Optimized feature space learning for generating efficient binary codes for image retrieval

• Published in: Signal processing. Image communication 2022-01, Vol.100, p.116529, Article 116529
• Main Authors: Jose, Abin, Ottlik, Erik Stefan, Rohlfing, Christian, Ohm, Jens-Rainer
• Format: Article
• Language: English
• Subjects: Binary codes; Canonical Correlation Analysis; Computer architecture; Correlation analysis; Correlation coefficients; Discriminant analysis; Eigenvalues; Hashing; Image management; Image retrieval; Iterative Quantization; Learning; Linear Discriminant Analysis; Lower bounds; Mathematical analysis; Neural networks; Object recognition; Optimization; Vectors (mathematics)
• ISSN: 0923-5965; 1879-2677
• DOI: 10.1016/j.image.2021.116529

In this paper, a novel approach for learning a low-dimensional optimized feature space for image retrieval with minimum intra-class variance and maximum inter-class variance is proposed. The classical approach of Linear Discriminant Analysis (LDA) is generally used for generating an optimized low-dimensional feature space for single-labeled images. Since image retrieval involves images with multiple objects, LDA cannot be directly used for dimensionality reduction and feature space optimization. This problem is addressed by utilizing the relationship between LDA and Canonical Correlation Analysis (CCA) eigenvalues to generate an optimized feature space for both single-labeled and multi-labeled images. A CCA-based network architecture which correlates the low-dimensional feature vectors with the image label vectors is proposed. We design a novel loss function such that the correlation coefficients of CCA are maximized. Our experiments prove that we could train the neural network to reach the theoretical lower bound of loss corresponding to the negative sum of the correlation coefficients. Once the optimized feature space is generated, feature vectors are binarized with the Iterative Quantization (ITQ) approach. Finally, we propose an ensemble network to generate binary codes of desired bit length for retrieval. The measurement of mean average precision shows that the proposed approach outperforms the retrieval results of other single-labeled and multi-labeled image retrieval benchmarks at same bit numbers in a considerable number of cases. •An optimized feature space for single-labeled images by utilizing the relationship between LDA and CCA.•Extended feature space learning to multi-labeled images with the CCA.•A novel loss function based on the correlation coefficients of CCA is designed•An efficient ensemble technique for generating binary codes of desired bit length is proposed