Improving Bag of Visual Words Image Retrieval: A Fuzzy Weighting Scheme for Efficient Indexation

Bouachir, Wassim; Kardouchi, Mustapha; Belacel, Nabil

doi:10.1109/sitis.2009.43

Cited by 17 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this regard, five existing image retrieval systems are selected for the comparison purpose namely Vector of Local Aggregated Descriptor (VLAD) for image retrieval [50], Fisher Vector (FV)-based approach [51], Fuzzy Bag-of-Visual-Words model (Fuzzy-BoVW) [61], weighted bag-of-visual-words model [62] and the direct use of local features for retrieval (SIFT) [63]. Table 5 shows the MAP values and the average F 1 scores of various aggregation-based image signatures for the retrieval operation.…”

Section: Retrieval Results and Discussionmentioning

confidence: 99%

Optimizing visual dictionaries for effective image retrieval

Arun

Govindan

2015

Int J Multimed Info Retr

View full text Add to dashboard Cite

Characterizing images by high-level concepts from a learned visual dictionary is extensively used in image classification and retrieval. This paper deals with inferring discriminative visual dictionaries for effective image retrieval and examines a non-negative visual dictionary learning scheme towards this direction. More specifically, a nonnegative matrix factorization framework with 0 -sparseness constraint on the coefficient matrix for optimizing the dictionary is proposed. It is a two-step iterative process composed of sparse encoding and dictionary enhancement stages. An initial estimate of the visual dictionary is updated in each iteration with the proposed 0 -constraint gradient projection algorithm. A desirable attribute of this formulation is an adaptive sequential dictionary initialization procedure. This leads to a sharp drop down of the approximation error and a faster convergence. Finally, the proposed dictionary optimization scheme is used to derive a compact image representation for the retrieval task. A new image signature is obtained by projecting local descriptors on to the basis elements of the optimized visual dictionary and then aggregating the resulting sparse encodings in to a single feature vector. Experimental results on various benchmark datasets show that the proposed system can infer enhanced visual dictionaries and the derived image feature vector can achieve better retrieval results as compared to state-of-the-art techniques.

show abstract

Section: Retrieval Results and Discussionmentioning

confidence: 99%

Optimizing visual dictionaries for effective image retrieval

Arun

Govindan

2015

Int J Multimed Info Retr

View full text Add to dashboard Cite

show abstract

“…Ahmed et al [72] 93.0 BoVW [71] 78.5 txx [73] 61.5 fuzzy weights [74] 80.0 vwa [75] 86.0 BoCIDVW [71] 95.4 NE-C (ours)…”

Section: Proposed Descriptors Mapmentioning

confidence: 99%

Colour Neural Descriptors for Instance Retrieval Using CNN Features and Colour Models

et al. 2021

View full text Add to dashboard Cite

Image representations in the form of neural activations derived from intermediate layers of deep neural networks are the state-of-the-art descriptors for instance based retrieval. However, the problem that persists consists of how to retrieve identical images as the most relevant ones from a large image or video corpus. In this work, we introduce colour neural descriptors that are made of convolutional neural networks (CNN) features obtained by combining different colour spaces and colour channels. In contrast to previous works, which rely on fine-tuning pre-trained networks, we compute the proposed descriptors based on the activations generated from a pretrained VGG-16 network without fine-tuning. Besides, we take advantage of an object detector to optimize our proposed instance retrieval architecture to generate features at both local and global scales. In addition, we introduce a stride based query expansion technique to retrieve objects from multi-view datasets. Finally, we experimentally proved that the proposed colour neural descriptors, obtain state-of-the-art results in Paris 6K, Revisiting-Paris 6k, INSTRE-M and COIL-100 datasets, with mAPs of 81.70, 82.02, 78.8 and 97.9, respectively.

show abstract

“…Each segment is described by a histogram, where the k bins are the visual words and the corresponding values are the weights of the words in the image region. To compute the weight of a visual word of a given region, we apply the fuzzy weighting scheme proposed in [22] and defined by the equation:…”

Section: Creating Signaturesmentioning

confidence: 99%

A bag of words approach for semantic segmentation of monitored scenes

Bouachir

Torabi

Bilodeau

et al. 2016

2016 International Symposium on Signal, Image, Video and Communications (ISIVC)

Self Cite

View full text Add to dashboard Cite

This paper proposes a semantic segmentation method for outdoor scenes captured by a surveillance camera. Our algorithm classifies each perceptually homogenous region as one of the predefined classes learned from a collection of manually labelled images. The proposed approach combines two different types of information. First, color segmentation is performed to divide the scene into perceptually similar regions. Then, the second step is based on SIFT keypoints and uses the bag of words representation of the regions for the classification. The prediction is done using a Naïve Bayesian Network as a generative classifier. Compared to existing techniques, our method provides more compact representations of scene contents and the segmentation result is more consistent with human perception due to the combination of the color information with the image keypoints. The experiments conducted on a publicly available data set demonstrate the validity of the proposed method.

show abstract

Improving Bag of Visual Words Image Retrieval: A Fuzzy Weighting Scheme for Efficient Indexation

Cited by 17 publications

References 17 publications

Optimizing visual dictionaries for effective image retrieval

Optimizing visual dictionaries for effective image retrieval

Colour Neural Descriptors for Instance Retrieval Using CNN Features and Colour Models

A bag of words approach for semantic segmentation of monitored scenes

Contact Info

Product

Resources

About