Improving content-based image retrieval for heterogeneous datasets using histogram-based descriptors

Reta, Carolina; Solis-Moreno, Ismael; Cantoral-Ceballos, Jose A.; Alvarez-Vargas, Rogelio; Townend, Paul

doi:10.1007/s11042-017-4708-8

Cited by 12 publications

(6 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the years, different approaches have been proposed to combine global and local descriptors (color and texture [ 13 , 33 , 44 , 45 , 107 ], color and shape [ 2 , 25 , 75 , 113 , 116 ], shape and texture [ 92 , 103 ], and color, shape, and texture [ 7 , 8 , 14 , 73 , 81 , 83 , 86 , 121 ]). To a lesser extent, authors have also proposed combinations of low- and high-level descriptors [ 57 , 58 ], and an ensemble of high-level descriptors [ 36 ].…”

Section: Related Workmentioning

confidence: 99%

ExpertosLF: dynamic late fusion of CBIR systems using online learning with relevance feedback

Alarcão

Mendonça

Maruta

et al. 2022

Multimed Tools Appl

View full text Add to dashboard Cite

One of the main challenges in CBIR systems is to choose discriminative and compact features, among dozens, to represent the images under comparison. Over the years, a great effort has been made to combine multiple features, mainly using early, late, and hierarchical fusion techniques. Unveiling the perfect combination of features is highly domain-specific and dependent on the type of image. Thus, the process of designing a CBIR system for new datasets or domains involves a huge experimentation overhead, leading to multiple fine-tuned CBIR systems. It would be desirable to dynamically find the best combination of CBIR systems without needing to go through such extensive experimentation and without requiring previous domain knowledge. In this paper, we propose ExpertosLF, a model-agnostic interpretable late fusion technique based on online learning with expert advice, which dynamically combines CBIR systems without knowing a priori which ones are the best for a given domain. At each query, ExpertosLF takes advantage of user’s feedback to determine each CBIR contribution in the ensemble for the following queries. ExpertosLF produces an interpretable ensemble that is independent of the dataset and domain. Moreover, ExpertosLF is designed to be modular, and scalable. Experiments on 13 benchmark datasets from the Biomedical, Real, and Sketch domains revealed that: (i) ExpertosLF surpasses the performance of state of the art late-fusion techniques; (ii) it successfully and quickly converges to the performance of the best CBIR sets across domains without any previous domain knowledge (in most cases, fewer than 25 queries need to receive human feedback).

show abstract

Section: Related Workmentioning

confidence: 99%

ExpertosLF: dynamic late fusion of CBIR systems using online learning with relevance feedback

Alarcão

Mendonça

Maruta

et al. 2022

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…In unsupervised and distance-based retrieval, Hoshl et al [12] have shown that histograms can be used as features in image searching. In histogram-based matching methods, distance measurements such as the Bhattacharyya coefficient, L 1 and L 2 norms or X 2 statistics are popular [48]. [6].…”

Section: Related Workmentioning

confidence: 99%

“…This method calculates the similarity in contents between the query and the target images by their histograms. The histogram can be used from color, texture, and shape descriptors [48]. To calculate the identical rate…”

Section: Deep Residual Similaritymentioning

confidence: 99%

Ornament Image Retrieval Using Multimodal Fusion

Sekh¹,

Joardar

Dogra

2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

Search-by-example, i.e. finding images that are similar to a query image, is an indispensable function for various modern image search engines. The applications of such systems are manifold. The primary application of search-by-example is in recommending fashion materials based on user interests. There are various challenges in this area of research such as a large volume of the product database, similar visual appearances, and a large variety of products. The problem becomes more difficult to solve when the product is complex in design such as ornaments. In this paper, we have proposed a fusion-based retrieval model. The method uses weighted average of multiple similarity measures. We have used four different methods namely hash-based, histogram-based, deep feature comparison, and feature cross correlation to find the similarity. A dataset of ornaments (golden earrings) has been prepared and made available to the research community. We achieve 81% top-1 and 89% top-5 accuracy using the proposed method. The dataset and the code is available publicly in https:// github. com/ skari fahmed/ RingF IR.

show abstract

“…Thereafter, simultaneously CDH features have been extracted from obtained edge orientation image and quantized L*a*b image components. Some other color histogram based CBIR schemes have been found in [28], [29] but the histogram based color information is unable to exploit the spatial relationship among the colors (or pixel values). To find the spatial relationship among the pixel values, color autocorrelogram [1] is an alternative solution which overcomes the limitations of the conventional color based approaches.…”

Section: Color Visual Feature Descriptorsmentioning

confidence: 99%

Image Retrieval Scheme Using Quantized Bins of Color Image Components and Adaptive Tetrolet Transform

et al. 2020

View full text Add to dashboard Cite

In this paper, a three stage hierarchical image retrieval scheme using a color, texture and shape visual contents (or descriptors) is proposed, since single visual content is not produce an adequate retrieval results effectively. This scheme has reduced the searching space during the image retrieval process at a certain extent due to the hierarchical mode. In Initial stage, the shape feature descriptor has been computed by simple fusion of histograms of gradients and invariant moments of segmented image planes. The shape based retrieval process has reduced the search space by discarding the non-relevant images from the universal dataset (or original dataset) effectively and kept the retrieved images into the intermediate dataset. In the second stage, the texture feature descriptors have been computed from the intermediate sub-image dataset by applying the adaptive tetrolet transform on image plane of preprocessed HSV color image. This transform provides the multi-resolution images with finer details by employing the tetrominoes and the proper arrangement of tetrominoes contributes the effective local geometry of image plane. The gray level co-occurrence matrix based texture feature descriptor is obtained by computing second order statistical parameters from each decomposed sub-image. At this stage, the most of the irrelevant images are discarded by retrieving the images from intermediate dataset but still some undesired images are left, those will be handled at the last stage. At this stage, fused color information is captured by applying the color autocorrelogram on both the non-uniform quantized color components of the preprocessed HSV color image. Finally, the color feature descriptor produces the desired retrieval results by discarding the irrelevant images from the texture based sub-image dataset. The proposed scheme has also low computational overhead due to the use of three descriptors at different stages separately. The retrieved results show the better accuracy as compared to the other related visual contents based image retrieval schemes.

show abstract

Improving content-based image retrieval for heterogeneous datasets using histogram-based descriptors

Cited by 12 publications

References 41 publications

ExpertosLF: dynamic late fusion of CBIR systems using online learning with relevance feedback

ExpertosLF: dynamic late fusion of CBIR systems using online learning with relevance feedback

Ornament Image Retrieval Using Multimodal Fusion

Image Retrieval Scheme Using Quantized Bins of Color Image Components and Adaptive Tetrolet Transform

Contact Info

Product

Resources

About