Fine-grained geometric shapes: A deep classification task


  • Jorge Díaz-Ramírez Universidad de Tarapacá, Departamento de Ingeniería y Tecnologías, Facultad de Ingeniería, Iquique, Chile
  • Fabrizio Alvarez-Alvarez Universidad de Tarapacá, Departamento de Ingeniería y Tecnologías, Facultad de Ingeniería, Iquique, Chile
  • Ximena Badilla-Torrico Universidad de Tarapacá, Departamento de Ingeniería y Tecnologías, Facultad de Ingeniería, Iquique, Chile


Convolutional Neural Networks, Fine-grained, Image classification, Deep Learning, Transfer Learning


Although the importance of Deep Learning has been well established in recent years, its role in classifying objects in images is far from being understood in fine categories and this open problem remains to be solved in geometric shapes. Here we compare deep learning models using convolutional neural networks, in order to classify fine categories in geometrical figure type images. Through the proposed method we found that there are several configurations of base models that obtain accuracies close to 80%. The proposed method also allowed us to identify that using Transfer Learning increases the accuracy by about 7% compared to the base models. Overall, these data show that the number of examples plays an important role in obtaining good classification results, as well as their quality, since noisy data in a dataset can severely reduce the generalization performance of the model in question.


Download data is not yet available.

Author Biographies

Jorge Díaz-Ramírez, Universidad de Tarapacá, Departamento de Ingeniería y Tecnologías, Facultad de Ingeniería, Iquique, Chile

Jorge Diaz-Ramirez graduated in computer engineering from Universidad de Tarapacá, Chile, in 2009 and obtained a Master’s degree in Information Technology from Universidad Técnica Federico Santa María, Chile, in 2015. He is currently pursuing the Ph.D. degree in computer Science at the Universidad Católica de Chile, PUC. He has been an professor of Computer Engineering at Universidad de Tarapacá since 2012. His research interests include Machine Learning, Deep Learning and Visual Navigation.

Fabrizio Alvarez-Alvarez, Universidad de Tarapacá, Departamento de Ingeniería y Tecnologías, Facultad de Ingeniería, Iquique, Chile

Fabrizio Alvarez-Alvarez is Computer Engineer graduated from Universidad de Tarapacá, Chile. He currently works as a computer engineer in a private certification company. His interests are Machine Learning, deep learning and data analysis.

Ximena Badilla-Torrico, Universidad de Tarapacá, Departamento de Ingeniería y Tecnologías, Facultad de Ingeniería, Iquique, Chile

Ximena Badilla-Torrico is a professor in the Engineering Faculty of Universidad de Tarapacá, she has a career in computer engineering and an MBA grade. Her interests include Information Systems, Software Engineering and Machine Learning.


S. Russel and P. Norvig, Inteligencia Artificial Un enfoque Moderno, vol. 1. 2da ed., 2004.

C. V. Krishna, H. R. Rohit, and Mohana, “A review of artificial intelligence methods for data science and data analytics: Applications and research challenges,” in Proceedings of the International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2018, pp. 591–594, Institute of Electrical and Electronics Engineers Inc., 2 2019.

A. L. Samuel, “Some Studies in Machine Learning Using the Game of Checkers,” IBM Journal of Research and Development, vol. 3, pp. 210– 229, 7 1959.

T. M. Mitchell, “Does Machine Learning Really Work?,” AI Magazine, vol. 18, no. 3, pp. 11–20, 1997.

I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.

J. Salas, F. De Barros Vidal, and F. Martinez-Trinidad, “Deep Learning: Current State,” IEEE Latin America Transactions, vol. 17, pp. 1925– 1945, 12 2019.

L. C. Soto-Ayala and J. A. Cantoral-Ceballos, “Automatic Blood- Cell Classification via Convolutional Neural Networks and Transfer Learning,” IEEE Latin America Transactions, vol. 19, pp. 2028–2036, 5 2021.

Y. Le Cun, L. D. Jackel, B. Boser, J. S. Denker, H. P. Graf, I. Guyon, D. Henderson, R. E. Howard, and W. Hubbard, “Handwritten digit recog- nition: applications of neural network chips and automatic learning,” IEEE Communications Magazine, vol. 27, no. 11, pp. 41–46, 1989.

D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,” Nature, vol. 323, no. 6088, pp. 533– 536, 1986.

S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, pp. 1735–1780, 11 1997.

K. Cho, B. van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation,” in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), (Doha, Qatar), pp. 1724–1734, Association for Computational Linguistics, 10 2014.

R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation,” in 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587, 2014.

R. Girshick, “Fast R-CNN,” in 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1440–1448, 2015.

S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” in Advances in Neural Information Processing Systems (C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett, eds.), vol. 28, pp. 91–99, Curran Associates, Inc., 2015.

K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” in 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980–2988, 2017.

M. Hussain, J. J. Bird, and D. R. Faria, “Astudyoncnntransferlearning for image classification,” in Advances in Computational Intelligence Systems (A. Lotfi, H. Bouchachia, A. Gegov, C. Langensiepen, and M. McGinnity, eds.), (Cham), pp. 191–202, Springer International Publishing, 2019.

A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby, “An image is worth 16x16 words: Transformers for image recognition at scale,” 2021.

F. A. Breiki, M. Ridzuan, and R. Grandhe, “Self-supervised learning for fine-grained image classification,” 2021.

Z. Lv, L. Qiao, A. K. Singh, and Q. Wang, “Fine-Grained Visual Computing Based on Deep Learning,” ACM Trans. Multimedia Comput. Commun. Appl., vol. 17, 4 2021.

J. Luo, Y. Jiang, and J. Qiu, “Fine-Grained Object Recognition Based on Multi-Scale Destruction and Construction Learning,” in Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2021, (New York, NY, USA), pp. 1227–1232, Association for Computing Machinery, 2021.

B. Zhao, J. Feng, X. Wu, and S. Yan, “A survey on deep learning-based fine-grained object classification and semantic segmentation,” International Journal of Automation and Computing, vol. 14, pp. 119–135, Apr 2017.

N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” Journal of Machine Learning Research, vol. 15, no. 56, pp. 1929–1958, 2014.

X.-S. Wei, J. Wu, and Q. Cui, “Deep Learning for Fine-Grained Image Analysis: A Survey,” 2019.

Y. Huang, J. Chen, W. Ouyang, W. Wan, and Y. Xue, “Image Captioning With End-to-End Attribute Detection and Subsequent Attributes Prediction,” IEEE Transactions on Image Processing, vol. 29, pp. 4013–4026, 2020.

T. Soenen, W. Tavernier, M. Peuster, F. Vicens, G. Xilouris, S. Kolometsos, M.-A. Kourtis, and D. Colle, “Empowering Network Service Developers: Enhanced NFV DevOps and Programmable MANO,” IEEE Communications Magazine, vol. 57, no. 5, pp. 89–95, 2019.

A. Wentzel, P. Hanula, T. Luciani, B. Elgohari, H. Elhalawani, G. Canahuate, D. Vock, C. D. Fuller, and G. E. Marai, “Cohort-based T-SSIM Visual Computing for Radiation Therapy Prediction and Exploration,” IEEE Transactions on Visualization and Computer Graphics, vol. 26, no. 1, pp. 949–959, 2020.

X. Shu, J. Tang, G.-J. Qi, Z. Li, Y.-G. Jiang, and S. Yan, “Image Classification With Tailored Fine-Grained Dictionaries,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 28, no. 2, pp. 454–467, 2018.

Y. Tan, M. M. Rahman, Y. Yan, J. Xue, L. Shao, and K. Lu, “Fine-Grained Categorization From RGB-D Images,” IEEE Transactions on Multimedia, vol. 24, pp. 917–928, 2022.

Y. Hu, X. Jiang, X. Liu, X. Luo, Y. Hu, X. Cao, B. Zhang, and J. Zhang, “Hierarchical Self-Distilled Feature Learning for Fine-Grained Visual Categorization,” IEEE Transactions on Neural Networks and Learning Systems, pp. 1–14, 2021.

Z. Pan, X. Yu, M. Zhang, and Y. Gao, “Mask-Guided Feature Extraction and Augmentation for Ultra-Fine Grained Visual Categorization,” in 2021 Digital Image Computing: Techniques and Applications (DICTA), pp. 1–8, 2021.

Q. Wang, K. Zhang, J. Fan, S. Huang, and L. Zhang, “Multi-Order Feature Statistical Model for Fine-Grained Visual Categorization,” in 2020 25th International Conference on Pattern Recognition (ICPR), pp. 7379–7386, 2021.

K. Xu, R. Lai, L. Gu, and Y. Li, “Multiresolution Discriminative Mixup Network for Fine-Grained Visual Categorization,” IEEE Transactions on Neural Networks and Learning Systems, pp. 1–13, 2021.

J. Han, X. Yao, G. Cheng, X. Feng, and D. Xu, “P-CNN: Part-Based Convolutional Neural Networks for Fine Grained Visual Categorization,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 2, pp. 579–590, 2022.

M. Gwilliam, A. Teuscher, C. Anderson, and R. Farrell, “Fair Comparison: Quantifying Variance in Results for Fine-grained Visual Categorization,” in 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 3308–3317, 2021.

M. Zhu, S. Wan, P. Jin, and Q. Tian, “A Feature Fusion Method Based on Multi-Classification Losses for Fine Grained Visual Categorization,” in 2021 IEEE International Conference on Big Data (Big Data), pp. 6072–6074, 2021.

M. Li, L. He, C. Lei, and Y. Gong, “Fine-grained image classification model based on improved SqueezeNet,” in 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), vol. 5, pp. 393–399, 2021.

Y. Seo and K.-s. Shin, “Image classification of fine-grained fashion image based on style using pre-trained convolutional neural network,” in 2018 IEEE 3rd International Conference on Big Data Analysis (ICBDA), pp. 387–390, 2018.

C. Qiu, J. Cui, S. Zhang, C. Wang, Z. Gu, H. Zheng, and B. Zheng, “Transfer Learning for Small-Scale Fish Image Classification,” in 2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO), pp. 1–5, 2018.

R. Sipes and D. Li, “Using Convolutional Neural Networks for Automated Fine Grained Image Classification of Acute Lymphoblastic Leukemia,” in 2018 3rd International Conference on Computational Intelligence and Applications (ICCIA), pp. 157–161, 2018.

Y.-H. Chen and M.-C. Yeh, “Text-Enhanced Attribute-Based Attention for Generalized Zero-Shot Fine Grained Image Classification,” in Proceedings of the 2021 International Conference on Multimedia Retrieval, ICMR ’21, (New York, NY, USA), pp. 447–450, Association for Computing Machinery, 2021.

X. Yang, J. Hu, Z. Wang, F. Xu, and L. Zhu, “Self-Supervised Fine-Grained Image Classification via Progressive Global Disturbance,” in 2021 4th International Conference on Computer Science and Software Engineering (CSSE 2021), CSSE 2021, (New York, NY, USA), pp. 119–125, Association for Computing Machinery, 2021.

A. E. Korchi and Y. Ghanou, “2D geometric shapes dataset – for machine learning and pattern recognition,” Data in Brief, vol. 32, p. 106090, 2020.

P. Cichosz, Data mining algorithms: explained using R. New York: Wiley, 2015.

S. Ming, Y. Yuan, Z. Feng, and D. Errui, “Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition,” in Computer Vision – ECCV 2018 (F. Vittorio, M. Hebert, S. Cristian, and W. Yair, eds.), (Cham), pp. 834–850, Springer International Publishing, 2018.

Z. Ning, J. Donahue, G. Ross, and D. Trevor, “Part-Based R-CNNs for Fine-Grained Category Detection,” in Computer Vision – ECCV 2014 (F. David, T. Pajdla, S. Bernt, and T. Tinne, eds.), (Cham), pp. 834–849, Springer International Publishing, 2014.

Y. Ze, T. Luo, W. Dong, H. Zhiqiang, G. Jun, and W. Liwei, “Learning to Navigate for Fine-Grained Classification,” in Computer Vision – ECCV 2018 (F. Vittorio, M. Hebert, S. Cristian, and W. Yair, eds.), (Cham), pp. 438–454, Springer International Publishing, 2018.

F. Chollet, “Keras: the Python deep learning API.”

V. Nair and G. E. Hinton, “Rectified Linear Units Improve Restricted Boltzmann Machines,” in Proceedings of the 27th International Conference on International Conference on Machine Learning, ICML’10, (Madison, WI, USA), pp. 807–814, Omnipress, 2010.

C. Nwankpa, W. Ijomah, A. Gachagan, and S. Marshall, “Activation Functions: Comparison of trends in Practice and Research for Deep Learning,” 11 2018.

Sklearn, “Metrics precision, recall, fscore and support.”

C. Szegedy, S. Ioffe, V. Vanhoucke, and A. Alemi, “Inception-v4, inception-resnet and the impact of residual connections on learning,” 2016.

G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” 2018.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” 2015.



How to Cite

Díaz-Ramírez, J., Alvarez-Alvarez, F., & Badilla-Torrico, X. . (2022). Fine-grained geometric shapes: A deep classification task. IEEE Latin America Transactions, 100(XXX). Retrieved from