Abstract
Due to the expension of High Dynamic Range (HDR) imaging applications into various aspects of daily life, an efficient retrieval system, tailored to this type of data, has become a pressing challenge. In this paper, the reliability of Convolutional Neural Networks (CNN) descriptor and its investigation for HDR image retrieval are studied. The main idea consists in exploring the use of CNN to determine HDR image descriptor. Specifically, a Perceptually Uniform (PU) encoding is initially applied to the HDR content to map the luminance values in a perceptually uniform scale. Afterward, the CNN features, using Fully Connected (FC) layer activation, are extracted and classified by applying the Support Vector Machines (SVM) algorithm. Experimental evaluation demonstrates that the CNN descriptor, using the VGG19 network, achieves satisfactory results for describing HDR images on public available datasets such as PascalVoc2007, Cifar-10 and Wang. The experimental results also show that the features, after a PU processing, are more descriptive than those directly extracted from HDR contents. Finally, we show the superior performance of the proposed method against a recent state-of-the-art technique.
Similar content being viewed by others
References
Aydin TO, Mantiuk R, Seidel HP (2008) Extending quality metrics to full luminance range images human. Human vision and electronic imaging XIII (Proceedings of SPIE), pp 6806–6810
Babenko A, Lempitsky V (2015) Aggregating deep convolutional features for image retrieval. International conference on computer vision, pp 1269–1277
Babenko A, Slesarev A, Chigorin A, Lempitsky V (2014) Neural codes for image retrieval. In: European conference on computer vision. Springer, Cham, pp 584–599
Banterle F, Ledda P, Debattista K, Chalmers A (2006) Inverse tone mapping. International conference on Computer graphics and interactive techniques. pp 349–356
Bronislav P, Chalmers A, Zemcík P., Hooberman L, Zadík M. (2016) Evaluation of feature point detection in high dynamic range imagery. J Vis Commun Image Represent 28(C):141–160
Chalmers A (2017) Debattista,K.: HDR video past, present and future: a perspective. Sig Process Image Commun 54:49–55
Debevec PE, Malik J (1997) Recovering high dynamicrange radiance maps from photographs. Proceedings SIGGRAPH, pp 369–378
Dufaux F, Callet PL, Mantiuk R, Mrak M (2016) High dynamic range video: from acquisition, to display and applications. Academic Press
Eilertsen G, Kronander J, Denes G, Mantiuk RK, Unger J (2017) HDR image reconstruction from a single exposure using deep CNNs. ACM Trans Graph 36(6):178:1–178:15
Endo Y, Kanamori Y, Mitani J (2017) Deep reverse tone mapping. ACM Trans Graph 36(6):177
Gao L, Li X, Song Shen HTJ (2020) Hierarchical LSTMs with adaptive attention for visual captioning. IEEE Trans Pattern Anal Mach Intell 42 (5):1112–1131
Gong Y, Wang L, Guo R, Lazebnik S (2014) Multi-scale orderless pooling of deep convolutional activation features. In: European conference on computer vision. Springer, Cham, pp 392–407
Gong Y, Wang L, Guo R, Lazebnik S (2014) Multi-scale orderless pooling of deep convolutional activation features. In: European conference on computer vision. Springer, Cham, pp 392–407
Gordo A, Almazan J, Revaud J, Larlus D (2017) End-to-end learning of deep visual representations for image retrieval. Int J Comput Vis 124 (2):237–254
He K, Zhang X, Ren S, Sun J (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. European Conference on Computer Vision, pp 346–361
Husain SS, Bober M (2019) Multi-layer entropy-guided pooling of dense CNN features for image retrieval. IEEE Trans Image Process 28(10):5201–5213
Kalantari NK, Ramamoorthi R (2017) Deep high dynamic range imaging of dynamic scenes. ACM Trans Graph 36(4):144:1–144:12
Kalantidis Y, Mellina C, Osindero S (2016) Cross-dimensional weighting for aggregated deep convolutional features. In: European conference on computer vision. Springer, Cham, pp 685–701
Khwildi R, Hachani M, Ouled Zaid A (2016) New indexing method of HDR images using color histograms. International conference on machine vision
Khwildi R, Ouled Zaid A (2018) Color Based HDR image retrieval using HSV histogram and color moments. In: International conference on computer systems and applications. IEEE, pp 1–5
Khwildi R, Ouled Zaid A (2018) New retrieval system based on low dynamic range expansion and SIFT descriptor. In: International workshop on multimedia signal processing. IEEE pp 1–6
Khwildi R, Ouled Zaid A (2020) HDR image retrieval by using color-based descriptor and tone mapping operator. Vis Comput 36:1111–1126
Kim BK, Park RH, Chang S (2016) Tone mapping with contrast preservation and lightness correction in high dynamic range imaging. SIViP 10(8):1425–1432
Kovaleski RP, Oliveira MM (2009) High-quality brightness enhancement functions for real-time reverse tone mapping. Vis Comput 25(5):539–547
Kovaleski RP, Oliveira MM (2014) High-quality reverse tone mapping for a wide range of exposures. In: Conference on graphics patterns and images. IEEE, pp 49–56
Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84–90
Larson GW (1998) Logluv encoding for full-gamut, high-dynamic range images. J Graph Tools 3(1):15–31
Lin K, Lu J, Chen C, Zhou J (2016) Learning compact binary descriptors with unsupervised deep neural networks. In: Conference on computer vision and pattern recognition, pp 1183–1192
Mantiuk RK, Myszkowski KH, Seidel P (2015) High dynamic range imaging. Wiley encyclopedia of electrical and electronics engineering, pp 1–4
Masia B, Serrano A, Gutierrez D (2017) Dynamic range expansion based on image statistics. Multimed Tools Appl 76(1):631–648
Mitsunaga T, Nayar SK (1999) Radiometric self calibration. In: Conference on computer vision and pattern recognition. IEEE, pp 374–380
Mohedano E, McGuinness K, et al. (2016) Bags of local convolution. International conference on multimedia retrieval, pp 327–331
Ng J, Yang F, Davis L (2015) Exploiting local features from deep networks for image retrieval. Conference on computer vision and pattern recognition workshops, pp 53–61
Pan Y, He F, Yu H (2020) Learning social representations with deep autoencoder for recommender system. World Wide Web 23:2259–2279
Quan Q, He F, Li H (2020) A multi-phase blending method with incremental intensity for training detection networks. Vis Comput, pp 1–15
Radenovic F, Tolias G, Chum O (2018) Fine-tuning CNN image retrieval with no human annotation. IEEE Trans Pattern Anal Mach Intell 41 (7):1655–1668
Rana A, Valenzise G, Dufaux F (2015) Evaluation of feature detection in HDR based imaging under changes in illumination conditions. In: IEEE international symposium on multimedia. IEEE, pp 289– 294
Rana A, Valenzise G, Dufaux F (2016) An Evaluation of HDR image matching under extreme illumination changes. In: Visual communications and image processing. IEEE, pp 1–4
Razavian AS, Azizpour H, Sullivan J, Carlsson S (2014) CNN features off-the-shelf: an astounding baseline for recognition. Computer vision and pattern recognition workshops, pp 512–519
Razavian AS, Sullivan J, Carlsson S, Maki A (2016) Visual instance retrieval with deep convolutional networks. ITE Trans Media Technol Appl 4(3):251–258
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. International conference on learning representations
Song J, He T, Gao L, et al. (2020) Unified binary generative adversarial network for image retrieval and compression. Int J Comput Vis 128:2243–2264
Tang Y (2013) Deep learning using linear support vector machines. International conference on neural information processing, pp 458–465
Tolias G, Sicre R, Jégou H. (2016) Particular object retrieval with integral max-pooling of CNN activations. International conference on learning representations, pp 1–12
Uricchio T, Bertini M, Seidenari L, Del Bimbo A (2015) Fisher encoded convolutional Bag-of-Windows for efficient image retrieval and social image tagging. In: International conference on computer vision workshop, pp 1020–1026
Vaccaro F, Bertini M, Uricchio T, Del BimboImage A (2020) Retrieval using multi-scale CNN features pooling. In: International conference on multimedia retrieval, pp 311–315
Vinyals O, Jia Y, Deng L, Darrell T (2012) Learning with recursive perceptual representations. Annu Conf Neural Inf Process Syst, pp 2834–2842
Ward G (1991) Real pixels. Graphics Gems, New York
Zhang N, Donahue J, Girshick R, Darrell T (2014) Part-based R-CNNs for fine-grained category detection. In: European conference on computer vision. Springer, Cham, pp 834–849
Zhang S, He F (2020) RCDN: Learning deep residual convolutional dehazing networks. Vis Comput 36(9):1797–1808
Zhang S, He F, Ren W (2020) NLDN: Non-local dehazing network for dense haze removal. Neurocomputing 410:363–373
Zhang J, Lalonde JF (2017) Learning high dynamic range from outdoor panoramas. In: International conference on computer vision. pp 4529–4538
Zheng L, Zhao Y, Wang S, Wang J, Tian Q (2016) Good practice in CNN feature transfer. arXiv preprint arXiv:1604.00133
Zhu H, Chen X, Dai W, Fu K, Ye Q, Jiao J (2015) Orientation robust object detection in aerial images using deep convolutional neural network. In: International conference on image processing. IEEE, pp 3735–3739
(2003) OpenEXR. http://www.openexr.org
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Khwildi, R., Ouled Zaid, A. & Dufaux, F. Query-by-example HDR image retrieval based on CNN. Multimed Tools Appl 80, 15413–15428 (2021). https://doi.org/10.1007/s11042-020-10416-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-10416-4