Russian Federation
Russian Federation
Russian Federation
Convolutional neural networks are a powerful tool for image processing and analysis. They allow you to automatically extract features from the input data and apply them to classification, object detection and other computer vision tasks. This article presents the convolutional neural networks architecture developed using the Keras library. The architecture of a convolutional neural network, which consists of several successive layers, is analyzed. The structure of the model has been built, which will be trained using the Adam optimizer and monitor the recall and precision metrics during the training process. The results of experiments are presented, which showed that the trained model successfully detects points in images, achieving high accuracy and completeness. The proposed model can be used in various areas where the detection of facial points in photographs is required.
neural network, computer vision, image analysis, Keras library, dots on images
1. Tynchenko S.V., Putilin V.O., Ovsyannikova A.K. Sravnenie algoritmov obnaruzheniya i lokalizacii lica na izobrazhenii // Molodoj uchenyj. Krasnoyarsk, 2018. S. 105–108.
2. Matrichnyj metod kak sposob opredeleniya antropometricheskih tochek lica / A.I. Sitnikov [i dr.] // Aktual'nye problemy deyatel'nosti podrazdelenij UIS: materialy Vseros. nauch.-prakt. konf. Voronezh, 2022. S. 193–194.
3. Mel'nikov N.A. Nekotorye osobennosti opredeleniya antropologicheskih harakteristik lica na osnove glubokogo mashinnogo obucheniya // Aktual'nye voprosy ekspluatacii sistem ohrany i zashchishchennyh telekommunikacionnyh sistem: materialy Vseros. nauch.-prakt. konf. Voronezh, 2022. S. 278–280.
4. Tolstyh A.A., Golubinskij A.N. Raspoznavanie ob"ektov na televizionnyh izobrazheniyah s ispol'zovaniem apparata svertochnyh nejronnyh setej // Vestnik Voronezhskogo instituta MVD Rossii: sb. nauch. trudov. Voronezh, 2017. № 1. C. 71–81.
5. Gafarov F.M., Galimyanov A.F. Iskusstvennye nejronnye seti i prilozheniya: ucheb. posobie. Kazan': Izd-vo Kazanskogo un-ta, 2018 121 s.
6. Tolstyh A.A., Golubinskij A.N. Vybor arhitektury iskusstvennoj nejronnoj seti na osnove sravneniya effektivnosti metodov raspoznavaniya izobrazhenij // Vestnik Voronezhskogo instituta MVD Rossii: sb. nauch. trudov. Voronezh, 2018. № 1. C. 27–37.
7. Butyrskij E.Yu., Matveev A.V. Matematicheskoe modelirovanie sistem i processov. SPb.: Inform. izd. ucheb.-nauch. centr «Strategiya budushchego», 2022. 733 s. DOI:https://doi.org/10.37468/book_011222. EDN CCRIRT.
8. Tolstyh A.A., Golubinskij A.N. Sravnenie effektivnosti metodov izmeneniya skorosti obucheniya iskusstvennyh nejronnyh setej v razlichnyh zadachah klassifikacii // Mezhdunarodnyj nauchno-issledovatel'skij zhurnal: sb. nauch. trudov. 2022. № 7–1 (121). C. 102–106.
9. Red'kin V.S., Sitnikov A.I. Ispol'zovanie metodov raspoznavaniya obrazov pri video fiksacii dlya povysheniya bezopasnosti ob"ektov // Aktual'nye problemy deyatel'nosti podrazdelenij UIS: materialy Vseros. nauch.-prakt. konf. Voronezh, 2021. S. 233–234.
10. Yaryshev S.N., Ryzhova V.A. Tekhnologii glubokogo obucheniya i nejronnyh setej v zadachah videoanaliza. SPb.: Un-t ITMO, 2022. 82 s.
11. Mel'nikov N.A., Sitnikov V.A., Nikitenko V.A. Stroenie svertochnoj nejronnoj seti dlya opredeleniya kontrol'nyh tochek lica cheloveka // Tekhnologii informacionnogo obshchestva: sb. trudov XVII Mezhdunar. otrasl. nauch.-tekhn. konf. M., 2023. S. 127–128.
