Research Article
BibTex RIS Cite

Unsupervised Image Hashing Using a Deep Convolutional Encoder-Decoder Model for Fast Image Retrieval

Year 2023, Volume: 23 Issue: 6, 1458 - 1465, 28.12.2023
https://doi.org/10.35414/akufemubid.1236064

Abstract

Image hashing methods transform high-dimensional image features into low-dimensional binary codes while preserving semantic similarity. Among image hashing techniques, supervised image hashing approaches outperform unsupervised and semisupervised methods. However, labelling image data requires extra time and expert effort. In this study, we proposed a deep learning-based unsupervised image hashing method for unlabeled image data. The proposed hashing method is built in an end-to-end fashion. It consists of an encoder-decoder model. As a novel idea, we used a supervised pre-trained network as an encoder model, which provides fast convergence in the training phase and efficient image features. Hash codes are extracted by optimizing those intermediate features. Experiments performed on two benchmark image datasets demonstrate the competitive results compared to unsupervised image hashing methods.

References

  • Akalın, B. and Veranyurt, Ü., 2022. Sağlık 4. O ve Sağlıkta Yapay Zekâ. Sağlık Profesyonelleri Araştırma Dergisi, 4(1), 57-64.
  • Aslan, F. and Subaşı, A., 2022. Hemşirelik Eğitimi ve Hemşirelik Süreci Perspektifinden Yapay Zeka Teknolojilerine Farklı Bir Bakış. Sağlık Bilimleri Üniversitesi Hemşirelik Dergisi, 4(3), 153-158.
  • Baduge, S.K., Thilakarathna, S., Perera, J.S., Arashpour, M., Sharafi, P., Teodosio, B., Shringi, A. and Mendis, P., 2022. Artificial intelligence and smart vision for building and construction 4.0: Machine and deep learning methods and applications. Automation in Construction, 141, 104440.
  • Baur, C., Denner, S., Wiestler, B., Navab, N. and Albarqouni, S., 2021. Autoencoders for unsupervised anomaly segmentation in brain MR images: a comparative study. Medical Image Analysis, 69, 101952.
  • Keerthi Nayani, A.S., Sekhar, C., Srinivasa Rao, M. and Venkata Rao, K., 2021. Enhancing image resolution and denoising using autoencoder. In Data Analytics and Management: Proceedings of ICDAM (649-659). Springer Singapore.
  • Mchergui, A., Moulahi, T. and Zeadally, S., 2022. Survey on artificial intelligence (AI) techniques for vehicular ad-hoc networks (VANETs). Vehicular Communications, 34, 100403.
  • Minh, D., Wang, H.X., Li, Y.F. and Nguyen, T.N., 2022. Explainable artificial intelligence: a comprehensive review. Artificial Intelligence Review, 1-66.
  • Mutlu, İ.N., Koçak, B., Kuş, E.A., Ulusan, M.B. and Kılıçkesmez, Ö., 2021. Machine Learning-Based Computed Tomography Texture Analysis of Lytic Bone Lesions Needing Biopsy: A Preliminary Study. Istanbul Medical Journal, 22(3).
  • Myronenko, A., 2019. 3D MRI brain tumor segmentation using autoencoder regularization. In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 4th International Workshop, BrainLes 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers, Part II 4 (311-320). Springer International Publishing.
  • Nahavandi, D., Alizadehsani, R., Khosravi, A. and Acharya, U.R., 2022. Application of artificial intelligence in wearable devices: Opportunities and challenges. Computer Methods and Programs in Biomedicine, 213, 106541.
  • Patel, F.S. and Kasat, D., 2017, February. Hashing based indexing techniques for content based image retrieval: A survey. In 2017 International Conference on Innovative Mechanisms for Industry Applications (ICIMIA) (279-283). IEEE.
  • Shi, X., Guo, Z., Xing, F., Liang, Y. and Yang, L., 2020. Anchor-based self-ensembling for semi-supervised deep pairwise hashing. International Journal of Computer Vision, 128, 2307-2324.
  • Singh, A. and Gupta, S., 2022. Learning to hash: A comprehensive survey of deep learning-based hashing methods. Knowledge and Information Systems, 64(10), 2565-2597.
  • Şendir, M., Şimşekoğlu, N., Abdulsamed, K.A.Y.A. and SÜMER, K., 2019. Geleceğin teknolojisinde hemşirelik. Sağlık Bilimleri Üniversitesi Hemşirelik Dergisi, 1(3), 209-214.
  • Tang, X., Liu, C., Zhang, X., Ma, J., Jiao, C. and Jiao, L., 2019, July. Remote sensing image retrieval based on semi-supervised deep hashing learning. In IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium (879-882). IEEE.
  • Tian, X., Zhou, X., Ng, W.W., Li, J. and Wang, H., 2020. Bootstrap dual complementary hashing with semi-supervised re-ranking for image retrieval. Neurocomputing, 379, 103-116.
  • Yu, Q., 2020. Improved denoising autoencoder for maritime image denoising and semantic segmentation of USV (J). China Communications, 17(3), 46-57.
  • Wang, J., Liu, W., Kumar, S. and Chang, S.F., 2015. Learning to hash for indexing big data—A survey. Proceedings of the IEEE, 104(1), 34-57.
  • Wang, Y., Song, J., Zhou, K. and Liu, Y., 2021. Unsupervised deep hashing with node representation for image retrieval. Pattern Recognition, 112, 107785.
  • Wang, Z. and Bovik, A.C., 2009. Mean squared error: Love it or leave it? A new look at signal fidelity measures. IEEE signal processing magazine, 26(1), 98-117.
  • Yu, Y., Yang, L. and Wang, S., 2021, November. Deep hash image retrieval method based on anti-autoencoder. In 2021 7th International Conference on Systems and Informatics (ICSAI) (1-5). IEEE.
  • Zhang, H., Gu, Y., Yao, Y., Zhang, Z., Liu, L., Zhang, J. and Shao, L., 2020. Deep unsupervised self-evolutionary hashing for image retrieval. IEEE Transactions on Multimedia, 23, 3400-3413.
  • Zhang, X., Wang, X. and Cheng, P., 2021. Contrast-based unsupervised hashing learning with multi-hashcode. IEEE Signal Processing Letters, 29, 219-223.
  • https://en.wikipedia.org/wiki/Mean_squared_error, (13.10.2023)
  • https://neptune.ai/blog/cross-entropy-loss-and-its-applications-in-deep-learning, (21.10.2022)
  • https://viso.ai/deep-learning/resnet-residual-neural-network, (03.11.2022)
  • https://www.image-net.org, (11.11.2022)
  • https://www.kaggle.com/datasets/awsaf49/coco-2017-dataset, (18.08.2022)
  • https://medmnist.com, (18.08.2022)
  • https://keras.io, (09.11.2022)
  • https://keras.io/api/optimizers/adam, (09.11.2022)
  • https://github.com/enverakbacak/AE, (11.01.2023)

Derin Konvolüsyonel Kodlayıcı-Kod Çözücü ile Görüntü Hash Kodlarının Çıkartılarak Hızlı Görüntü Erişiminin Gerçekleştirilmesi

Year 2023, Volume: 23 Issue: 6, 1458 - 1465, 28.12.2023
https://doi.org/10.35414/akufemubid.1236064

Abstract

Görüntü hash kodlarını elde eden metotlar, yüksek boyutlu ve sayısal olan görüntü özniteliklerini, görüntüler arasındaki anlamsal ilişkileri koruyacak şekilde daha düşük boyutlu ikili kodlara dönüştürürler. Hash teknikleri arasında denetimli öğrenmeye dayalı yöntemler, denetimsiz ve yarı denetimli öğrenme metotlarına göre daha verimlidirler. Ancak denetimli öğrenmeye dayalı yöntemler görüntülerin anlamsal etiketlerini kullanırlar ve bu da ilave bir çalışma ve uzman emeği gerektirir. Bu çalışmada etiketsiz görüntüler için denetimsiz öğrenmeye dayalı bir yöntem sunulmuştur. Bu yöntem uçtan uca kesintisiz entegre bir yöntemdir. Yöntem kodlayıcı-kod çözücü tabanlıdır. Yeni bir öneri olarak, kodlayıcı kısmında önceden denetimli olarak eğitilmiş bir derin ağın bloklarını kullanmamız, eğitim aşamasında hızlı yakınsamayı ve görüntü özniteliklerinin verimli olmasını sağlamıştır. Hash kodları ise bu özniteliklerin optimize edilmesi ile çıkarılmıştır. İki bilinen görüntü veri seti ile gerçekleştirilen deney sonuçları önerilen yöntemin diğer denetimsiz öğrenme yöntemlerine kıyasla rekabetçi sonuçlar verdiğini göstermiştir.

References

  • Akalın, B. and Veranyurt, Ü., 2022. Sağlık 4. O ve Sağlıkta Yapay Zekâ. Sağlık Profesyonelleri Araştırma Dergisi, 4(1), 57-64.
  • Aslan, F. and Subaşı, A., 2022. Hemşirelik Eğitimi ve Hemşirelik Süreci Perspektifinden Yapay Zeka Teknolojilerine Farklı Bir Bakış. Sağlık Bilimleri Üniversitesi Hemşirelik Dergisi, 4(3), 153-158.
  • Baduge, S.K., Thilakarathna, S., Perera, J.S., Arashpour, M., Sharafi, P., Teodosio, B., Shringi, A. and Mendis, P., 2022. Artificial intelligence and smart vision for building and construction 4.0: Machine and deep learning methods and applications. Automation in Construction, 141, 104440.
  • Baur, C., Denner, S., Wiestler, B., Navab, N. and Albarqouni, S., 2021. Autoencoders for unsupervised anomaly segmentation in brain MR images: a comparative study. Medical Image Analysis, 69, 101952.
  • Keerthi Nayani, A.S., Sekhar, C., Srinivasa Rao, M. and Venkata Rao, K., 2021. Enhancing image resolution and denoising using autoencoder. In Data Analytics and Management: Proceedings of ICDAM (649-659). Springer Singapore.
  • Mchergui, A., Moulahi, T. and Zeadally, S., 2022. Survey on artificial intelligence (AI) techniques for vehicular ad-hoc networks (VANETs). Vehicular Communications, 34, 100403.
  • Minh, D., Wang, H.X., Li, Y.F. and Nguyen, T.N., 2022. Explainable artificial intelligence: a comprehensive review. Artificial Intelligence Review, 1-66.
  • Mutlu, İ.N., Koçak, B., Kuş, E.A., Ulusan, M.B. and Kılıçkesmez, Ö., 2021. Machine Learning-Based Computed Tomography Texture Analysis of Lytic Bone Lesions Needing Biopsy: A Preliminary Study. Istanbul Medical Journal, 22(3).
  • Myronenko, A., 2019. 3D MRI brain tumor segmentation using autoencoder regularization. In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 4th International Workshop, BrainLes 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers, Part II 4 (311-320). Springer International Publishing.
  • Nahavandi, D., Alizadehsani, R., Khosravi, A. and Acharya, U.R., 2022. Application of artificial intelligence in wearable devices: Opportunities and challenges. Computer Methods and Programs in Biomedicine, 213, 106541.
  • Patel, F.S. and Kasat, D., 2017, February. Hashing based indexing techniques for content based image retrieval: A survey. In 2017 International Conference on Innovative Mechanisms for Industry Applications (ICIMIA) (279-283). IEEE.
  • Shi, X., Guo, Z., Xing, F., Liang, Y. and Yang, L., 2020. Anchor-based self-ensembling for semi-supervised deep pairwise hashing. International Journal of Computer Vision, 128, 2307-2324.
  • Singh, A. and Gupta, S., 2022. Learning to hash: A comprehensive survey of deep learning-based hashing methods. Knowledge and Information Systems, 64(10), 2565-2597.
  • Şendir, M., Şimşekoğlu, N., Abdulsamed, K.A.Y.A. and SÜMER, K., 2019. Geleceğin teknolojisinde hemşirelik. Sağlık Bilimleri Üniversitesi Hemşirelik Dergisi, 1(3), 209-214.
  • Tang, X., Liu, C., Zhang, X., Ma, J., Jiao, C. and Jiao, L., 2019, July. Remote sensing image retrieval based on semi-supervised deep hashing learning. In IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium (879-882). IEEE.
  • Tian, X., Zhou, X., Ng, W.W., Li, J. and Wang, H., 2020. Bootstrap dual complementary hashing with semi-supervised re-ranking for image retrieval. Neurocomputing, 379, 103-116.
  • Yu, Q., 2020. Improved denoising autoencoder for maritime image denoising and semantic segmentation of USV (J). China Communications, 17(3), 46-57.
  • Wang, J., Liu, W., Kumar, S. and Chang, S.F., 2015. Learning to hash for indexing big data—A survey. Proceedings of the IEEE, 104(1), 34-57.
  • Wang, Y., Song, J., Zhou, K. and Liu, Y., 2021. Unsupervised deep hashing with node representation for image retrieval. Pattern Recognition, 112, 107785.
  • Wang, Z. and Bovik, A.C., 2009. Mean squared error: Love it or leave it? A new look at signal fidelity measures. IEEE signal processing magazine, 26(1), 98-117.
  • Yu, Y., Yang, L. and Wang, S., 2021, November. Deep hash image retrieval method based on anti-autoencoder. In 2021 7th International Conference on Systems and Informatics (ICSAI) (1-5). IEEE.
  • Zhang, H., Gu, Y., Yao, Y., Zhang, Z., Liu, L., Zhang, J. and Shao, L., 2020. Deep unsupervised self-evolutionary hashing for image retrieval. IEEE Transactions on Multimedia, 23, 3400-3413.
  • Zhang, X., Wang, X. and Cheng, P., 2021. Contrast-based unsupervised hashing learning with multi-hashcode. IEEE Signal Processing Letters, 29, 219-223.
  • https://en.wikipedia.org/wiki/Mean_squared_error, (13.10.2023)
  • https://neptune.ai/blog/cross-entropy-loss-and-its-applications-in-deep-learning, (21.10.2022)
  • https://viso.ai/deep-learning/resnet-residual-neural-network, (03.11.2022)
  • https://www.image-net.org, (11.11.2022)
  • https://www.kaggle.com/datasets/awsaf49/coco-2017-dataset, (18.08.2022)
  • https://medmnist.com, (18.08.2022)
  • https://keras.io, (09.11.2022)
  • https://keras.io/api/optimizers/adam, (09.11.2022)
  • https://github.com/enverakbacak/AE, (11.01.2023)
There are 32 citations in total.

Details

Primary Language English
Subjects Artificial Intelligence
Journal Section Articles
Authors

Enver Akbacak 0000-0002-6753-7887

Early Pub Date December 22, 2023
Publication Date December 28, 2023
Submission Date January 17, 2023
Published in Issue Year 2023 Volume: 23 Issue: 6

Cite

APA Akbacak, E. (2023). Unsupervised Image Hashing Using a Deep Convolutional Encoder-Decoder Model for Fast Image Retrieval. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, 23(6), 1458-1465. https://doi.org/10.35414/akufemubid.1236064
AMA Akbacak E. Unsupervised Image Hashing Using a Deep Convolutional Encoder-Decoder Model for Fast Image Retrieval. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi. December 2023;23(6):1458-1465. doi:10.35414/akufemubid.1236064
Chicago Akbacak, Enver. “Unsupervised Image Hashing Using a Deep Convolutional Encoder-Decoder Model for Fast Image Retrieval”. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi 23, no. 6 (December 2023): 1458-65. https://doi.org/10.35414/akufemubid.1236064.
EndNote Akbacak E (December 1, 2023) Unsupervised Image Hashing Using a Deep Convolutional Encoder-Decoder Model for Fast Image Retrieval. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi 23 6 1458–1465.
IEEE E. Akbacak, “Unsupervised Image Hashing Using a Deep Convolutional Encoder-Decoder Model for Fast Image Retrieval”, Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, vol. 23, no. 6, pp. 1458–1465, 2023, doi: 10.35414/akufemubid.1236064.
ISNAD Akbacak, Enver. “Unsupervised Image Hashing Using a Deep Convolutional Encoder-Decoder Model for Fast Image Retrieval”. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi 23/6 (December 2023), 1458-1465. https://doi.org/10.35414/akufemubid.1236064.
JAMA Akbacak E. Unsupervised Image Hashing Using a Deep Convolutional Encoder-Decoder Model for Fast Image Retrieval. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi. 2023;23:1458–1465.
MLA Akbacak, Enver. “Unsupervised Image Hashing Using a Deep Convolutional Encoder-Decoder Model for Fast Image Retrieval”. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, vol. 23, no. 6, 2023, pp. 1458-65, doi:10.35414/akufemubid.1236064.
Vancouver Akbacak E. Unsupervised Image Hashing Using a Deep Convolutional Encoder-Decoder Model for Fast Image Retrieval. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi. 2023;23(6):1458-65.