Content-Based Image Retrieval Using Moments of Local Ternary Pattern

Abstract

Due to the availability of large number of digital images, development of an efficient content-based indexing and retrieval method is required. Also, the emergence of smartphones and modern PDAs has further substantiated the need of such systems. This paper proposes a combination of Local Ternary Pattern (LTP) and moments for Content-Based Image Retrieval. Image is divided into blocks of equal size and LTP codes of each block are computed. Geometric moments of LTP codes of each block are computed followed by computation of distance between moments of LTP codes of query and database images. Then, the threshold using distance values is applied to retrieve images similar to the query image. Performance of the proposed method is compared with other state-of-the-art methods on the basis of results obtained on Corel-1,000 database. The comparison shows that the proposed method gives better results in terms of precision and recall as compared to other state-of-the-art image retrieval methods.

An efficient content based image retrieval using enhanced multi-trend structure descriptor

“…Recently, SIFT and center symmetric LBP is combined by Heikkilä et al [28] in which intensity of center symmetric pixels are only considered. Along this direction, center-symmetric local ternary patterns (CS-LTP) is introduced by Gupta et al [29]; Local tetra pattern (LTrP) is introduced by Murula et al [30] to define the structural formation of local level structure by including all the four directions for center pixel; directional binary wavelet pattern is reported in Murala et al [30] for biomedical image indexing and retrieval; co-occurrence of similar ternary edges are encoded for CT and MRI image retrieval using the local ternary co-occurrence patterns (LTCoP) and is suggested in Murala and Wu [31]; Local ternary pattern is described in Srivastava et al [32]; Local mesh pattern (LMeP) and Local bit-plane decoded pattern for medical image retrieval is presented in Murala and Jonathan [33] and Dubey et al [34] respectively; Dubey et al [35,36] described Local diagonal extrema pattern and Local wavelet pattern for CT image retrieval; Local quantized extrema pattern (LQEP) is introduced by Rao and Rao [37] for natural and texture image retrieval which captures the spatial relation between any pair of neighbors in a local region along the directions 0°, 45°, 90° and 135° for a given center pixel in an image; Directional local ternary quantized extrema pattern (DLTerQEP) is suggested in Deep et al [38] for CT and MRI image retrieval and it captures more spatial structure information by adopting ternary patterns from horizontal, vertical, diagonal, antidiagonal structure of directional local extrema values of an image.…”

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

“…The comparative test results with recognized techniques are given in Table 6. The proposed algorithm provides better result than all of the identified state-of-the-art methods given by Xia et al [48], Srivastava et al [73,77], Pardede et al [79], Zhou et al [69], Liu and Yang [84], and Srivastava and Khare [78] except MS-LBP (7 × 7) + GLCM [49]. The ARP of the proposed method and MS-LBP (7×7) + GLCM [49] demonstrated with bold text as shown in Table 6.…”

“…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.…”

Adaptive Content-Based Medical Image Retrieval Based On Local Features Extraction In Shearlet Domain

“…Recall (%) CBIR using moments [14] 61.232 78.753 Gabor histogram [15] 65.451 78.863 Color histogram [15] 66.121 79.539 CBIR using moments of local ternary pattern [12] 68 in table 1, table 2, table 3 and other experiments, the results of the proposed method are better than the other methods as shown in the table 3.…”