Enhancement of the Search System for Similar Objects of Iintellectual Property Using the Neural Network Approach

Student: Bogdanova Ekaterina

Faculty: HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)

Educational Programme: Applied Mathematics (Bachelor)

Year of Graduation: 2019

The purpose of the study is to improve the search system for similar objects of industrial designs. During the development, a database of images was collected, processed and analyzed. Models architecture neural networks were considered. During the implementation process, Densenet and VGG neural network architectures were applied. The transfer learning method was used. Python 3 and PyTorch were used as a language and auxiliary library for writing models. The development took place on the platform of Google Colaboratory. As a result, VGG19 model has an accuracy rate of 93%, and Densenet161 95%. For more detailed analysis, loss for each class were compared. The results of the work will help to further research in improving the system.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses