Pruning SIFT & SURF for Efficient Clustering of Near-duplicate Images

doi:10.1109/ICASSP.2019.8683078

Home
/
Papers
/
Pruning SIFT & SURF for Efficient Clustering of Near-duplicate Images

Proceedings Article•DOI•

Pruning SIFT & SURF for Efficient Clustering of Near-duplicate Images

Tushar Shankar Shinde¹, Anil Kumar Tiwari¹•Institutions (1)

Indian Institute of Technology, Jodhpur¹

09 May 2019-pp 3132-3136

TL;DR: A simple approach to reduce the cardinality of keypoint set and prune the dimension of SIFT and SURF feature descriptors for efficient image clustering is proposed, and clustering accuracy is found to be at par with traditional SIFTand SURF with a significant reduction in computational cost.

read less

Abstract: Clustering and categorization of similar images using SIFT and SURF require a high computational cost. In this paper, a simple approach to reduce the cardinality of keypoint set and prune the dimension of SIFT and SURF feature descriptors for efficient image clustering is proposed. For this purpose, sparsely spaced (uniformly distributed) important keypoints are chosen. In addition, multiple reduced dimensional variants of SIFT and SURF descriptors are presented. Moreover, clustering time complexity is also improved by proposed contextual bag-of-features approach for partitioned keypoint set. The F-measure statistic is used to evaluate clustering performance on a California-ND dataset containing near-duplicate images. Clustering accuracy of the proposed pruned SIFT and SURF is found to be at par with traditional SIFT and SURF with a significant reduction in computational cost.

...read moreread less

Citations

PDF

Open Access

More filters

Proceedings Article•DOI•

Efficient Image Set Compression

[...]

Tushar Shankar Shinde¹•Institutions (1)

Indian Institutes of Technology¹

01 Sep 2019

TL;DR: This thesis proposes approaches for efficient clustering, fast direction oriented motion estimation algorithm, and an image reordering scheme with minimum predictive costs for better compression of near-duplicate image collection.

...read moreread less

Abstract: The explosion of digital photos has posed a challenge for storage and transmission bandwidth. The thesis briefly discusses my work on efficient image set compression. The lossless compression of near-duplicate image collection is carried out using multiple steps, where each step is computationally demanding. My task is to make them work faster without compromising on compression efficiency. In this pursuit, we propose approaches for efficient clustering, fast direction oriented motion estimation algorithm, and an image reordering scheme with minimum predictive costs for better compression. The preliminary results for the proposed approach are promising. We also aim to extend our approach to hyperspectral and medical image set compression.

...read moreread less

10 citations

Cites background from "Pruning SIFT & SURF for Efficient C..."

...The preliminary clustering results on the publicly available California-ND dataset containing nearduplicate images have been promising (see [7])....
[...]

Proceedings Article•DOI•

Local Image Feature Extraction using Stacked-Autoencoder in the Bag-of-Visual Word modelling of Images

[...]

Abass A. Olaode¹, Golshah Naghdy¹•Institutions (1)

University of Wollongong¹

01 Dec 2019

TL;DR: The proposed Bag-of-Visual Word Modelling in which Image Feature Extraction is achieved using Deep Feature Learning via Stacked-Autoencoder is tested and the ability of deep feature learning to yield optimum image categorisation performance is confirmed.

...read moreread less

Abstract: The Bag-of-Visual Words has been recognised as an effective mean of representing images for image classification. However, its reliance on hand crafted image feature extraction algorithms often results in significant computational overhead, and poor classification accuracies. Therefore, this paper presents a Bag-of-Visual Word Modelling in which Image Feature Extraction is achieved using Deep Feature Learning via Stacked-Autoencoder. The proposed method is tested using three image collections constituted from the Caltech 101 image collection and the results confirm the ability of deep feature learning to yield optimum image categorisation performance.

...read moreread less

4 citations

Journal Article•DOI•

Adaptive bag-of-visual word modelling using stacked-autoencoder and particle swarm optimisation for the unsupervised categorisation of images

[...]

Abass A. Olaode, Golshah Naghdy

01 Jul 2020-Iet Image Processing

TL;DR: This study presents an adaptive BOVW modelling, in which image feature extraction is achieved using deep feature learning and the amount of computation required for the development of visual codebook is minimised using a batch implementation of particle swarm optimisation.

...read moreread less

Abstract: The bag-of-visual words (BOVWs) have been recognised as an effective mean of representing images for image classification. However, its reliance on a visual codebook developed using handcrafted image feature extraction algorithms and vector quantisation via k -means clustering often results in significant computational overhead, and poor classification accuracies. Therefore, this study presents an adaptive BOVW modelling, in which image feature extraction is achieved using deep feature learning and the amount of computation required for the development of visual codebook is minimised using a batch implementation of particle swarm optimisation. The proposed method is tested using Caltech-101 image dataset, and the results confirm the suitability of the proposed method in improving the categorisation performance while reducing the computational load.

...read moreread less

3 citations

Cites background from "Pruning SIFT & SURF for Efficient C..."

...Although compared to SIFT and SURF, the image features generated for any given image collection with the Stacked-Autoencoder is considerably less, when the image collection is large, the number of image features generated using Stacked Autoencoder may still be numerous enough to cause lengthy computation during the implementation of the PSO clustering [59]....
[...]
...In [8] the authors demonstrated that the opportunity to change the number of layers and the number of neurons in each layer of a Deep Learning algorithm allows the feature extraction process to be adaptable to the content diversity of the image collection during BOVW modelling, thus generating image feature vectors whose dimension guarantees optimum discrimination, unlike the fixed 128 dimensions of Scale Invariant Feature Transform (SIFT) and 64 dimensions of Speeded-Up Robust Feature (SURF) [57, 58, 59]....
[...]
...An important advantage of the application of Deep Feature learning at this stage is the opportunity to control the number of image features to be collected from each image in the collection to be processed thus avoiding excessive computational overhead, commonly associated with sparse image features such as SIFT or SURF where the number of image features per image is not predetermined or in Dense-SIFT where the number of features per image can be more than 10,000 with no means of controlling the number of image features....
[...]
...Although the time taken is higher than the time taken to complete the unsupervised categorisation with SURF features due to the time taken to train the Stacked-Autoencoder, the higher accuracy recorded by Stacked Autoencoder confirms its better efficiency....
[...]

References

PDF

Open Access

More filters

Proceedings Article•DOI•

SIFT and SURF Performance Evaluation against Various Image Deformations on Benchmark Dataset

[...]

Nabeel Younus Khan¹, Brendan McCane¹, Geoff Wyvill¹•Institutions (1)

University of Otago¹

06 Dec 2011

TL;DR: This paper summarizes the performance of two robust feature detection algorithms namely Scale Invariant Feature Transform (SIFT) and Speeded up Robust Features (SURF) on several classification datasets.

...read moreread less

Abstract: Scene classification in indoor and outdoor environments is a fundamental problem to the vision and robotics community. Scene classification benefits from image features which are invariant to image transformations such as rotation, illumination, scale, viewpoint, noise etc. Selecting suitable features that exhibit such invariances plays a key part in classification performance. This paper summarizes the performance of two robust feature detection algorithms namely Scale Invariant Feature Transform (SIFT) and Speeded up Robust Features (SURF) on several classification datasets. In this paper, we have proposed three shorter SIFT descriptors. Results show that the proposed 64D and 96D SIFT descriptors perform as well as traditional 128D SIFT descriptors for image matching at a significantly reduced computational cost. SURF has also been observed to give good classification results on different datasets.

...read moreread less

163 citations

"Pruning SIFT & SURF for Efficient C..." refers background in this paper

...Many researchers have reduced the dimension of the SIFT descriptor [12, 13]....
[...]

Proceedings Article•

Pruning SIFT for scalable near-duplicate image matching

[...]

Jun Jie Foo¹, Ranjan Sinha¹•Institutions (1)

RMIT University¹

30 Mar 2007

TL;DR: This work shows that for this application domain, the SIFT interest points can be dramatically pruned to effect large reductions in both memory requirements and query run-time, with almost negligible loss in effectiveness.

...read moreread less

Abstract: The detection of image versions from large image collections is a formidable task as two images are rarely identical. Geometric variations such as cropping, rotation, and slight photometric alteration are unsuitable for content-based retrieval techniques, whereas digital watermarking techniques have limited application for practical retrieval. Recently, the application of Scale Invariant Feature Transform (SIFT) interest points to this domain have shown high effectiveness, but scalability remains a problem due to the large number of features generated for each image. In this work, we show that for this application domain, the SIFT interest points can be dramatically pruned to effect large reductions in both memory requirements and query run-time, with almost negligible loss in effectiveness. We demonstrate that, unlike using the original SIFT features, the pruned features scales better for collections containing hundreds of thousands of images.

...read moreread less

74 citations

"Pruning SIFT & SURF for Efficient C..." refers background in this paper

...Moreover, the cardinality of the keypoint set can be reduced by raising the keypoint inclusion threshold value [11]....
[...]
...In general, the cardinality of keypoint set is in the order of 10(3) to 10(4) (depends on image size and content) [11]....
[...]

Proceedings Article•DOI•

Clustering near-duplicate images in large collections

[...]

Jun Jie Foo¹, Justin Zobel¹, Ranjan Sinha²•Institutions (2)

RMIT University¹, University of Melbourne²

24 Sep 2007

TL;DR: It is demonstrated that this clustering approach is highly effective for collections of up to a few hundred thousand images and presents a viable solution for clustering near-duplicate images on the Web.

...read moreread less

Abstract: Near-duplicate images introduce problems of redundancy and copyright infringement in large image collections. The problem is acute on the web, where appropriation of images without acknowledgment of source is prevalent. In this paper, we present an effective clustering approach for near-duplicate images, using a combination of techniques from invariant image local descriptors and an adaptation of near-duplicate text-document clustering techniques; we extend our earlier approach of near-duplicate image pairwise identification for this clustering approach. We demonstrate that our clustering approach is highly effective for collections of up to a few hundred thousand images. We also show --- via experimentation with real examples --- that ourapproach presents a viable solution for clustering near-duplicate images on the Web.

...read moreread less

43 citations

"Pruning SIFT & SURF for Efficient C..." refers methods in this paper

...The list of alterations similar to that of the works in [22] is described in Table 2....
[...]

Proceedings Article•DOI•

California-ND: An annotated dataset for near-duplicate detection in personal photo collections

[...]

Amornched Jinda-Apiraksa, Vassilios Vonikakis, Stefan Winkler

03 Jul 2013

TL;DR: A new dataset that may assist researchers in testing algorithms for the detection of near-duplicates in personal photo libraries is presented, derived directly from an actual personal travel photo collection.

...read moreread less

Abstract: Managing photo collections involves a variety of image quality assessment tasks, e.g. the selection of the “best” photos. Detecting near-duplicate images is a prerequisite for automating these tasks. This paper presents a new dataset that may assist researchers in testing algorithms for the detection of near-duplicates in personal photo libraries. The proposed dataset is derived directly from an actual personal travel photo collection. It contains many difficult cases and types of near-duplicates. More importantly, in order to deal with the inevitable ambiguity that the near-duplicate cases exhibit, the dataset is annotated by 10 different subjects. These annotations are combined into a non-binary ground truth, which indicates the probability that a pair of images may be considered a near-duplicate by an observer.

...read moreread less

36 citations

"Pruning SIFT & SURF for Efficient C..." refers background in this paper

...near-duplicate images (with slightly varying viewpoints) resulting in total 150 photos are chosen from California-ND dataset [21]....
[...]

Journal Article•DOI•

Well-distributed SIFT features

[...]

Rachel Song¹, Janusz Szymanski¹•Institutions (1)

University of York¹

12 Mar 2009-Electronics Letters

TL;DR: In this paper, a method to enhance the recognition of spatially distributed features based on the scale invariant feature transform (SIFT) is reported, where the key idea is to modify the way in which the selection of a set of contender interest points from each input image is carried out, using a non-maximal suppression approach in different scale spaces.

...read moreread less

Abstract: A method to enhance the recognition of spatially distributed features, based on the scale invariant feature transform (SIFT), is reported. The key idea is to modify the way in which the selection of a set of contender interest points from each input image is carried out, using a non-maximal suppression approach in the different scale spaces.

...read moreread less

20 citations