Keywords
How to Cite
Abstract
Annotatsiya. Tasvir tiniqligini yaxshilashda tasvir sifatini baxolash eng muxum
bosqichlardan biridir. Tasvir sifatini yaxshilashda uni baxolash muxum axamiyatga
ega bo’lib, tasvir holatiga qarab xalaqtlarni bartaraf qiluvchi algaritomlarning
modellarini aniqlashga yordam beradi. Bu esa o’z o’rnida tasvir aniqligi, barqarorligi
va xususiyatlarni ajratish qobiliyatiga ta'sir ko‘rsatadi. Ushbu Ishda tasvir sifatini
baholashning asosiy yondashuvlari – subyektiv va ob'ektiv usullar, shuningdek, to‘liq-
referens, kamaytirilgan-referens va referensiz algoritmlar ko‘rib chiqiladi. Tasvir
sifatini ob'ektiv baholashda keng qo‘llaniladigan o‘lchovlar, jumladan, Peak Signal-to-
Noise Ratio (PSNR), Mean Square Error (MSE), Pixel Error Rate (PEER) va boshqa
tasvir sifat metrikalari tahlil qilinadi[5]. Shuningdek, tasvir sifatini oshirish uchun
qo‘llaniladigan oldindan ishlov berish texnikalari – o‘lchamini o‘zgartirish,
normallashtirish, shovqinni kamaytirish, kontrastni oshirish, keskinlashtirish, rangni
tuzatish va tasvirni augmentatsiyalash ham ko‘rib chiqiladi. Ish natijalariga ko‘ra,
tasvir sifatini baholash algoritmlarini tanlash va ularni mos oldindan ishlov berish
usullari bilan birga qo‘llash tanib olish modellarining samaradorligini oshiradi.
Tadqiqot shuni ko‘rsatadiki, tasvir sifatini baholash algoritmlari va ularning ishlash
samaradorligi tanlangan vazifa, tasvirlar to‘plami va model arxitekturasiga bog‘liq
bo‘lib, eksperiment va baholash orqali optimallashtirilishi lozim.
References
FOYDALANILGAN ADABIYOTLAR RO‘YXATI:
1. Wang, Z., Bovik, A.C., Sheikh, H.R., & Simoncelli, E.P. (2004). Image quality
assessment: From error visibility to structural similarity. IEEE Transactions on
Image Processing, 13(4), 600–612.
2. Hore, A., & Ziou, D. (2010). Image quality metrics: PSNR vs. SSIM. 20th
International Conference on Pattern Recognition, 2366–2369.
3. Mittal, A., Moorthy, A.K., & Bovik, A.C. (2012). No-reference image quality
assessment in the spatial domain. IEEE Transactions on Image Processing, 21(12),
4695–4708.
4. Zhang, L., Zhang, L., & Mou, X. (2012). FSIM: A feature similarity index for image
quality assessment. IEEE Transactions on Image Processing, 20(8), 2378–2386.
5. Wang, S., & Simoncelli, E.P. (2003). Maximum differentiation (MAD)
competition: A methodology for comparing computational models of perceptual
quantities. Journal of Vision, 3(8), 533–551.
6. Sheikh, H.R., & Bovik, A.C. (2006). Image information and visual quality. IEEE
Transactions on Image Processing, 15(2), 430–444.
7. Li, X., Wang, Z., & Wang, S. (2011). Reduced-reference image quality assessment
using natural scene statistics. IEEE Transactions on Image Processing, 20(12),
3431–3444.
8. Lin, W., & Kuo, C.-C. J. (2011). Perceptual visual quality metrics: A survey.
Journal of Visual Communication and Image Representation, 22(4), 297–312.
9. Zhang, R., Isola, P., Efros, A.A., Shechtman, E., & Wang, O. (2018). The
unreasonable effectiveness of deep features as a perceptual metric. CVPR 2018,
586–595.
10. Mittal, A., Soundararajan, R., & Bovik, A.C. (2013). Making a “completely blind”
image quality analyzer. IEEE Signal Processing Letters, 20(3), 209–212.
This work is licensed under a Creative Commons Attribution 4.0 International License.