Evolutionary granular approach for recognizing faces altered due to plastic surgery
Citations
26 citations
22 citations
Cites background from "Evolutionary granular approach for ..."
...proposed an evolutionary granular approach to extract discriminative information from non-disjoint face granules [3]....
[...]
16 citations
Cites methods from "Evolutionary granular approach for ..."
...[6] proposed an evolutionary algorithm to compute optimal weights for face granules during the face matching process....
[...]
15 citations
Cites methods from "Evolutionary granular approach for ..."
...[9] adopted an evolutionary three-level granular approach with speeded up robust features (SURF) and CLBP features towards processing tessellated facial images....
[...]
12 citations
Cites background or methods from "Evolutionary granular approach for ..."
...[24,25], global surgeries like rhytidectomy severely impacted on their recognition algorithm....
[...]
...Face recognition performance in plastic surgery scenarios for cases such as rhytidectomy (face and mid-face lift), rhinoplasty (nose reshaping), blepharoplasty (eye surgery), otoplasty (ear surgery), browlift, dermabrasion, and skin peeling has been investigated [2,22-24,35-38]....
[...]
...[24,25] adopted non-disjoint face granulation approach where the granules are obtained from HE-normalized images....
[...]
...In other words, rhytidectomy is an embodiment of local and global appearance-changing surgery procedures, which may explain the challenges that the existing intensity-based recognition methods in the case of rhytidectomy [2] and subsequent works [22-25] faced....
[...]
References
52,797 citations
14,245 citations
"Evolutionary granular approach for ..." refers background or methods in this paper
...CLBP can be further extended to Uniform CLBP [13] to achieve robustness to rotation variations and dimensionality reduction....
[...]
...Further, two feature extractors, namely Uniform Circular Local Binary Pattern (UCLBP) [13] and Speeded Up Robust Features (SURF) [6], are used for extracting discriminating information from face granules....
[...]
...Circular local binary pattern (CLBP) [3], [13] is a feature extractor where the texture descriptor is computed based on the neighboring pixels that are well separated on a circle around the central pixel....
[...]
...1) Uniform Circular Local Binary Patterns: Local binary pattern based descriptor [3], [13] is a widely used texture operator because of its robustness to gray level changes and high computational efficiency....
[...]
...Uniform CLBP is described using Equations 5 and 6....
[...]
13,011 citations
"Evolutionary granular approach for ..." refers background or methods in this paper
...Further, two feature extractors, namely Uniform Circular Local Binary Pattern (UCLBP) [13] and Speeded Up Robust Features (SURF) [6], are used for extracting discriminating information from face granules....
[...]
...2) Speeded Up Robust Features: SURF is a scale and rotation invariant descriptor [6], [9] that generates a compact representation of an image based on the spatial distribution of gradient information around the interest points....
[...]
...∙ Performance of SURF [6], [9], on the other hand, reduces when applied on face granules....
[...]
5,563 citations
"Evolutionary granular approach for ..." refers background or methods in this paper
...1) Uniform Circular Local Binary Patterns: Local binary pattern based descriptor [3], [13] is a widely used texture operator because of its robustness to gray level changes and high computational efficiency....
[...]
...2) For assigning weights to each face granule, a chromosome with weights proportional to the identification accuracy of each face granule (as proposed by Ahonen [3]) is used as the initial chromosome....
[...]
...Circular local binary pattern (CLBP) [3], [13] is a feature extractor where the texture descriptor is computed based on the neighboring pixels that are well separated on a circle around the central pixel....
[...]
4,816 citations
"Evolutionary granular approach for ..." refers methods in this paper
...from the CMU-PIE database [16], 661 subjects from the FERET database [14], 36 subjects from the Georgia Tech database [1] and 23 subjects from the GTAV database [2]....
[...]