Gender and Age Classification of Human Faces for Automatic Detection of Anomalous Human Behaviour

Ali, Azliza Mohd; Angelov, Plamen

doi:10.1109/cybconf.2017.7985780

Cited by 25 publications

(9 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We assume that security system collects the GAFace image dataset of faces, and we use it for recognition as to be applied in this scenario. We applied pre-trained deep neural network to extract the features and classify them by using SVM (Wang et al 2017). Table 3 compared the accuracy results of age and gender classification.…”

Section: Results and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Anomalous behaviour detection based on heterogeneous data and data fusion

Ali

Angelov

2018

Soft Comput

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a new approach to identify anomalous behaviour based on heterogeneous data and a data fusion technique. There are four types of datasets applied in this study including credit card, loyalty card, GPS, and image data. The first step of the complete framework in this proposed study is to identify the best features for every dataset. Then, the new anomaly detection technique which is recently introduced and known as empirical data analytics (EDA) is applied to detect the abnormal behaviour based on the datasets. Standardised eccentricity (a newly introduced within EDA measure offering a new simplified form of the well-known Chebyshev inequality) can be applied to any data distribution. Image data are processed using pre-trained deep learning network, and classification is done by using support vector machine. Most of the other data used in our previous work are of type "signal"/real number (e.g. credit card, loyalty card and GPS data). However, a clear conclusion that a misuse was made very often cannot be reached based on them only. When gender or age is different from the expected, it is obvious misuse. At the final stage of the proposed method is combining anomaly result and image recognition using data fusion technique. From the experiment results, this proposed technique may simplify the tedious job in the real complex cases of forensic investigation. The proposed technique is using heterogeneous data which combine all the data from the VAST Challenge as well as image data using an introduced data fusion technique. These can assist the human expert in processing huge amount of heterogeneous data to detect anomalies. In future research, text data can also be used as a part of heterogeneous data mixture, and the data fusion technique may be applied to other datasets.

show abstract

Section: Results and Analysismentioning

confidence: 99%

“…Figure 3 shows the combination of AlexNet and SVM classifiers to classify new images. There are three steps in the algorithm of this proposed solution, namely (Wang et al 2017):…”

Section: Deep Learningmentioning

confidence: 99%

Anomalous behaviour detection based on heterogeneous data and data fusion

Ali

Angelov

2018

Soft Comput

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is easy to classify a person as male or female or the age group in online advertising because of the tracking nature of websites such as Google and Facebook which track your movement throughout the internet by injecting scripts into other websites using their advertisement portal. We want to take this approach of targeted advertising to offline channels, but since there is no way to track where a person goes and what a person does in his/her life, we focus on the two main attributes: Gender and Age [11].…”

Section: B Generation Of Demographicsmentioning

confidence: 99%

User Targeted Offline Advertising using Recognition Based Demographics and Queue Scheduling

Malhotra,

Gupta,

Katyal

et al. 2020

IJEAT

View full text Add to dashboard Cite

Offline advertisements are static in nature. Advertising companies use billboards for advertising. These billboards display advertisements in a random fashion depending on the investment made by the advertiser. Advertisers pay a fixed amount of money for displaying their advertisements and not on the basis of relevant viewership. The technology proposed in the paper ensures that this disparity is handled wherein offline advertisements are targeted to the relevant audience. The technology has been named TARP which is an abbreviation for Target. Advertise. Revolutionise. Promote. TARP uses built in cameras on offline advertising platforms such as billboards & TV Screens in malls, restaurants, metro & airports to target advertisements based on gender, age and other relevant demographics. The technology is a boon for the advertising industry and benefits both advertisers and viewers. It displays what viewers want to see and who the advertisers want to reach out to. Convolutional neural networks are used to generate demographics of viewing population. Centroids of the viewing population are maintained for each billboard. Advertisements search for the most relevant billboard for display. Display of advertisements is monitored by a queue scheduling algorithm. The research paper proposes an algorithm to generate demographics, search most relevant billboard for each advertisement as well as generate priority queues.

show abstract

“…CNNs is based on feedforward neural network and have better generalisation than networks with full connectivity between adjacent layers [11]. Moreover, CNNs has been successfully applied in many applications especially in image identification [12][13][14][15], surveillance [16], and human recognition [17][18][19]. Lei and She [20] authenticate voice using CNNs method in a noisy environment.…”

Section: Introductionmentioning

confidence: 99%

“…Support Vector Machine (SVM) can be categorised as one of the best classifications techniques. SVM also has been applied in various applications for instance in biometrics [17,[22][23], sentiment analysis [24][25] and security such as intrusion detection [26][27]. Selvakumari and Radha [28] applied SVM in classifying speech pathology and achieved 98% accuracy compared to the Naïve Bayes algorithm.…”

Section: Introductionmentioning

confidence: 99%

Comparison of CNNs and SVM for voice control wheelchair

Sharifuddin

Nordin

Ali

2020

IJ-AI

Self Cite

View full text Add to dashboard Cite

In this paper, we develop an intelligent wheelchair using CNNs and SVM voice recognition methods. The data is collected from Google and some of them are self-recorded. There are four types of data to be recognized which are go, left, right, and stop. Voice data are extracted using MFCC feature extraction technique. CNNs and SVM are then used to classify and recognize the voice data. The motor driver is embedded in Raspberry PI 3B+ to control the movement of the wheelchair prototype. CNNs produced higher accuracy i.e. 95.30% compared to SVM which is only 72.39%. On the other hand, SVM only took 8.21 seconds while CNNs took 250.03 seconds to execute. Therefore, CNNs produce better result because noise are filtered in the feature extraction layer before classified in the classification layer. However, CNNs took longer time due to the complexity of the networks and the less complexity implementation in SVM give shorter processing time.

show abstract

Gender and Age Classification of Human Faces for Automatic Detection of Anomalous Human Behaviour

Cited by 25 publications

References 27 publications

Anomalous behaviour detection based on heterogeneous data and data fusion

Anomalous behaviour detection based on heterogeneous data and data fusion

User Targeted Offline Advertising using Recognition Based Demographics and Queue Scheduling

Comparison of CNNs and SVM for voice control wheelchair

Contact Info

Product

Resources

About