Object Classifier in MATLAB® with Deep Learning Neural Networks
DOI:
https://doi.org/10.29105/ingenierias24.90-16Keywords:
Artificial neural network, deep learning, AlexNet, GoogLeNet, VGG-16, image recognitionAbstract
In this work, in an introductory way, the implementation of three pre-trained neural networks with the deep learning paradigm in MATLAB® software is illustrated, which can recognize objects in images captured by a camera. Through experiments to recognize objects, it was determined which of these networks performed better, taking advantage of a standard database of images. These results are illustrated with examples of the use of the software and comparative data of the hits.
Downloads
References
Coronel Tobar, Hernán Fabricio. (2007). Reconocimiento de rostros utilizando redes neuronales. Tesis, Escuela Politécnica Nacional, Quito, Ecuador.
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115–118. DOI: https://doi.org/10.1038/nature21056
Yun Liu, Krishna Gadepalli, Mohammad Norouzi, George E. Dahl, Timo Kohlberger, Aleksey Boyko, Subhashini Venugopalan, Aleksei Timofeev, Philip Q. Nelson, Gregory S. Corrado, Jason D. Hipp, Lily Peng, Martin C. (2017). Detecting Cancer Metastases on Gigapixel Pathology Images. CoRR abs/1703.02442.
Ramírez González, D., Pulido Sarmiento, G., Gerardino Arévalo, B., Cruz Romero, J., Estupiñán Escalante, E., & Cancino Suárez, S. (2009). Adquisición y reconocimiento de imágenes por medio de técnicas de visión e inteligencia artificial. ITECKNE, 6(1), 5-13. DOI: https://doi.org/10.15332/iteckne.v6i1.290
García García, Pedro Pablo. (2013). Reconocimiento de imágenes utilizando redes neuronales artificiales. Tesis de Maestría, Universidad Complutense de Madrid, España.
Castro García, José Francisco. (2006). Fundamentos para la implementación de red neuronal perceptrón multicapa mediante software. Tesis, Universidad de San Carlos, Guatemala.
Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. “ImageNet Classification with Deep Convolutional Neural Networks.” Advances in neural information processing systems. 2012.
Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg and Li Fei-Fei. (2015). ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision, 115(3), 211-252. DOI: https://doi.org/10.1007/s11263-015-0816-y
Pretrained GoogLeNet convolutional neural network. http://la.mathworks.com/help/deeplearning/ref/googlenet.html
Zhou, B., Khosla, A., Lapedriza, À., Torralba, A., & Oliva, A. (2017). Places: An Image Database for Deep Scene Understanding. CoRR, abs/1610.02055. DOI: https://doi.org/10.1167/17.10.296
Pretrained VGG-16 convolutional neural network. http://la.mathworks.com/help/deeplearning/ref/vgg16.html
Siddharth, Das. (2017) CNN Architectures: LeNet, AlexNet, VGG, GoogLeNet, ResNet.
Pretrained AlexNet convolutional neural network. http://la.mathworks.com/help/deeplearning/ref/alexnet.html
