Abstract
LEGO bricks are highly popular due to the ability to build almost any type of creation. This is possible thanks to availability of multiple shapes and colors of the bricks. For the smooth build process the bricks need to properly sorted and arranged. In our work we aim at creating an automated LEGO bricks sorter. With over 3700 different LEGO parts bricks classification has to be done with deep neural networks. The question arises which model of the available should we use? In this paper we try to answer this question. The paper presents a comparison of 28 models used for image classification trained to classify objects to high number of classes with potentially high level of similarity. For that purpose a dataset consisting of 447 classes was prepared. The paper presents brief description of analyzed models, the training and comparison process and discusses the results obtained. Finally the paper proposes an answer what network architecture should be used for the problem of LEGO bricks classification and other similar problems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adam: LEGO sorting chart (2019). https://go.gliffy.com/go/publish/12232322. Accessed 24 Mar 2022
Aplhin, T.: The LEGO storage guide (2020). https://brickarchitect.com/guide/. Accessed 34 Mar 2022
Boiński, T.: Images of LEGO bricks (2021). https://doi.org/10.34808/xz76-ez11. Accessed 24 Mar 2022
Boiński, T., Zaraziński, S., Śledź, B.: LEGO bricks for training classification network (2021). https://doi.org/10.34808/3qfs-rt94. Accessed 24 Mar 2022
Boiński, T., Zawora, K., Zaraziński, S., Śledź, B., Łobacz, B.: LDRAW based renders of LEGO bricks moving on a conveyor belt (2020). https://doi.org/10.34808/jykr-8d71. Accessed 24 Mar 2022
Boiński, T.M.: Hierarchical 2-step neural-based LEGO bricks detection and labeling. In: Proceedings of 37th Business Information Management Association Conference, pp. 1344–1350 (2021)
Chollet, F.: Xception: Deep learning with depthwise separable convolutions (2017)
Dua, D., Graff, C.: UCI machine learning repository (2017). http://archive.ics.uci.edu/ml. Accessed 22 Nov 2021
Foundation, T.B.: Blender (2002). https://www.blender.org/. Accessed 22 Nov 2021
Garcia, P.: LEGO Sorter using TensorFlow on Raspberry Pi (2018). https://medium.com/@pacogarcia3/tensorflow-on-raspbery-pi-lego-sorter-ab60019dcf32. Accessed 22 Nov 2021
He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks (2016)
Hochreiter, S.: The vanishing gradient problem during learning recurrent neural nets and problem solutions. Internat. J. Uncertain. Fuzziness Knowl. Based Syst. 6(02), 107–116 (1998)
Howard, A., et al.: Searching for mobilenetv3 (2019)
Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications (2017)
Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely Connected Convolutional Networks (2018)
Jessiman, J.: LDraw. http://www.ldraw.org (1995). Accessed 22 Nov 2021
Jung, A.: imgaug source code. https://github.com/aleju/imgaug. Accessed 22 Nov 2021
Krasin, I., et al.: Openimages: a public dataset for large-scale multi-label and multi-class image classification. Dataset available from https://storage.googleapis.com/openimages/web/index.html (2017)
Krizhevsky, A., Nair, V., Hinton, G.: Cifar-10 and cifar-100 datasets. https://www.cs.toronto.edu/~kriz/cifar.html. Accessed 24 Mar 2022
Kuznetsova, A., et al.: The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale. IJCV (2020)
Li, M., et al.: The deep learning compiler: a comprehensive survey. IEEE Trans. Parallel Distrib. Syst. 32(3), 708–727 (2021). https://doi.org/10.1109/tpds.2020.3030548
Lin, T., et al.: Microsoft COCO: common objects in context. CoRR abs/1405.0312 (2014). http://arxiv.org/abs/1405.0312
Maren, T.: 60 fun LEGO facts every LEGO fan needs to know (2018). https://mamainthenow.com/fun-lego-facts/
Micikevicius, P., et al.: Mixed precision training (2018)
Nelson, T.: ImportLDRaw. https://github.com/TobyLobster/ImportLDraw. Accessed 16 June 2021
Papert, S.A.: The summer vision project (1966). https://dspace.mit.edu/handle/1721.1/6125. Accessed 22 Nov 2021
Le, Q., Zoph, B., Research Scientists, G.B.t.: Using machine learning to explore neural network architecture (2017). https://ai.googleblog.com/2017/05/using-machine-learning-to-explore.html. Accessed 22 Nov 2021
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: Inverted residuals and linear bottlenecks (2019)
Shukla, N., Fricklas, K.: Machine learning with TensorFlow. Manning Shelter Island, Ny (2018)
Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition (2015)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (2016)
Szegedy, C., et al.: Going Deeper with Convolutions (2014)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the Inception Architecture for Computer Vision (2015)
Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., Le, Q.V.: Mnasnet: platform-aware neural architecture search for mobile. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2820–2828 (2019)
Tan, M., Le, Q.V.: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (2020)
West, D.: LEGO sorting machine (2019). https://twitter.com/JustASquid/sta-tus/1201959889943154688. Accessed 08 Feb 2021
Zagoruyko, S., Komodakis, N.: Wide residual networks (2017)
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning (2017)
Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning Transferable Architectures for Scalable Image Recognition (2018)
Acknowledgment
The authors would like to thank Bartosz Śledź and Sławomir Zaraziński for help with part of the implementation and dataset creation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Boiński, T., Zawora, K., Szymański, J. (2022). How to Sort Them? A Network for LEGO Bricks Classification. In: Groen, D., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2022. ICCS 2022. Lecture Notes in Computer Science, vol 13352. Springer, Cham. https://doi.org/10.1007/978-3-031-08757-8_52
Download citation
DOI: https://doi.org/10.1007/978-3-031-08757-8_52
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08756-1
Online ISBN: 978-3-031-08757-8
eBook Packages: Computer ScienceComputer Science (R0)