Multi-Level Search Space Reduction Framework for Face Image Database

2015 ◽  
Vol 11 (1) ◽  
pp. 12-29 ◽  
Author(s):  
C. Sweetlin Hemalatha ◽  
V. Vaidehi ◽  
K. Nithya ◽  
A. Annis Fathima ◽  
M. Visalakshi ◽  
...  
Keyword(s):  
Face Recognition ◽  
Large Scale ◽  
Search Time ◽  
Image Database ◽  
Search Space ◽  
Face Image ◽  
Tree Model ◽  
Space Reduction ◽  
Search Space Reduction ◽  
Multi Level

In face recognition, searching and retrieval of relevant images from a large database form a major task. Recognition time is greatly related to the dimensionality of the original data and the number of training samples. This demands the selection of discriminant features that produce similar results as the entire set and a reduced search space. To address this issue, a Multi-Level Search Space Reduction framework for large scale face image database is proposed. The proposed approach identifies discriminating features and groups face images sharing similar properties using feature-weighted Fuzzy C-Means approach. A hierarchical tree model is then constructed inside every cluster based on the discriminating features which enables a branch based selection, thereby reducing the search space. The proposed framework is tested on three benchmark and two self-created databases. The experimental results show that the proposed method achieved an average accuracy of 93% and an average search time reduction of 66% compared to existing approaches for search space reduction of face recognition.

Symmetric Uncertainty Based Search Space Reduction for Fast Face Recognition

2018 ◽  
Vol 14 (4) ◽  
pp. 77-97
Author(s):  
C. Sweetlin Hemalatha ◽  
Vignesh Sankaran ◽  
Vaidehi V ◽  
Shree Nandhini S ◽  
Sharmi P ◽  
...  
Keyword(s):  
Face Recognition ◽  
Search Time ◽  
Search Space ◽  
Feature Subset Selection ◽  
Feature Subset ◽  
Space Reduction ◽  
Search Space Reduction ◽  
Fuzzy C Means Clustering ◽  
Face Datasets ◽  
Synthetic Datasets

Face recognition from a large video database involves more search time. This article proposes a symmetric uncertainty based search space reduction (SUSSR) methodology that facilitates faster face recognition in video, making it viable for real time surveillance and authentication applications. The proposed methodology employs symmetric uncertainty based feature subset selection to obtain significant features. Further, Fuzzy C-Means clustering is applied to restrict the search to nearest possible cluster, thus speeding up the recognition process. Kullback Leibler's divergence based similarity measure is employed to recognize the query face in video by matching the query frame with that of stored features in the database. The proposed search space reduction methodology is tested upon benchmark video face datasets namely FJU, YouTube celebrities and synthetic datasets namely MIT-Dataset-I and MIT-Dataset-II. Experimental results demonstrate the effectiveness of the proposed methodology with a 10 increase in recognition accuracy and 35 reduction in recognition time.

Search Space Reduction in Biometric Databases

2017 ◽  
pp. 236-262 ◽  
Author(s):  
Ilaiah Kavati ◽  
Munaga V. N. K. Prasad ◽  
Chakravarthy Bhagvati
Keyword(s):  
Response Time ◽  
Large Scale ◽  
Search Space ◽  
Comprehensive Review ◽  
Space Reduction ◽  
Reduction Techniques ◽  
Search Space Reduction ◽  
Search Speed ◽  
Personal Recognition ◽  
Real Time Applications

Deployment of biometrics for personal recognition in various real time applications lead to large scale databases. Identification of an individual on such large biometric databases using a one-one matching (i.e., exhaustive search) increases the response time of the system. Reducing the search space during identification increases the search speed and reduces the response time of the system. This chapter presents a comprehensive review of the current developments of the search space reduction techniques in biometric databases. Search space reduction techniques for the fingerprint databases are categorized into classification and indexing approaches. For the palmprint, the current search space reduction techniques are classified as hierarchical matching, classification and indexing approaches. Likewise, the iris indexing approaches are classified as texture based and color based techniques.

Search Space Reduction in Biometric Databases

2018 ◽  
pp. 1600-1626 ◽  
Author(s):  
Ilaiah Kavati ◽  
Munaga V. N. K. Prasad ◽  
Chakravarthy Bhagvati
Keyword(s):  
Response Time ◽  
Large Scale ◽  
Search Space ◽  
Comprehensive Review ◽  
Space Reduction ◽  
Reduction Techniques ◽  
Search Space Reduction ◽  
Search Speed ◽  
Personal Recognition ◽  
Real Time Applications

Deployment of biometrics for personal recognition in various real time applications lead to large scale databases. Identification of an individual on such large biometric databases using a one-one matching (i.e., exhaustive search) increases the response time of the system. Reducing the search space during identification increases the search speed and reduces the response time of the system. This chapter presents a comprehensive review of the current developments of the search space reduction techniques in biometric databases. Search space reduction techniques for the fingerprint databases are categorized into classification and indexing approaches. For the palmprint, the current search space reduction techniques are classified as hierarchical matching, classification and indexing approaches. Likewise, the iris indexing approaches are classified as texture based and color based techniques.

A Search Space Reduction Method for Optimizing Sequential Control by Hypothetically Achievable Bound Estimation of the Objective Function

2016 ◽  
Author(s):  
Yuya Tokuda ◽  
Yasuhiro Yoshida ◽  
Takaaki Sekiai ◽  
Kazunori Yamanaka ◽  
Atsushi Yamashita ◽  
...  
Keyword(s):  
Objective Function ◽  
Large Scale ◽  
Reduction Method ◽  
Search Space ◽  
The State ◽  
Space Reduction ◽  
Sequential Control ◽  
Metaheuristic Methods ◽  
Search Space Reduction ◽  
State Of The Environment

Metaheuristic methods such as genetic algorithm, simulated annealing, and artificial bee colony algorithm methods take much time to obtain an optimal solution, particularly when a large scale simulator is employed for estimating the state of the environment. In this paper, a search space reduction method for accelerating the optimization of sequential control systems is proposed. The proposed method estimates a hypothetical achievable bound of the objective function and uses it as the prior knowledge to reduce the search space. The hypothetical achievable bound is estimated using the fact that large scale plants consisting of multiple components are in many cases controlled in a sequential manner. The size of the search space reduction obtained by the proposed method is evaluated by an example problem that minimizes the start-up time of a thermal power plant. As a result, the size of the search space is reduced by 65%. The proposed method does not lose the optimality of the optimization method to be accelerated. In addition, this method is also applicable to optimization problems other than sequential control if the hypothetical achievable bound of the objective function is estimable without measuring the state of the environment or using the simulator.

scholarly journals CASIA-Face-Africa: A Large-scale African Face Image Database

2021 ◽  
pp. 1-1
Author(s):  
Jawad Muhammad ◽  
Yunlong Wang ◽  
Caiyong Wanga ◽  
Kunbo Zhang ◽  
Zhenan Sun
Keyword(s):  
Large Scale ◽  
Image Database ◽  
Face Image
Sign in / Sign up

Export Citation Format

Share Document