A Distributed CBIR System Based on Improved SURF on Apache Spark

Huang, Taiwen; Yu, Zhihao; Lin, Xiao; Jiang, Linhua; Zhao, Dongfang

doi:10.1007/978-981-10-6451-7_18

Cited by 2 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to BRISK, the SURF's feature point identification is a Hessian matrix based. SURF detects the keypoint feature and greatly speeds up computation by locating the Hessian matrix local maximum determinant and using the integral image [17]. The point X=(x,y) in the image's Hessian matrix is defined as follows on the scale σ:…”

Section: Speeded-up Robust Featuresmentioning

confidence: 99%

“…By creating concentric circles with varying radii around the feature point as the center, N sampling points are obtained through evenly spaced sampling on each circle. Gaussian filtering is then applied to the sample points of the concentric circles to avoid aliasing problems, as stated in [17]. As there are N sample points, these points are merged to form N(N-1)/2 point pairs, which are represented by a set A using Equation (3).…”

Section: Binary Robust Invariant Scalable Keypointmentioning

confidence: 99%

See 1 more Smart Citation

Content-Based Image Retrieval Using BRISK and SURF as Bag-of-Visual-Words for Naïve Bayes Classifier

Bakheet¹,

Mofaddel²,

Soliman³

et al. 2023

Sohag Journal of Sciences

View full text Add to dashboard Cite

For Content-Based Image Retrieval (CBIR) systems, there are numerous ways. However, the results from the single feature kind are not sufficient. In this paper, The Adaptive Feature Fusion for the Naïve Bayes classifier (AFF-NB) framework is proposed. The local features are constructed from the fuse of the Binary Robust Invariant Scalable (BRISK) and the Speeded-Up Robust Features (SURF) detectors. The local features are then adaptively fused. The Gaussian Mixture Models (GMM) clustering algorithm clusters the extracted features to build a visual words codebook. Then a feature, quantization algorithm via the Cosine Distance Matrix (CDM) is applied to construct the Bag-of-Visual-Words (BoVW). To minimize the risk of data overfitting, the BoVW is normalized. The retrieved images are sorted according to how closely they resemble the query image using an inverted index strategy based on the CDM. The results demonstrate that the suggested technique increases CBIR accuracy to 96.8% on the commonly used Caltech-10 dataset.

show abstract

Section: Speeded-up Robust Featuresmentioning

confidence: 99%

Section: Binary Robust Invariant Scalable Keypointmentioning

confidence: 99%