30

Mazkur maqolada ko‘zi ojiz va zaif ko‘ruvchi insonlarga qulaylik yaratish uchun sun’iy intellekt texnologiyalaridan foydalanib, yordamchi tizim ishlab chiqish masalasi o‘rganilgan. Ushbu tizim obyektlarni tanib olish, to‘siqlargacha bo‘lgan masofani o‘lchash va matnlarni aniqlash kabi vazifalarni bajaradi. Obyektlarni tanib olish va to‘siqlar masofasini o‘lchashda mashinali o‘qitish, tasvirdagi matnlarni aniqlashda optik belgilarni aniqlash hamda olingan natijalarni ovozli ifodalashda matnlarni tahlil qilish algoritmlaridan foydalanildi. Ko‘zi ojiz va zaif ko‘ruvchi insonlarning atrof-muhitni anglashi, insonlar bilan muloqot qilishi va mustaqil harakatlanishiga ko‘maklashish hamda ijtimoiy faoliyatini yaxshilash asosiy maqsad hisoblanadi. Ko‘zi ojiz insonlar uchun foydalanishga qulay, arzon va o‘zbek tilida natijalarni bayon qiluvchi dasturiy vositalar ishlab chiqish dolzarb muammolardan biridir. Ishlab chiqilgan algoritmlar yordamida obyektlar va matnlarni aniqlash bo‘yicha o‘tkazilgan tadqiqot natijalari mos ravishda 92,16 va 99,87 %ni tashkil qildi. To‘siqlar masofasini o‘lchashning mobil ilovaga nisbatan maksimal og‘ish darajasi 6,32 %ni tashkil etdi. Bunday natijalar shuni ko‘rsatadiki, taklif etilayotgan yordamchi tizim tijorat qurilmalari kabi ishonchli ko‘rsatkichlar taqdim etadi. Bundan tashqari, ko‘rish qobiliyati zaif insonlarning xavfsizligiga foyda keltiradigan kundalik hayotning asosiy talablariga javob beradi.

  • Internet ҳавола
  • DOI
  • UzSCI тизимида яратилган сана 16-10-2024
  • Ўқишлар сони 30
  • Нашр санаси 22-04-2024
  • Мақола тилиO'zbek
  • Саҳифалар сони25-35
Ўзбек

Mazkur maqolada ko‘zi ojiz va zaif ko‘ruvchi insonlarga qulaylik yaratish uchun sun’iy intellekt texnologiyalaridan foydalanib, yordamchi tizim ishlab chiqish masalasi o‘rganilgan. Ushbu tizim obyektlarni tanib olish, to‘siqlargacha bo‘lgan masofani o‘lchash va matnlarni aniqlash kabi vazifalarni bajaradi. Obyektlarni tanib olish va to‘siqlar masofasini o‘lchashda mashinali o‘qitish, tasvirdagi matnlarni aniqlashda optik belgilarni aniqlash hamda olingan natijalarni ovozli ifodalashda matnlarni tahlil qilish algoritmlaridan foydalanildi. Ko‘zi ojiz va zaif ko‘ruvchi insonlarning atrof-muhitni anglashi, insonlar bilan muloqot qilishi va mustaqil harakatlanishiga ko‘maklashish hamda ijtimoiy faoliyatini yaxshilash asosiy maqsad hisoblanadi. Ko‘zi ojiz insonlar uchun foydalanishga qulay, arzon va o‘zbek tilida natijalarni bayon qiluvchi dasturiy vositalar ishlab chiqish dolzarb muammolardan biridir. Ishlab chiqilgan algoritmlar yordamida obyektlar va matnlarni aniqlash bo‘yicha o‘tkazilgan tadqiqot natijalari mos ravishda 92,16 va 99,87 %ni tashkil qildi. To‘siqlar masofasini o‘lchashning mobil ilovaga nisbatan maksimal og‘ish darajasi 6,32 %ni tashkil etdi. Bunday natijalar shuni ko‘rsatadiki, taklif etilayotgan yordamchi tizim tijorat qurilmalari kabi ishonchli ko‘rsatkichlar taqdim etadi. Bundan tashqari, ko‘rish qobiliyati zaif insonlarning xavfsizligiga foyda keltiradigan kundalik hayotning asosiy talablariga javob beradi.

Русский

В данной статье речь идёт о разработке системы-помощника с использованием технологий искусственного интеллекта для обеспечения комфорта незрячим и слабовидящим людям. Эта система выполняет такие задачи, как распознавание объектов и текста, измерение расстояния до препятствий. Алгоритмы машинного обучения использовались для распознавания объектов и измерения расстояния до препятствий, алгоритмы оптического распознавания знаков – для распознавания текста на изображении и алгоритмы анализа текста – для голосового представления выявленных результатов. Основная цель – помочь слепым и слабовидящим людям понять окружающую среду, общаться с людьми и самостоятельно передвигаться, а также улучшить свою социальную активность. Одной из актуальных проблем в нашей стране является разработка программных средств на узбекском языке для незрячих людей, простых в использовании, недорогих и эффективных. Результаты исследования по идентификации объектов и текстов с помощью разработанных алгоритмов составили 92,16 и 99,87% соответственно. Максимальное отклонение измерения расстояния до препятствий по сравнению с мобильным приложением составило 6,32%. Такие результаты показывают, что предлагаемая вспомогательная система обеспечивает надёжную работу, аналогичную коммерческим устройствам. Она отвечает основным требованиям повседневной жизни, которые способствуют безопасности и благополучию людей с нарушениями зрения.

English

The article reveals development of a support system based on the artificial intelligence (AI) technologies to help the blind and visually impaired people. This system is effective in implementing of the following tasks: object recognition, measurement of distances towards obstacles, and text recognition. Machine learning algorithms were used for object recognition and obstacle distance measurement, optical character recognition algorithms for text recognition in the image, and text analysis algorithms for voice representation of the identified results. The main goal is to help blind and partially sighted people to realize their environment, communicate with people and move independently, as well as improve their social activities. One of the urgent problems in our republic is the development of software tools that will be easy in use, affordable and effective in Uzbek for the blind. Findings from the research into identifying objects and texts by means of developed algorithms were 92.16% and 99.87%, respectively. Maximum deviation of the obstacle distance measurement compared to the one measured by mobile application was 6.32%. Such findings show that the proposed support system ensures reliable performance similar to commercial devices. It meets basic requirements of everyday life that benefit safety and well-being of visually impaired people.

Муаллифнинг исми Лавозими Ташкилот номи
1 Umarov M.A. texnika fanlari bo‘yicha falsafa doktori (PhD), dotsent “University of Management and Future Technologies” MChJ, “Kommunikatsiya va raqamli texnologiyalar” kafedrasi
Ҳавола номи
1 Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. (2008). Speeded-up robust features (SURF). Comput. Vis. Image Underst., 110, 346–359.
2 Chang, W., Chen, L., Hsu, C., Chen, J., Yang, T., & Lin, C. (2020). MedGlasses: A wearable smart-glasses-based drug pill recognition system using deep learning for visually impaired chronic patients. IEEE Access, 8, 17013– 17024.
3 Dunai, L. D., Lengua, I. L., Tortajada, I., & Simon, F. B. (2014, May 22–24). Obstacle detectors for visually impaired people. Proceedings of the 2014 International Conference on Optimization of Electrical and Electronic Equipment (OPTIM) (pp. 809–816). Bran, Romania.
4 El-Rashidy, N., El-Sappagh, S., Islam, S. M. R., El-Bakry, H. M., & Abdelrazek, S. (2021). Mobile health in remote patient monitoring for chronic diseases: Principles, trends, and challenges. Diagnostics, 11, 607.
5 Glenk, L.M., Prˇibylová, L., Stetina, B. U., Demirel, S., & Weissenbacher, K. (2019). Perceptions on health benefits of guide dog ownership in an Austrian population of blind people with and without a guide dog. Animals, 9, 428.
6 Husin, M. H., & Lim, Y. K. (2020). InWalker: Smart white cane for the blind. Disabil. Rehabil. Assist. Technol., 15, 701–707.
7 Jivrajani, K., Patel, S. K., Parmar, C., Surve, J., Ahmed, K., Bui, F. M., & Al-Zahrani, F. A. (2023). AIoT-based smart stick for visually impaired person. IEEE Trans. Instrum. Meas., 72, 2501311.
8 Khamdamov, U., Umarov, M., Elov, J., Khalilov, S., & Narzullayev, I. (2022). Uzbek traffic sign dataset for traffic sign detection and recognition systems. Proceedings of the 2022 International Conference on Information Science and Communications Technologies (ICISCT) (pp. 1–5). Tashkent, Uzbekistan. doi:10.1109/ ICISCT55600.2022.10146832
9 Kirill, S., Anastasiya, Ch., Dmytro, D., & Serhii, M. (2021, April 22–23). Effectiveness of modern text recognition solutions and tools for common data sources. Proceedings of the 5th COLINS-2021. Kharkiv, Ukraine.
10 Kuriakose, B., Shrestha, R., Sandnes, F. E. (2020). Tools and technologies for blind and visually impaired navigation support: A review. IETE Tech. Rev., 39, 3.
11 LESH - Laser Eye Surgery Hub. (2023). Visual Impairment & Blindness Global Data & Statistics. https:// www.lasereyesurgeryhub.co.uk/data/visual-impairment-blindness-data-statistics
12 Li, B., Muñoz, J.P., Rong, X., Chen, Q., Xiao, J., Tian, Y., Arditi, A., & Yousuf, M. (2019). Vision-based mobile indoor assistive navigation aid for blind people. IEEE Trans. Mobile Comput., 18, 702–714.
13 Liu, Y., Sun, P., Wergeles, N., & Shang, Y. (2021). A survey and performance evaluation of deep learning methods for small object detection. Expert Syst. Appl., 172, 114602.
14 Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis., 60, 91– 110.
15 Meshram, V. V., Patil, K., Meshram, V. A., & Shu, F. C. (2019). An astute assistive device for mobility and object recognition for visually impaired people. IEEE Trans. Hum. Mach. Syst., 49, 449–460.
16 Monteiro, J., Aires, J. P., Granada, R., Barros, R. C., & Meneguzzi, F. (2017, May 14–19). Virtual guide dog: An application to support visually-impaired people through deep convolutional neural networks. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN) (pp. 2267–2274). Anchorage, AK, USA.
17 Mukhiddinov, M., & Cho, J. (2021). Smart glass system using deep learning for the blind and visually impaired. Electronics, 10, 2756.
18 Mustapha, B., Zayegh, A., & Begg, R. K. (2013, December 3–5). Ultrasonic and infrared sensors performance in a wireless obstacle detection system. Proceedings of the 2013 1st International Conference on Artificial Intelligence, Modelling and Simulation (AIMS) (pp. 487–492). Kota Kinabalu, Malaysia.
19 Pei, S., & Zhu, M. (2020, Oct 31). Real-time text detection and recognition. Computer Vision and Pattern Recognition (cs.CV). doi:10.48550/arXiv.2011.00380
20 Plikynas, D., Žvironas, A., Gudauskis, M., Budrionis, A., Daniušis, P., & Sliesoraityte, I. (2020). Research advances of indoor navigation for blind people: A brief review of technological instrumentation. IEEE Instrum. Meas. Mag., 23, 22.
21 Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016, June). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 779–788). Las Vegas, NV, USA.
22 Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013). Overfeat: Integrated recognition, localization and detection using convolutional networks. Computer Vision and Pattern Recognition (cs.CV). doi:10.48550/arXiv.1312.6229
23 Society of the Blind of Uzbekistan. (2024). https://uzkoj.uz/about-us/
24 Umarov, M., Elov, J., Khalilov, S., Narzullayev, I., & Karimov, M. (2022). An algorithm for parallel processing of traffic signs video on a graphics processor. Proceedings of the 2022 International Conference on Information Science and Communications Technologies (ICISCT) (pp. 1–5). Tashkent, Uzbekistan. doi:10.1109/ ICISCT55600.2022.10146809
25 Villanueva, J., & Farcy, R. (2011). Optical device indicating a safe free path to blind people. IEEE Trans. Instrum. Meas., 61, 170–177.
26 Wu, M., Yue, H., Wang, J., Huang, Y., Liu, M., Jiang, Y., Ke, C., & Zeng, C. (2020). Object detection based on RGC mask R-CNN. IET Image Process., 14, 1502–1508.
27 Xiao, Y., Tian, Z., Yu, J., Zhang, Y., Liu, S., Du, S., & Lan, X. (2020). A review of object detection based on deep learning. Multimed. Tools Appl., 79, 23729–23791.
Кутилмоқда