Loading...

Toward real-time image annotation using marginalized coupled dictionary learning

Roostaiyan, S. M ; Sharif University of Technology | 2022

78 Viewed
  1. Type of Document: Article
  2. DOI: 10.1007/s11554-022-01210-6
  3. Publisher: Springer Science and Business Media Deutschland GmbH , 2022
  4. Abstract:
  5. In most image retrieval systems, images include various high-level semantics, called tags or annotations. Virtually all the state-of-the-art image annotation methods that handle imbalanced labeling are search-based techniques which are time-consuming. In this paper, a novel coupled dictionary learning approach is proposed to learn a limited number of visual prototypes and their corresponding semantics simultaneously. This approach leads to a real-time image annotation procedure. Another contribution of this paper is that utilizes a marginalized loss function instead of the squared loss function that is inappropriate for image annotation with imbalanced labels. We have employed a marginalized loss function in our method to leverage a simple and effective method of prototype updating. Meanwhile, we have introduced ℓ1 regularization on semantic prototypes to preserve the sparse and imbalanced nature of labels in learned semantic prototypes. Finally, comprehensive experimental results on various datasets demonstrate the efficiency of the proposed method for image annotation tasks in terms of accuracy and time. The reference implementation is publicly available at https://github.com/hamid-amiri/MCDL-Image-Annotation. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature
  6. Keywords:
  7. Image annotation ; Real-time ; Convolutional neural networks ; Image analysis ; Image retrieval ; Search engines ; Convolutional neural network ; Coupled dictionary learning ; Dictionary learning ; Image retrieval systems ; Loss functions ; Real time images ; Real- time ; Real-time images ; Sparse representation ; Semantics
  8. Source: Journal of Real-Time Image Processing ; Volume 19, Issue 3 , 2022 , Pages 623-638 ; 18618200 (ISSN)
  9. URL: https://link.springer.com/article/10.1007/s11554-022-01210-6