Various methods have been performed for the purpose of Low Dynamic Range (LDR) image retrieval. However, no major work concerning the High Dynamic Range (HDR) image indexing has been widely diffused yet. We therefore propose a method that tackles the problem of efficiently and accurately retrieving HDR images. The proposed system is based on a hybrid descriptor which combines two color features. The first one is histogram based on the hue–saturation–value (HSV) color space that approaches the perception of human vision, whereas the second comprises the first- and second-order moments of the color bands. As a dissimilarity measure, we retained the Manhattan distance. In the second part of our work, we proposed an automatic tone mapping operator (TMO) to get an overview on the result images by using Standard Dynamic Range (SDR) devices. Comparisons with recent state-of-the-art TMOs have shown that our TM method produces LDR images with adequate quality while maintaining low complexity. Finally, to test our retrieval system, we have created two databases. Experimental evaluation showed that our system supports HDR images while achieving satisfying results in terms of accuracy and computational cost.

HDR image retrieval by using color-based descriptor and tone mapping operator

An anchoring theory of lightness perception comprehensively explains many characteristics of human visual system such as lightness constancy and its spectacular failures which are important in the perception of images. We present a novel approach to tone mapping of high dynamic range (HDR) images which is inspired by the anchoring theory. The key concept of this method is the decomposition of an HDR image into areas (frameworks) of consistent luminance and the local calculation of the lightness values. The net lightness of an image is calculated via the merging of the frameworks proportionally to their strength. We stress out the importance of relating the luminance to a known brightness value (anchoring) and investigate the advantages of anchoring to the luminance value perceived as white. We validate the accuracy of the lightness reproduction in the presented algorithm by simulating a well known perception experiment. Our approach does not affect the local contrast and preserves the natural colors of an HDR image due to the linear handling of luminance.

Lightness Perception in Tone Reproduction for High Dynamic Range Images

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.

/pdf/query-by-example-hdr-image-retrieval-based-on-cnn-3gxbt8esl8.pdf

Query-by-example HDR image retrieval based on CNN

The proposed abstraction framework manipulates the visual-features from low-illuminated and underexposed images while retaining the prominent structural, medium scale details, tonal information, and suppresses the superfluous details like noise, complexity, and irregular gradient. The significant image features are refined at every stage of the work by comprehensively integrating a series of AnshuTMO and NPR filters through rigorous experiments. The work effectively preserves the structural features in the foreground of an image and diminishes the background content of an image. Effectiveness of the work has been validated by conducting experiments on the standard datasets such as Mould, Wang, and many other interesting datasets and the obtained results are compared with similar contemporary work cited in the literature. In addition, user visual feedback and the quality assessment techniques were used to evaluate the work. Image abstraction and stylization applications, constraints, challenges, and future work in the fields of NPR domain are also envisaged in this paper.

Structure Preserving Non-Photorealistic Rendering Framework for Image Abstraction and Stylization of Low-Illuminated and Underexposed Images

In this work, we address the problem of efficiently and accurately retrieving High Dynamic Range (HDR) images and displaying the retrieval results in Standard Dynamic Range (SDR) devices. The proposed approach considers a set of global descriptors for modeling an HDR image using vector of features that combines two color attributes: the color histogram based on the Hue-Saturation-Value (HSV) space and the color moments. The dissimilarity between images is measured using Manhattan distance. To evaluate the effectiveness of our retrieval system and conduct our tests, we created a collection of various HDR images. Experimental results demonstrate that the proposed method yields satisfactory results. It can accurately retrieve the similar HDR images. Moreover, we applied our retrieval method on Low Dynamic Range (LDR) version of the same dataset. The comparisons confirm that the features extracted from HDR images are more effective than those extracted from LDR ones.

Color Based HDR Image Retrieval using HSV Histogram and Color Moments

Various methods for color histogram based indexing of Low Dynamic Range Images, have been developed. All these methods are considered to be effective, but none of the algorithms has been extended to High Dynamic Range (HDR) Images. In this paper, we present a new method for HDR image indexing using histogram intersection in the hue-saturation-value (HSV) color space. For a given HDR image, the proposed approach considers a global descriptor computed according to the quantization of the HSV color space. This descriptor it is highly discriminative and fast to compute. The strength of our approach is proven through experimental results using a database which contains 205 images that are classified into 12 categories. Preliminary results showed that the developed algorithm performs well for HDR image retrieval.

A new indexing method of HDR images using color histograms

When comparing the intelligibility of Low Dynamic Range (LDR) content with that of the human visual system (HSV), we find that the former is quite limited. This is straightforward, as LDR technologies could only handle 8 or 12-bit per color channel. This being said, LDR images are still used in a wide range of multimedia applications. This paper presents a solution for efficiently indexing LDR content by introducing a novel descriptor based on LDR content expansion. To increase the richness of features that are strongly dependent on the illumination of the scene, the LDR image is converted to High Dynamic Range (HDR) one using reverse Tone Mapping Operator (rTMO). The result HDR image is in turn tone mapped and the relevant features are determined according the Scale Invariant Feature Transform (SIFT) descriptor. After that, the obtained features are gathered into a vector using Bag-of-Visual-Word (BoVW) strategy. A set of routine benchmarking experiments utilizing the Wang and Pascal Voc databases indicates that our system performs well for image retrieval. These experiments also demonstrate that features extracted from reverse tone mapped and tone mapped image are more descriptive than those extracted from LDR and HDR contents.

Raoua Khwildi

Papers

HDR image retrieval by using color-based descriptor and tone mapping operator

Query-by-example HDR image retrieval based on CNN

A new indexing method of HDR images using color histograms

Color Based HDR Image Retrieval using HSV Histogram and Color Moments

A New Retrieval System Based on Low Dynamic Range Expansion and SIFT Descriptor