Deteksi Objek untuk Produk Retail dengan TensorFlow 2
Bilah Samping Artikel
Diterbitkan:
Des 30, 2024
Kata Kunci:
TensorFlow, Deteksi Objek, Perangkat Bergerak, Ketersediaan Barang di Rak
Isi Artikel Utama
Abstrak
Ketersediaan barang di rak (on-shelf availability) merupakan aspek penting dalam industri retail yang berdampak langsung pada kepuasan konsumen dan penjualan. Teknologi deteksi objek berbasis Kecerdasan Buatan dapat meningkatkan efisiensi dalam memantau ketersediaan produk. Penelitian ini mengkaji penerapan TensorFlow 2 untuk deteksi objek produk retail di rak, menggunakan arsitektur SSD MobileNetV2 FPNLite. Tiga variasi model dikembangkan berdasarkan ukuran input gambar, yaitu 320x320, 640x640, dan 1024x1024. Model dilatih menggunakan metode transfer learning dengan dataset yang berisi 128 kelas produk retail. Hasil evaluasi menunjukkan bahwa model dengan ukuran gambar 640x640 memberikan performa terbaik dalam hal trade-off antara presisi dan kecepatan, dengan mAP sebesar 0.72049 dan waktu inferensi 0.283 detik. Model 320x320 memiliki waktu inferensi tercepat sebesar 0.073 detik, menjadikannya cocok untuk aplikasi real-time. Penelitian ini menawarkan solusi untuk meningkatkan pengelolaan stok produk retail dengan deteksi objek otomatis, guna mengurangi risiko out-of-stock.
Rincian Artikel
##submission.howToCite##
Ahmad Azzam Alhanafi, & Arrie Kurniawardhani. (2024). Deteksi Objek untuk Produk Retail dengan TensorFlow 2. JITSI : Jurnal Ilmiah Teknologi Sistem Informasi, 5(4), 144 - 152. https://doi.org/10.62527/jitsi.5.4.298
Terbitan
Bagian
Articles
##submission.license.cc.by-sa4.footer##
Referensi
REFERENSI
[1] Har, Loh & Rashid, Umi Kartini & Te Chuan, Lee & Yin Xia, Loh. (2022). Revolution of Retail
Industry: From Perspective of Retail 1.0 to 4.0. Procedia Computer Science. 200.
10.1016/j.procs.2022.01.362.
[2] Klimchenia, L.. (2024). Retail transformation concepts development under the influence of industrial
revolutions. Vestnik Universiteta. 121-129. 10.26425/1816-4277-2024-6-121-129.
[3] Rai, Prakruthi & Nanjundan, Preethi & George, Jossy. (2024). Enhancing Industrial Operations through
AI-Driven Decision-Making in the Era of Industry 4.0. 10.1201/9781003432319-3..
[4] Andaur, Juan & Ruz, Gonzalo & Goycoolea, Marcos. (2021). Predicting Out-of-Stock Using Machine
Learning: An Application in a Retail Packaged Foods Manufacturing Company. Electronics. 10. 2787.
10.3390/electronics10222787.
[5] Šikić F, Kalafatić Z, Subašić M, Lončarić S. (2024). Enhanced Out-of-Stock Detection in Retail Shelf
Images Based on Deep Learning. Sensors; 24(2):693. https://doi.org/10.3390/s2402069.
[6] Afram, G. (2020). A study on how to improve On-shelf availability : With deep learning (Dissertation).
Retrieved from https://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-40006.
[7] al Azzo, Fadwa & Taqi, Arwa & Milanova, Mariofanna. (2018). Human Related-Health Actions
Detection using Android Camera based on TensorFlow Object Detection API. International Journal of
Advanced Computer Science and Applications. 9. 10.14569/IJACSA.2018.091002.
[8] Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J.,
Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Kaiser, L., Kudlur, M.,
Levenberg, J., & Zheng, X. (2015). TensorFlow : Large-Scale Machine Learning on Heterogeneous
Distributed Systems. arXiv:1603.04467v2 [cs.DC]
[9] Vasilakopoulos, G. P., (2024). An Automatic Differentiation Algorithm for Recursive Functions and its
Implementation in TensorFlow. Thesis. National and Kapodistrian University of Athens.
[10] Rezaei Nasab, Ali & Dashti, Maedeh & Shahin, Mojtaba & Zahedi, Mansooreh & Khalajzadeh, Hourieh
& Arora, Chetan & Liang, Peng. (2024). Fairness Concerns in App Reviews: A Study on AI-based
Mobile Apps. 10.48550/arXiv.2401.08097.
[11] Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016). SSD: Single
Shot Multibox Detector. European Conference on Computer Vision (ECCV), 21-37.
[12] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted
Residuals and Linear Bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern
Recognition (CVPR), 4510-4520.
[13] Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H.
(2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv
preprint arXiv:1704.04861.
[14] Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature Pyramid
Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern
Recognition (CVPR), 2117-2125.
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi, Volume x No x, March xxxx Hal x - xx
Ahmad Azzam Alhanafi, Arrie Kurniawardhani 11Deteksi Objek untuk Produk Retail dengan TensorFlow 2
[15] Goldsborough, P. (2016). A Tour of TensorFlow. ArXiv, abs/1610.01178.
[16] LabelImg, "LabelImg: LabelImg is a graphical image annotation tool and label object bounding boxes in
images", Available: https://github.com/heartexlabs/labelImg, accessed on 22 October 2024.
[17] Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010). The Pascal Visual
Object Classes (VOC) Challenge. International Journal of Computer Vision, 88(2), 303–338.
https://doi.org/10.1007/s11263-009-0275-4..
[18] TensorFlow, "TFRecord and tf.train.Example", Available:
https://www.tensorflow.org/tutorials/load_data/tfrecord, accessed on 22 October 2024.
[19] TensorFlow, "TensorFlow Object Detection API," Available:
https://github.com/tensorflow/models/tree/master/research/object_detection, accessed on 22 October
2024.
[20] TensorFlow, "Training a TensorFlow Object Detection Model" Available:
https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/training.html, accessed on 22
Oktober 2024.
[21] Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollar, P., & Zitnick, C. L. (2014).
Microsoft COCO: Common Objects in Context. European Conference on Computer Vision (ECCV),
740–755. https://doi.org/10.1007/978-3-319-10602-1_48.
[22] Manning, C. D., Raghavan, P., & Schütze, H. (2008). Introduction to Information Retrieval. Cambridge
University Press.
[23] TensorFlow, "TensorFlow Lite", Available: https://www.tensorflow.org/lite, accessed on 23 October
2024.
[1] Har, Loh & Rashid, Umi Kartini & Te Chuan, Lee & Yin Xia, Loh. (2022). Revolution of Retail
Industry: From Perspective of Retail 1.0 to 4.0. Procedia Computer Science. 200.
10.1016/j.procs.2022.01.362.
[2] Klimchenia, L.. (2024). Retail transformation concepts development under the influence of industrial
revolutions. Vestnik Universiteta. 121-129. 10.26425/1816-4277-2024-6-121-129.
[3] Rai, Prakruthi & Nanjundan, Preethi & George, Jossy. (2024). Enhancing Industrial Operations through
AI-Driven Decision-Making in the Era of Industry 4.0. 10.1201/9781003432319-3..
[4] Andaur, Juan & Ruz, Gonzalo & Goycoolea, Marcos. (2021). Predicting Out-of-Stock Using Machine
Learning: An Application in a Retail Packaged Foods Manufacturing Company. Electronics. 10. 2787.
10.3390/electronics10222787.
[5] Šikić F, Kalafatić Z, Subašić M, Lončarić S. (2024). Enhanced Out-of-Stock Detection in Retail Shelf
Images Based on Deep Learning. Sensors; 24(2):693. https://doi.org/10.3390/s2402069.
[6] Afram, G. (2020). A study on how to improve On-shelf availability : With deep learning (Dissertation).
Retrieved from https://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-40006.
[7] al Azzo, Fadwa & Taqi, Arwa & Milanova, Mariofanna. (2018). Human Related-Health Actions
Detection using Android Camera based on TensorFlow Object Detection API. International Journal of
Advanced Computer Science and Applications. 9. 10.14569/IJACSA.2018.091002.
[8] Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J.,
Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Kaiser, L., Kudlur, M.,
Levenberg, J., & Zheng, X. (2015). TensorFlow : Large-Scale Machine Learning on Heterogeneous
Distributed Systems. arXiv:1603.04467v2 [cs.DC]
[9] Vasilakopoulos, G. P., (2024). An Automatic Differentiation Algorithm for Recursive Functions and its
Implementation in TensorFlow. Thesis. National and Kapodistrian University of Athens.
[10] Rezaei Nasab, Ali & Dashti, Maedeh & Shahin, Mojtaba & Zahedi, Mansooreh & Khalajzadeh, Hourieh
& Arora, Chetan & Liang, Peng. (2024). Fairness Concerns in App Reviews: A Study on AI-based
Mobile Apps. 10.48550/arXiv.2401.08097.
[11] Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016). SSD: Single
Shot Multibox Detector. European Conference on Computer Vision (ECCV), 21-37.
[12] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted
Residuals and Linear Bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern
Recognition (CVPR), 4510-4520.
[13] Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H.
(2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv
preprint arXiv:1704.04861.
[14] Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature Pyramid
Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern
Recognition (CVPR), 2117-2125.
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi, Volume x No x, March xxxx Hal x - xx
Ahmad Azzam Alhanafi, Arrie Kurniawardhani 11Deteksi Objek untuk Produk Retail dengan TensorFlow 2
[15] Goldsborough, P. (2016). A Tour of TensorFlow. ArXiv, abs/1610.01178.
[16] LabelImg, "LabelImg: LabelImg is a graphical image annotation tool and label object bounding boxes in
images", Available: https://github.com/heartexlabs/labelImg, accessed on 22 October 2024.
[17] Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010). The Pascal Visual
Object Classes (VOC) Challenge. International Journal of Computer Vision, 88(2), 303–338.
https://doi.org/10.1007/s11263-009-0275-4..
[18] TensorFlow, "TFRecord and tf.train.Example", Available:
https://www.tensorflow.org/tutorials/load_data/tfrecord, accessed on 22 October 2024.
[19] TensorFlow, "TensorFlow Object Detection API," Available:
https://github.com/tensorflow/models/tree/master/research/object_detection, accessed on 22 October
2024.
[20] TensorFlow, "Training a TensorFlow Object Detection Model" Available:
https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/training.html, accessed on 22
Oktober 2024.
[21] Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollar, P., & Zitnick, C. L. (2014).
Microsoft COCO: Common Objects in Context. European Conference on Computer Vision (ECCV),
740–755. https://doi.org/10.1007/978-3-319-10602-1_48.
[22] Manning, C. D., Raghavan, P., & Schütze, H. (2008). Introduction to Information Retrieval. Cambridge
University Press.
[23] TensorFlow, "TensorFlow Lite", Available: https://www.tensorflow.org/lite, accessed on 23 October
2024.