YUZ TASVIRLARIGA DASTLABKI ISHLOV BERISHDA NEYRON TARMOQ ALGORITMLARINI QO'LLASH SAMARADORLIGI
- 1. "Axborot texnologiyalari kafedrsi assistenti" Muhammad al-Xorazmiy nomidagi Toshkent axborot texnologiyalari universiteti Farg'ona filiali Farg'ona, O'zbekiston
Description
Yuz tasvirlariga dastlabki ishlov berish algoritmlari biometrik tizimlar, yuzni aniqlash va ifoda tahlilida muhim ahamiyat kasb etadi. Ushbu maqola yuz tasvirlarga dastlabki ishlov berish model o'qitishning eng muhim bosqichlaridan biri ekanligi hamda yuz tasvirlariga dastlabki ishlov berish neyron tarmoqni muvaffaqiyatli o'qitish va yuqori aniqlikni ta'minlash uchun muhim. Dastlabki ishlovning sifati modelning nafaqat ma'lumotlarni qayta ishlash tezligiga, balki murakkab sharoitlarda aniqlik bilan ishlashiga ham bevosita ta'sir qiladi.To'g'ri ishlov berilgan ma'lumotlar neyron tarmoqni samarali o'qitishni va yuqori aniqlikdagi natijalarga erishishni ta'minlaydi.Zamonaviy usullar tahlil qilinadi. Ushbu algoritmlar ma'lumot sifatini oshirish va keyingi ishlov berish jarayonlarini soddalashtirish imkonini beradi. Tadqiqot yuzni qayta ishlashning ilmiy asoslarini yoritib, amaliy tatbiq uchun qo'llanma sifatida xizmat qiladi
Files
final_79_710-429-436-Mohizoda.pdf
Files
(1.2 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:7d50d3ab10edfb0e480b31274e00bb79
|
1.2 MB | Preview Download |
Additional details
References
- Ren, S., He, K., Girshick, R., et al. (2015) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Advances in Neural Information ProcessingSystems, 28, 91-99. https://www.scirp.org/reference/referencespapers?referenceid=3143500
- Davis Cope1, Barbara Blakeslee2, and Mark E. Analysis of multidimensional difference-of-Gaussians filters in terms of directly observable parameters Published in final edited form as: J Opt Soc Am A Opt Image Sci Vis. 2013 May 1
- 30(5): 1002–1012 https://pmc.ncbi.nlm.nih.gov/articles/PMC3789628/
- Xiancheng Zhang1, 2, Shigeho Noda2, Ryutaro Himeno2 va Hao Liu Cardiovascular disease-induced thermal responses during passive heat stress: an integrated computational study INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN BIOMEDICAL ENGINEERING Int. J. Numer. Meth. Biomed. Engng. (2016)
- e02768 Published online in Wiley Online Library (wileyonlinelibrary.com). DOI: 10.1002/cnm.2768 https://www.researchgate.net/publication/302956391_Zhang_et_al-2016-International_Journal_for_Numerical_Methods_in_Biomedical_Engineering-2
- Moving Medical Image Analysis to GPU Embedded Systems: Application to Brain Tumor Segmentation July 202034(2):1-14 DOI:10.1080/08839514.2020.1787678
- https://www.researchgate.net/publication/342825010_Moving_Medical_Image_Analysis_to_GPU_Embedded_Systems_Application_to_Brain_Tumor_Segmentation
- F. Schroff, D. Kalenichenko and J. Philbin, "FaceNet: A unified embedding for face recognition and clustering, " 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 815-823, doi: 10.1109/CVPR.2015.7298682
- Cortes, C., Vapnik, V. Support-vector networks. Mach Learn 20, 273–297 (1995). https://doi.org/10.1007/BF00994018
- Y.Tang, Deep Learning using Linear Support Vector Machines, arXiv: Learning, 2013, 1-6 pp., url: https://doi.org/10.48550/arXiv.1306.0239
- Abdukadirova G.X., Orifjonov B.M., Mukaramov T.T. Binoga kirishni boshqarish tizimlarida yuz niqoblarini aniqlashga bo'lgan yondashuv // Ҳисоблаш ва амалий математика муаммолари, Тошкент 2022, Махсус сон №2/1(40). 5-12 б.