A novel fast face recognition algorithm based on multi-dimension neural network model and boundary feature extraction technique

The manuscript addresses the subject of measured learning, which is the learning of a dissimilarity work from an arrangement of similar or dissimilar example pairs. The domain plays an important part in many machine learning applications, for example, those related to face acknowledgment or face retrieval. All the more specifically, themanuscript expands on the late Improved Measure Knowledge (IMK) strategy. Improved Measure Knowledge (IMK) has been appeared to perform exceptionally well for face retrieval tasks, however the algorithm depends on the computation of a weak measured which is extremely tedious. Themanuscript demonstrates how, by bringing scatter into the weak projectors, the meeting time can be decreased up when compared to Improved Measure Knowledge (IMK), with no performance misfortune. The manuscript also acquaints an unequivocal way with control the rank of the so-obtained measurements, allowing settling in advance the measurement of the feature space. The proposed ideas are experimentally validated on a face retrieval task with three unique signatures.

[1]  Peng Li,et al.  Similarity Metric Learning for Face Recognition , 2013, 2013 IEEE International Conference on Computer Vision.

[2]  Jiwen Lu,et al.  Discriminative Deep Metric Learning for Face Verification in the Wild , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Marc Sebban,et al.  Metric Learning , 2015, Metric Learning.

[4]  Frédéric Jurie,et al.  PCCA: A new approach for distance learning from sparse pairwise constraints , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Horst Bischof,et al.  Large scale metric learning from equivalence constraints , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  E. M. Wright,et al.  Adaptive Control Processes: A Guided Tour , 1961, The Mathematical Gazette.

[7]  Frédéric Jurie,et al.  Boosted Metric Learning for Efficient Identity-Based Face Retrieval , 2015, BMVC.

[8]  Lei Wang,et al.  PSDBoost: Matrix-Generation Linear Programming for Positive Semidefinite Matrices Learning , 2008, NIPS.

[9]  Jinbo Bi,et al.  AdaBoost on low-rank PSD matrices for metric learning , 2011, CVPR 2011.

[10]  Cordelia Schmid,et al.  Face recognition from caption-based supervision , 2010 .

[11]  Zoubin Ghahramani,et al.  Unifying linear dimensionality reduction , 2014, 1406.0873.

[12]  Jiwen Lu,et al.  Regularized Bayesian Metric Learning for Person Re-identification , 2014, ECCV Workshops.

[13]  Patrick Pérez,et al.  Some Faces are More Equal than Others: Hierarchical Organization for Accurate and Efficient Large-Scale Identity-Based Face Retrieval , 2014, ECCV Workshops.

[14]  Baba C. Vemuri,et al.  A Robust and Efficient Doubly Regularized Metric Learning Approach , 2012, ECCV.

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Andrew Zisserman,et al.  Deep Face Recognition , 2015, BMVC.

[17]  Gaurav Sharma,et al.  CP-mtML: Coupled Projection Multi-Task Metric Learning for Large Scale Face Retrieval , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  David Picard,et al.  Web-Scale Image Retrieval Using Compact Tensor Aggregation of Visual Descriptors , 2013, IEEE MultiMedia.