Object Detection in E-Commerce Using YOLO in Real Time

  • Frans Mikael Sinaga Faculty of Informatics, Department of Informatics Engineering, Universitas Mikroskil, Medan, Sumatera Utara, Indonesia
  • Gunawan Faculty of Informatics, Department of Informatics Engineering, Universitas Mikroskil, Medan, Sumatera Utara, Indonesia
  • Sunaryo Winardi Faculty of Informatics, Department of Informatics Engineering, Universitas Mikroskil, Medan, Sumatera Utara, Indonesia
  • Heru Kurniawan Faculty of Informatics, Department of Informatics Engineering, Universitas Mikroskil, Medan, Sumatera Utara, Indonesia
  • Wulan Sri Lestari Faculty of Informatics, Department of Informatics Engineering, Universitas Mikroskil, Medan, Sumatera Utara, Indonesia
  • Karina Mannita Tarigan Faculty of Informatics, Department of Informatics Engineering, Universitas Mikroskil, Medan, Sumatera Utara, Indonesia
Keywords: CTEBIR, Detection, E-commerce, Real-time, YOLOv4

Abstract

Presently, e-commerce platforms incorporate image search functionalities. Nevertheless, these systems possess constraints; input images necessitate static and manual cropping since the system does not automatically generate bounding boxes. Addressing this concern requires the implementation of an object detection algorithm to ascertain the quantity, location, and type of desired objects within real-time bounding boxes before users finalize their selection. This capability empowers users to readily discern their desired items, thereby augmenting the precision and efficiency of visual searches. Despite the availability of swifter object detection algorithms such as R-CNN and Mask R-CNN, which prioritize accuracy over speed, rendering them less suited for real-time detection, we opted to employ the YOLOv4 algorithm as an alternative, renowned for its efficacy in real-time object detection. Furthermore, we adopted the Color, Texture, and Edge-Based Image Retrieval (CTEBIR) technique for image matching. The results of our experimentation demonstrate that the utilization of the YOLOv4 algorithm can enhance the accuracy and speed of visual searches by streamlining the search process based on the identified classes. Additionally, our precision assessment yielded a score of 95%, with individual scores for camera objects reaching 90%, keyboards achieving 85%, and laptops attaining 71%. These findings corroborate the dependability of the CTEBIR algorithm in image matching and contribute to a deeper comprehension of the system's efficacy in accurately detecting and distinguishing objects.

Downloads

Download data is not yet available.

References

S. Amin and K. Kansana, “A Review Paper on E-Commerce,” 2016. [Online]. Available: https://www.researchgate.net/publication/304703920

G. Anand, S. Wang, and K. Ni, “Large-scale visual search and similarity for e-commerce,” in Applications of Machine Learning 2021, M. E. Zelinski, T. M. Taha, and J. Howe, Eds., SPIE, Aug. 2021, p. 31. doi: 10.1117/12.2594924.

M. P. Eckstein, “Visual search: A retrospective,” J Vis, vol. 11, no. 5, pp. 14–14, Dec. 2011, doi: 10.1167/11.5.14.

S. Vijayanarasimhan and K. Grauman, “Efficient region search for object detection,” in CVPR 2011, IEEE, Jun. 2011, pp. 1401–1408. doi: 10.1109/CVPR.2011.5995545.

V. Narayanan and M. Likhachev, “PERCH: Perception via search for multi-object recognition and localization,” in 2016 IEEE International Conference on Robotics and Automation (ICRA), IEEE, May 2016, pp. 5052–5059. doi: 10.1109/ICRA.2016.7487711.

Y. F. Dewi and N. Fadillah, “Deteksi Objek Berwarna Merah Secara Real Time Dengan Algoritma Color Filtering,” Jurnal Media Informatika Budidarma, vol. 3, no. 2, p. 140, Apr. 2019, doi: 10.30865/mib.v3i2.1114.

Q. Liu, X. Fan, Z. Xi, Z. Yin, and Z. Yang, “Object detection based on Yolov4-Tiny and Improved Bidirectional feature pyramid network,” J Phys Conf Ser, vol. 2209, no. 1, p. 012023, Feb. 2022, doi: 10.1088/1742-6596/2209/1/012023.

E. R. Setyaningsih and M. S. Edy, “YOLOv4 dan Mask R-CNN Untuk Deteksi Kerusakan Pada Karung Komoditi,” Teknika, vol. 11, no. 1, pp. 45–52, Mar. 2022, doi: 10.34148/teknika.v11i1.419.

R. Gai, N. Chen, and H. Yuan, “A detection algorithm for cherry fruits based on the improved YOLO-v4 model,” Neural Comput Appl, vol. 35, no. 19, pp. 13895–13906, Jul. 2023, doi: 10.1007/s00521-021-06029-z.

A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” Apr. 2020, [Online]. Available: http://arxiv.org/abs/2004.10934

J. Yu and W. Zhang, “Face Mask Wearing Detection Algorithm Based on Improved YOLO-v4,” Sensors, vol. 21, no. 9, p. 3263, May 2021, doi: 10.3390/s21093263.

L. K. Pavithra and T. S. Sharmila, “An efficient framework for image retrieval using color, texture and edge features,” Computers & Electrical Engineering, vol. 70, pp. 580–593, Aug. 2018, doi: 10.1016/j.compeleceng.2017.08.030.

G. Ramaditya and W. F. Al Maki, “Single Object Tracking with Minimum False Positive using YOLOv4, VGG16, and Cosine Distance,” Jurnal Media Informatika Budidarma, vol. 6, no. 4, p. 2196, Oct. 2022, doi: 10.30865/mib.v6i4.4827.

N. D. Lynn, A. I. Sourav, and A. J. Santoso, “Implementation of Real-Time Edge Detection Using Canny and Sobel Algorithms,” IOP Conf Ser Mater Sci Eng, vol. 1096, no. 1, p. 012079, Mar. 2021, doi: 10.1088/1757-899X/1096/1/012079.

X. Zhou, L. Jiang, C. Hu, S. Lei, T. Zhang, and X. Mou, “YOLO-SASE: An Improved YOLO Algorithm for the Small Targets Detection in Complex Backgrounds,” Sensors, vol. 22, no. 12, p. 4600, Jun. 2022, doi: 10.3390/s22124600.

P. Laia, “Penerapan Metode Prewitt, Canny dan Sobel Pada Proses Deteksi Tepi Citra,” Jurnal Media Informatika Budidarma, vol. 2, no. 1, Jan. 2018, doi: 10.30865/mib.v2i1.996.

Published
2024-03-18
How to Cite
Sinaga, F. M., Gunawan, Winardi, S., Kurniawan, H., Lestari, W. S., & Tarigan, K. M. (2024). Object Detection in E-Commerce Using YOLO in Real Time. Teknika, 13(1), 145-154. https://doi.org/10.34148/teknika.v13i1.773
Section
Articles