A Hierarchical Face Recognition Method Based on Local Binary Pattern

A Hierarchical Face Recognition Method Based on Local Binary Pattern

A Hierarchical Face Recognition Method Based on Local Binary Pattern

 

Abstract

This paper proposes a hierarchical method to deal with the multi-pose face recognition problem. The Local Binary Pattern (LBP) feature is used as the uniform feature throughout the two-hierarchy process. Also, a new method, named Multi-expert Intelligent Decision System, is proposed to improve the performance of the pose estimation
process. According to the experiments, the method is proved to be efficient and robust. Key words: Hierarchical Face Recognition, Local Binary Pattern, Multi-expert Intelligent Decision System, Facial Pose Estimation.

 


Image result for A Hierarchical Face Recognition Method Based on Local Binary Pattern


What we provide:

  • Complete Research Assistance

Technology Involved:-

  • MATLAB, Simulink, MATPOWER, GRIDLAB-D,OpenDSS, ETAP, GAMS

Deliverables:-  

  • Complete Code of this paper
  • Complete Code of the approach to be propose
  • A document containing complete explanation of code and research approach
  • All materials used for this research
  • Solution to all your queries related to your work

 

Hyperspectral Image Classification Using Metric Learning in One-Dimensional Embedding Framework

Hyperspectral Image Classification Using Metric Learning in One-Dimensional Embedding Framework

Hyperspectral Image Classification Using Metric Learning in One-Dimensional Embedding Framework

Abstract:

Hyperspectral image (HSI) classification has become an active research area in the remote sensing field. In order to construct a simple and reliable classifier, learning an adequate distance metric from a given HSI dataset is still a critical and challenging task in many HSI applications. In this paper, a novel distance metric learning (DML) framework based on 1-D manifold embedding (1DME), named DL1DME, is proposed for HSI classification. The 1DME framework was developed by using the recently developed smooth ordering technique. This framework enables us to elaborately exploit the benefits of DML in the development of the 1DME algorithm. The core of the state-of-the-art DML is to learn a Mahalanobis matrix from the given dataset that better describes the similarity between pixels. Largest margin nearest neighbors (LMNN) and information theoretic metric learning (ITML) are employed for the Mahalanobis matrix learning. Then, based on the affinity defined by the Mahalanobis matrix, the preclassifiers are constructed using the simple 1-D regularization on 1DME; and they predict the labels of the test data. By a voting rule, the pixels labeled in the same class by most of the preclassifiers are voted into the confidently predicted set, which are then merged with the current labeled set. The labeled set enlargement process is repeated if the original one has a very small size. The final classifier is then constructed in the 1DME framework again, but based on the enlarged labeled set. According to the aforementioned strategy, two novel DML-based 1DME classification algorithms, DL1DME-LMNN and DL1DME-ITML, are developed in this paper. Experimental results on three popular real-world HSIs demonstrate that the classification performance of the proposed DL1DME is superior to other most popular SSL methods in terms of classification accuracies.
Date of Publication: 15 February 2017
ISSN Information:
INSPEC Accession Number: 16808795
Publisher: IEEE

What we provide:

Complete Research Assistance

Technology Involved:-

MATLAB, Simulink, MATPOWER, GRIDLAB-D,OpenDSS, ETAP, GAMS

Deliverables:-  

  • Complete Code of this paper
  • Complete Code of the approach to be propose
  • A document containing complete explanation of code and research approach
  • All materials used for this research
  • Solution to all your queries related to your work

An efficient BTC image compression technique

An efficient BTC image compression technique

An efficient BTC image compression technique

Abstract:

This paper presents a moment preserving and visual information dominance technique to achieve the low-bit rate block truncation coding (BTC). Compared with other existing strategies as transform coding and vector quantization, conventional BTC compression has the advantage of simple and fast computation. Nevertheless the compression ratio is limited by its low efficiency. Our proposed technique accomplishes the goal of simple computation with variable bit rate selection by the moment preservation and information extraction algorithm. The proposed technique has the advantage of simple operations and it does not require complicated mathematical computations. Thus, the overall computation does not increase the burden compared with ordinary BTC. The simulations are carried with natural images to evaluate the performance. The generated decoded images have moderate quality with a bit rate of 0.5-1.0 bit/pixel.
Published in: IEEE Transactions on Consumer Electronics ( Volume: 44, Issue: 2, May 1998 )
Date of Publication: 06 August 2002
Print ISSN: 0098-3063
INSPEC Accession Number: 5942302
Publisher: IEEE

What we provide:

Complete Research Assistance

Technology Involved:-

MATLAB, Simulink, MATPOWER, GRIDLAB-D,OpenDSS, ETAP, GAMS

Deliverables:-  

  • Complete Code of this paper
  • Complete Code of the approach to be propose
  • A document containing complete explanation of code and research approach
  • All materials used for this research
  • Solution to all your queries related to your work