Adaptive content based image retrieval based on RICE algorithm selection model

Hamreras, Safa; Boucheham, Bachir

doi:10.1109/isps.2018.8379022

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be seen that the proposed work performs better than the identified existing approaches. The [74] Gabor Histogram 41.30 Yu et al [75] Image-based HOG-LBP 46.00 Deselaers et al [74] LF-SIFT Histogram 48.20 Hamreras and Bucheham [76] RICE Algorithm selection model 49.72 Deselaers et al [74] Color histogram 50.50 Srivastava et al [77] Moments of LTP 53.70 Kumar and Nagarajan [51] LCP 78.30 Mohiuddin et al [68] CCV + LBP 82.52 Srivastava and Khare [78] DWT + SURF + GLCM 84.97 Pardede et al [79] Low-level features + relevance feedback 85.59 Srivastava and Khare [49] MS-LBP (7 Thus, the proposed technique surpasses over the literature of Xia et al [48], Srivastava et al [73,77,80], Vipparthi and Nagar [52], Srivastava and Khare [49], Zhou et al [69], Verma et al [81], Zhou et al [71], and Mohiuddin et al [68], as shown in Table 4.…”

Section: Performance On Corel-5kmentioning

confidence: 99%

Hybrid Approach to Content-Based Image Retrieval Using Modified Multi-Scale LBP and Color Features

Chavda

Goyani

2020

SN COMPUT. SCI.

View full text Add to dashboard Cite

The objective of the content-based image retrieval (CBIR) system is to retrieve the visually identical images from the database efficiently and effectively. It is a broad research realm with the availability of numerous applications. Performance dependence of CBIR focuses on the extraction, reduction, and selection of the features along with the practice of classification technique. In this work, we have proposed the hybrid approach of two different feature descriptors: global color histogram and multi-scale local binary pattern (MS-LBP); furthermore, the use of PCA for dimension reduction and LDA for the selection of features. The proposed method is evaluated concerning various benchmark datasets, viz., Corel-1k, Corel-5k, Corel-10k, and Ghim-10k together with result comparison based on the precision and recall values at different thresholds. The classification purposes are satisfied with Euclidean and City Block distance. The performance study of the proposed work displays it as outperformer than the identified state-of-the-art literature.

show abstract