Local curve pattern for content-based image retrieval

Kumar, T. Ganesh; Nagarajan, V.

doi:10.1007/s10044-018-0724-1

Cited by 10 publications

(5 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spatial patterns like LBP [44], LDP [45], LTP [46], and LTrP [47] are still famous in the area of CBIR. Some of the spatial patterns are multi-scale local binary Patterns (MS-LBP) [48,49], local smoothness patterns (LSP) [50], local curve patterns (LCP) [51], color directional local quinary patterns (CDLQP) [52], and so many more. The main reason that these approaches became popular and successful is their easiness of feature extraction stage and supremacy on the feature classification performance.…”

Section: Traditional Retrieval Practicesmentioning

confidence: 99%

“…It performs better than LBP [44] as per the results of the paper shows. Later on, they also introduced the local curve pattern (LCP) in their further work of texture description in another literature [51]. LCP technique uses image line/curve characteristics to derive the local patterns.…”

Section: Traditional Retrieval Practicesmentioning

confidence: 99%

“…LBP operator does not consider directions for achieving the intensity value of center pixel, it only considers the magnitude of the neighborhood pixel intensities. So that, it is the main issue related to the LBP operator which led us to other spatial patterns like LDP [45], LTP [46], LTrp [47], MS-LBP [48,49], LSP [50], LMQEP [53], LCP [51], etc.…”

Section: Traditional Retrieval Practicesmentioning

confidence: 99%

“…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%

“…Fig. 9 Average retrieval rate on Corel-10k [80] Moments of wavelet transform 22.35 Srivastava et al [77] Moments of LTP 24.92 Verma and Raman [82] CSLBP + LNDP 36.21 Murala et al [47] LTrP 36.30 Pardede et al [79] Low-level features + relevance feedback 37.16 Dubey et al [83] BOF of LBP 39.20 Verma and Raman [82] DLEP + LNDP 40.49 Verma and Raman [82] LTrP + LNDP 41.11 Verma and Raman [82] LBP + LNDP 42.81 Kumar and Nagarajan [51] LCP (80 categories) 43.10 Liu and Yang [84] CDH 45.24 Srivastava et al [49] MS-LBP (7 × 7) + GLCM 48.69 Zhou et al [69] CH + LDP 51.91 Zhao et al [85] Multi-trend structure descriptor 51.95 Proposed method 54.46…”

Section: Performance On Ghim-10kmentioning

confidence: 99%

See 4 more Smart Citations

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