Patents Images Retrieval and Convolutional Neural Network Training Dataset Quality Improvement
Alla Kravets, Nikita Lebedev, Maxim Legenchenko
Available Online December 2017.
- https://doi.org/10.2991/itsmssm-17.2017.59How to use a DOI?
- patent image, neural network, formation dataset, training dataset quality, deep learning, patents images retrieval, convolutional neural network.
- The paper considers the problem of the analysis of patents' figures for formalization of subjective opinions of the patent office experts that reviews applications for inventions. Drawings omission may indicate an incomplete description of the invention and entail the rejection of patent applications and other problems. Since patent images, even if one considers images of the same type, class, etc., are unique, different from each other. Nowadays for image processing are applied neural networks with different architectures. Neural network, Convolutional neural network, Siamese neural network were considered in the research. 4 libraries (Theano, TensorFlow, Caffe, and Keras) were studied. The main contributions of the paper are the new classification of patents' imaged, training dataset formation and quality improvement approach, and the software implementation for CNN training.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Alla Kravets AU - Nikita Lebedev AU - Maxim Legenchenko PY - 2017/12 DA - 2017/12 TI - Patents Images Retrieval and Convolutional Neural Network Training Dataset Quality Improvement BT - IV International research conference "Information technologies in Science, Management, Social sphere and Medicine" (ITSMSSM 2017) PB - Atlantis Press SN - 2352-538X UR - https://doi.org/10.2991/itsmssm-17.2017.59 DO - https://doi.org/10.2991/itsmssm-17.2017.59 ID - Kravets2017/12 ER -