Abstract
Classification and evaluation of sketch works is an important step in sketch teaching. The speed for manual evaluation of massive works is very slow and its cost is also high. Regarding the sketch works after scoring is hard to be collected, the limitations from small dataset create many challenges for training a great scoring model. In this paper, we firstly collects 400 teaching sketches of college students from South China Normal University and constructs a dataset. Then an improved transfer learning model based on ResNet50 was proposed for learning the high-level abstract characteristics of sketch works because transfer learning can reuse knowledge from a large dataset and employ the feature extraction capability in sketch subject scenario. In our improved model, three strategies (i.e., data augmentation, dropout and feature fusion) are used to prevent the model from early overfitting and improve the accuracy and stability of the model. Comparing with traditional feature extraction algorithms, our model provides an end-to-end mechanism. Moreover, compared with the accuracy of AlexNet and ResNet50, it is improved by 24.2% and 7.82% respectively. Our results indicate that the three strategies have outstanding effects for the transfer learning model for sketch works ranking.
Similar content being viewed by others
References
Changchun Z (2015) Art works retrieval and classification. Master?s thesis. Zhejiang University
Chao L, Shouqian* S, Xin M, Weixing W, Zhichuan T (2017) Application of deep convolutional features in sketch works classification and evaluation. J Comput-Aided Design Comput Graph 029(010):1898–1904
Fan GF, Guo YH, Zheng JM, Hong WC (2020) A generalized regression model based on hybrid empirical mode decomposition and support vector regression with back-propagation neural network for mid-short-term load forecasting. Journal of Forecasting
Fan GF, Wei X, Li YT, Hong WC (2020) Forecasting electricity consumption using a novel hybrid model. Sustainable Cities and Society, pp 102320
Glorot X, Bordes A, Bengio Y (2011) Deep Sparse Rectifier Neural Networks. J Mach Learn Res 15:315–323
Hao X, Zhang G, Ma S (2016) Deep learning. Int J Semantic Comput 10(03):417–439
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: pp 770–778
He K, Zhang X, Ren S, Sun J (2016) Deep Residual Learning for Image Recognition
Hu J, Shen L, Albanie S, Sun G, Wu E Squeeze-and-Excitation Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 2017; PP(99)
Hughes JM, Graham DJ, Rockmore DN (2010) Quantification of artistic style through sparse coding analysis in the drawings of Pieter Bruegel the Elder. Proc Natl Acad Sci 107(4):1279–1283
Huang Hua CW (2009) Real—time image sketch. Chinese J Comput 1:32
Iwendi C, Moqurrab SA, Anjum A, Khan S, Mohan S, Srivastava G (2020) N-Sanitization: A semantic privacy-preserving framework for unstructured medical datasets. Comput Commun 161:160–171
Jia-chuan S (2013) Computerized Learning and Classification of Traditional Chinese IWPs(Ink and Wash Paintings). PhD thesis Tianjin: Tianjin University
Jingte T (2018) The Research Sketch-Based Object Detection And Retrieval. Master’s thesis Jiangxi Normal University
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: pp 1097–1105
Li MW, Geng J, Hong WC, Zhang LD (2019) Periodogram estimation based on LSSVR-CCPSO compensation for forecasting ship motion. Nonlinear Dyn 97(4):2579–2594
Lu C, Xu L, Jia J (2012) Combining sketch and tone for pencil drawing production. In: Citeseer, pp 65–73
Peng L (2009) Neural Network-Based Chinese Ink-Painting Artistic Style Learning[D] Tianjing: Tianjing University
SANG Sang DYSY (2010) Pencil Drawing Generation Based on Texture and Profile. Journal of Shanghai University(Natural Science) 16(3):312–317
Sun ZJ, Xue L, Xu YM, Wang Z (2012) Overview of deep learning. Appl Res Comput 29(8):2806–2810
Shan-xiao G (2016) Research on real time sketch style rendering algotithm based on GPU. Master’s thesis Fujian Normal University
Shuo HDw SUN (2007) Efficient region-based pencil drawing. Comput Eng Appl 43(14):34–37
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. The J Mach Learn Res 15(1):1929–1958
Torrey L, Shavlik J (2010) Transfer learning. In: IGI global, pp 242–264
Xie S, Girshick R, Dollár P, Tu Z, He K (2016) Aggregated Residual Transformations for Deep Neural Networks
Yi R, Liu YJ, Lai YK, Rosin PL (2019) APDrawingGAN: Generating Artistic Portrait Drawings from Face Photos with Hierarchical GANs. In: pp 10743–10752
Yi R, Liu YJ, Lai YK, Rosin PL (2020) Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping. In: pp 8217–8225
Yu W, Yang K, Yao H, Sun X, Xu P (2017) Exploiting the complementary strengths of multi-layer CNN features for image retrieval. Neurocomputing 237:235–241
Yu-sheng W Research on Computer Classification of Chinese Painting. PhD thesis. Xi‘an University of Architecture and Technology
Yuzhi L, Jiachuan S, Bin H (2018) Improved Embedded Learning for Classification of Chinese Paintings. J Comput-Aided Design Comput Graph 30(5):893–900
Zagoruyko S, Komodakis N (2016) Wide residual networks. arXiv:1605.07146
Zhang Z, Ding S, Sun Y (2020) A support vector regression model hybridized with chaotic krill herd algorithm and empirical mode decomposition for regression task. Neurocomputing
Zhang Z, Hong WC (2019) Electric load forecasting by complete ensemble empirical mode decomposition adaptive noise and support vector regression with quantum-based dragonfly algorithm. Nonlinear Dyn 98(2):1107–1136
Zhang H, Wu C, Zhang Z et al (2020) ResNeSt. Split-Attention Networks
Zheng W, Hao-yue L, Hong-shan X, Mei-Jun S (2017) Chinese Painting Emotion Classification Based on Convolution Neural Network and SVM. Journal of Nanjing Normal University(Natural Science Edition) 40(3):79
Acknowledgments
This work was partially supported by Guangdong Basic and Applied Basic Research Fund Regional Joint Fund Project (Key Project) (2020B1515120089) and the Featured Innovation Project of Guangdong Province Department of Education (Natural Science)(2019KTSCX035).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yu, S., Lin, Z., Liang, J. et al. Sketch works ranking based on improved transfer learning model. Multimed Tools Appl 80, 33663–33678 (2021). https://doi.org/10.1007/s11042-021-11305-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11305-0