1. ACPS
  2. Всі випуски
  3. Випуск 6, Номер 2, 2021
  4. Analysis of Algorithms for Searching Objects in Images Using Convolutional Neural Network

Analysis of Algorithms for Searching Objects in Images Using Convolutional Neural Network

ACPS.
2021;
Випуск 6, Номер 2
: cc. 128 - 133
https://doi.org/10.23939/acps2021.02.128
Автори:
  1. Ihor Koval
1
Lviv Polytechnic National University, Educatinoal and Rasearch Institute of Law, Psychology and Innovative Education

The problem of finding objects in images using modern computer vision algorithms has been considered. The description of the main types of algorithms and methods for finding objects based on the use of convolutional neural networks has been given. A comparative analysis and modeling of neural network algorithms to solve the problem of finding objects in images has been conducted. The results of testing neural network models with different architectures on data sets VOC2012 and COCO have been presented. The results of the study of the accuracy of recognition depending on different hyperparameters of learning have been analyzed. The change in the value of the time of determining the location of the object depending on the different architectures of the neural network has been investigated.

виявлення об'єктів на відеозображенні
нейронні мережі
глибинне навчання
R-CNN
Fast R-CNN
Faster R-CNN
  1. Butenko, V. V. (2015) ‘Finding objects in the image using the adaptive gain algorithm’, Young scientist, 4, pp. 52–56. Available at: https://moluch.ru/archive/84/15604/ (Accessed: 10 October 2021).
  2. Dalal, N. and Triggs, B. (2005) ‘Histograms of oriented gradients for human detection’, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA, 1, pp. 886–893. doi: 10.1109/CVPR.2005.177.
  3. Artemov, A. A., Kavalerov, M. V. and Kuznetsov, G. S. (2011) ‘The problem of finding objects in images using computer vision based  on  color  information’, Bulletin  of PNRPU. Electrical engineering, information technology, control systems, 5, pp. 70-79. Available at: https://cyberleninka.ru/article/n/problema-poiska-obektov-na-izobrazheni... (Accessed:           10 October 2021).
  4. Akimov, A. V. and Sirota, A. A. (2016) ‘Models and algorithms for artificial data multiplication for training face recognition algorithms using  the  Viola-Jones  method’, Computer    Optics,    6,    pp.    899–906.    Available    at: https://readera.org/modeli-i-algoritmy-iskusstvennogo- razmnozhenija-dannyh-dlja-obuchenija-algoritmov- 14059619 (Accessed: 10 October 2021).
  5. Viola, P. and Jones, M. (2004) ‘Robust real time face detection’, International Journal of Computer Vision, 57(2), pp. 137–154. doi: 10.1023/B:VISI.0000013087.49260.fb.
  6. Towards data science (2018) R-CNN, Fast R-CNN, Faster R- CNN, YOLO – Object Detection Algorithms. Available at: https://towardsdatascience.com/r-cnn-fast-r-cnn-faster-r-cnn- yolo-object-detection-algorithms-36d53571365e (Accessed: 10 October 2021).
  7. Kushnir, D. and Paramud, Y. (2019) ‘Methods for real-time object searching and recognizing in video images on ios mobile platform’, Computer systems and network, 1(1), pp. 24-34. doi: 10.23939/csn2019.01.024.
  8. Michelucci, U. (2019) Advanced Applied Deep Learning: Convolutional Neural Networks and Object Detection, 1st edition, TOELT LLC, Dübendorf, Switzerland, September 29 2019, 303 p.
  9. Girshick, R., Darrell, J. and Malik, T. (2015) ‘Region-Based Convolutional Networks for Accurate Object Detection and Segmentation’, IEEE Transactions on Pattern Analysis and Machine Intelligence, 38, pp. 142-158. doi: 10.1109/TPAMI.2015.2437384.
  10. Girshick, R. (2015) ‘Fast R-CNN’, International Conference on Computer Vision (ICC), pp. 1440-1448. doi: 10.1109/ICCV.2015.169.
  11. Girshick, R., Shaoqing, R. and Kaiming, H. (2015) ‘Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks’, Neural Information Processing Systems (NIPS),    39(6),        pp.           1137-1149. doi: 10.1109/TPAMI.2016.2577031.
  12. Wang, Y., Wang, C., Zhan, H., Yingbo, G. and Wei, S. (2019) ‘Automatic Ship Detection Based on RetinaNet Using Multi-Resolution’, Remote Sensing, 11(5), 531 p. doi: 10.3390/rs11050531.
  13. Pascal   2   (2012)   The   PASCAL   Visual   Object   Classes Challenge  2012         (VOC2012).               Available   at: http://host.robots.ox.ac.uk/pascal/VOC/voc2012/index.html (Accessed: 10 October 2021).
  14. Microsoft (2021) COCO: Common Objects in Context. Available at: http://cocodataset.org/#home (Accessed: 10 October 2021).
  15. Zitnick, C. and Dollár, P. (2014) ‘Edge boxes:  Locating object proposals from edges’, Computer Vision, 5, pp. 391– 405. doi: 10.1007/978-3-319-10602-1_26.
  16. Sande, J., Gevers, K. and Smeulders, T. (2013) ‘Selective Search for Object Recognition’, International Journal of Computer Vision, 104, pp. 154-171. doi: 10.1007/s11263- 013-0620-5.
  17. Chopra, R., England, A. and Noordeen Alaudeen, M. (2019) Data Science with Python: Combine Python with machine learning principles to discover hidden patterns in raw data, Packt Publishing Ltd, July 2019, 426 p.