2023, Vol. 8, No. 3. - go to content...

Permanent address of this page - https://kostumologiya.ru/en/29tlkl323.html

Метаданные этой статьи так же доступны на русском языке

Full article in PDF format (file size: 690.5 KB)

For citation:

Smirnov E.E., Kostyleva V.V., Murtazina A.R., Razin I.B., Sergeev V.A. Determining the position of the feet in the image using a convolutional neural network. Journal of Clothing Science. 2023; 8(3). Available at: https://kostumologiya.ru/PDF/29TLKL323.pdf (in Russian).

Determining the position of the feet in the image using a convolutional neural network

Smirnov Evgeniy Evgenʹevich
Russian State University named A.N. Kosygin (Technologies. Design. Art), Moscow, Russia
E-mail: evg7162@mail.ru
RSCI: https://elibrary.ru/author_profile.asp?id=1097456

Kostyleva Valentina Vladimirovna
Russian State University named A.N. Kosygin (Technologies. Design. Art), Moscow, Russia
E-mail: kostyleva-vv@rguk.ru
RSCI: https://elibrary.ru/author_profile.asp?id=353612

Murtazina Alʹfiya Rustyamovna
Russian State University named A.N. Kosygin (Technologies. Design. Art), Moscow, Russia
E-mail: aly1029@yandex.ru
RSCI: https://elibrary.ru/author_profile.asp?id=906389

Razin Igor Borisovich
Russian State University named A.N. Kosygin (Technologies. Design. Art), Moscow, Russia
E-mail: razin-ib@rguk.ru
RSCI: https://elibrary.ru/author_profile.asp?id=850439

Sergeev Viktor Alekseevich
Russian State University named A.N. Kosygin (Technologies. Design. Art), Moscow, Russia
E-mail: sevastopof@yandex.ru

Abstract. As a result of the manufacture of individual orthopedic shoes and its elements, a high percentage of work increases rapidly, which increases education. In the absence of a corrective effect, the pathology progresses and the therapeutic function is performed according to the previously taken standards of orthopedic supplies. To customize steles in orthopedics, podometers are used — devices that take anthropometric data of the feet and visualize them. Based on an assessment of the degree of severity of the first degree of severity of insole customization. This process is time consuming. With the help of neural networks, it can be automated. Within the framework of this consideration, articles on the detection of objects in images with the help of neural networks. In such a situation, convolutions of neural networks with a large number of generalized fragments of images on various objects are most often used. Goal of research was to create a principle for localizing objects in an image by using a neural network to automate the process of individual manufacturing of orthopedic insoles. Applying such an estimate, we treat the image area separately for the right and left feet, and estimates of the quality of the prediction are given. Such solutions are considered in the framework of the doctoral dissertation of Smirnov E.E. and use in the educational process the departments «Artistic Modeling, Design and Technology of Leather Products», «Information Technology» RSU A.N. Kosygin (Technology. Design. Art) in video tutorials.

Keywords: neural network; machine learning; data processing; deep learning; shoe customization; automation; orthopedic shoes

Download article in PDF format