, "Image super-resolution using deep convolutional networks", IEEE transactions on pattern analysis and machine intelligence, 38(2), pp.295~307 (2015)
- V. Sharma, "Classificationdriven dynamic image enhancement", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.4033~4041 (2018)
- K. Simonyan, "Very deep convolutional networks for large-scale image recognition", arXiv preprint arXiv:1409.1556, ~ (2014)
- Y. Taigman, "Deepface: Closing the gap to human-level performance in face verification", Proceedings of the IEEE conference on computer vision and pattern recognition (2014)
- M. Lin, "Network in network", arXiv preprint arXiv:1312.4400, ~ (2013)
- Hoang-Trong Vo, "Analyze weeds classification with visual explanation based on Convolutional Neural Networks", 스마트미디어저널, 8(3), pp.31~40 (2019), (사)한국스마트미디어학회[DOI]
- V. H. Trong, "Late fusion of multimodal deep neural networks for weeds classification", Computers and Electronics in Agriculture (2020)
- L. N. Smith, "Cyclical learning rates for training neural networks", 2017 IEEE Winter Conference on Applications of Computer Vision (WACV) (2017)