Learned Features are Better for Ethnicity Classification
Ethnicity is a key demographic attribute of human beings and it plays a vital role in automatic facial recognition and have extensive real world applications such as Human Computer Interaction (HCI); demographic based classification; biometric based recognition; security and defense to name a few. I...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2017-09-01
|
| Series: | Cybernetics and Information Technologies |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/cait-2017-0036 |
| _version_ | 1830201509245091840 |
|---|---|
| author | Anwar Inzamam Ul Islam Naeem |
| author_facet | Anwar Inzamam Ul Islam Naeem |
| author_sort | Anwar Inzamam |
| collection | DOAJ |
| description | Ethnicity is a key demographic attribute of human beings and it plays a vital role in automatic facial recognition and have extensive real world applications such as Human Computer Interaction (HCI); demographic based classification; biometric based recognition; security and defense to name a few. In this paper, we present a novel approach for extracting ethnicity from the facial images. The proposed method makes use of a pre trained Convolutional Neural Network (CNN) to extract the features, then Support Vector Machine (SVM) with linear kernel is used as a classifier. This technique uses translational invariant hierarchical features learned by the network, in contrast to previous works, which use hand crafted features such as Local Binary Pattern (LBP); Gabor, etc. Thorough experiments are presented on ten different facial databases, which strongly suggest that our approach is robust to different expressions and illuminations conditions. Here we consider ethnicity classification as a three class problem including Asian, African-American and Caucasian. Average classification accuracy over all databases is 98.28%, 99.66% and 99.05% for Asian, African-American and Caucasian respectively. All the codes are available for reproducing the results on request. |
| first_indexed | 2024-12-18T02:55:19Z |
| format | Article |
| id | doaj.art-6370ee458a1e4f9fafdcb70000e4cbd7 |
| institution | Directory Open Access Journal |
| issn | 1314-4081 |
| language | English |
| last_indexed | 2024-12-18T02:55:19Z |
| publishDate | 2017-09-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Cybernetics and Information Technologies |
| spelling | doaj.art-6370ee458a1e4f9fafdcb70000e4cbd72022-12-21T21:23:23ZengSciendoCybernetics and Information Technologies1314-40812017-09-0117315216410.1515/cait-2017-0036Learned Features are Better for Ethnicity ClassificationAnwar Inzamam0Ul Islam Naeem1Intelligent Systems Research Institute (ISRI), College of Information and Communication Engineering, Sungkyunkwan University, Suwon, South KoreaIntelligent Systems Research Institute (ISRI), College of Information and Communication Engineering, Sungkyunkwan University, Suwon, South KoreaEthnicity is a key demographic attribute of human beings and it plays a vital role in automatic facial recognition and have extensive real world applications such as Human Computer Interaction (HCI); demographic based classification; biometric based recognition; security and defense to name a few. In this paper, we present a novel approach for extracting ethnicity from the facial images. The proposed method makes use of a pre trained Convolutional Neural Network (CNN) to extract the features, then Support Vector Machine (SVM) with linear kernel is used as a classifier. This technique uses translational invariant hierarchical features learned by the network, in contrast to previous works, which use hand crafted features such as Local Binary Pattern (LBP); Gabor, etc. Thorough experiments are presented on ten different facial databases, which strongly suggest that our approach is robust to different expressions and illuminations conditions. Here we consider ethnicity classification as a three class problem including Asian, African-American and Caucasian. Average classification accuracy over all databases is 98.28%, 99.66% and 99.05% for Asian, African-American and Caucasian respectively. All the codes are available for reproducing the results on request.https://doi.org/10.1515/cait-2017-0036ethnicity recognitionrace classificationconvolutional neural network (cnn)vgg facesupport vector machine (svm) |
| spellingShingle | Anwar Inzamam Ul Islam Naeem Learned Features are Better for Ethnicity Classification Cybernetics and Information Technologies ethnicity recognition race classification convolutional neural network (cnn) vgg face support vector machine (svm) |
| title | Learned Features are Better for Ethnicity Classification |
| title_full | Learned Features are Better for Ethnicity Classification |
| title_fullStr | Learned Features are Better for Ethnicity Classification |
| title_full_unstemmed | Learned Features are Better for Ethnicity Classification |
| title_short | Learned Features are Better for Ethnicity Classification |
| title_sort | learned features are better for ethnicity classification |
| topic | ethnicity recognition race classification convolutional neural network (cnn) vgg face support vector machine (svm) |
| url | https://doi.org/10.1515/cait-2017-0036 |
| work_keys_str_mv | AT anwarinzamam learnedfeaturesarebetterforethnicityclassification AT ulislamnaeem learnedfeaturesarebetterforethnicityclassification |