Papers by Shelina K H A L I D Jilani
PSM Biological Research, 2019
Craniofacial anthropometry plays an important role in facial structure. This review paper evaluat... more Craniofacial anthropometry plays an important role in facial structure. This review paper evaluates existing research surrounding population norms of studied facial parameters. The purpose is twofold: (1) to determine variations in facial measurements due to demi-group or ethnic variations based on traditional (direct) caliper based and image based (indirect) anthropometric methods. (2) to compare where possible, measured facial parameters between referenced studies. Inter and intra-population variations in addition to sexual dimorphism of facial parameters such as the nose and eyes, singularly or in combination with one another, have been concluded. Ocular measurements have exhibited ethnic variations between males and females of the Saudi, Turkish, Egyptian and Iranian group. Moreover, demic variations are reported when the native language has been used a key criterion. It has been concluded that with the current state of migration and inter-demic marriages, the study of homogenous populations will prove difficult. Subsequently, this will result in ambiguous physical traits that are not representative for any one demic or ethnic population. In this paper, results for the following adult male and female populations have been discussed: African American, Azerbaijani, Caribbean, Chinese, Croatian, Egyptian, Italian, Iranian, Turkish, Saudi Arabian, Syrian and South African. The qualitative research presented serves as a knowledge base for learners and strikes up thought provoking concepts about the direction anthropometrical research is heading.
Demographic-based identification plays an active role in the field of face identification. Over t... more Demographic-based identification plays an active role in the field of face identification. Over the past decade, machine learning algorithms have been used to investigate challenges surrouding ethnic classification for specific populations, such as African, Asian and Caucasian people. Ethnic classification for individuals of South Asian, Pakistani heritage, however, remains to be addressed. The present paper addresses a two-category (Pakistani Vs Non-Pakistani) classification task from a novel, purpose-built dataset. To the best of our knowledge, this work is the first to report a machine learning ethnic classification task with South Asian (Pakistani) faces. We conduted a series of experiments using deep learning algorithms (ResNet-50, ResNet-101 and ResNet-152) for feature extraction and a linear support vector machine (SVM) for classification. The experimental results demonstrate ResNet-101 achieves the highest performance accuracy of 99.2% for full-face ethnicity classification, followed closely by 91.7% and 95.7% for the nose and mouth respectively.
The nose is the most central feature on the face which is known to exhibit both gender and ethnic... more The nose is the most central feature on the face which is known to exhibit both gender and ethnic differences. ResNet-50 achieves the highest performance accuracy of 94.1%. In comparison, the highest score for the VGG-based models (VGG-16) was 90.8%. These results demonstrate that information from the nose is sufficient for deep learning models to achieve >90% accuracy on judgements of ethnicity.
Current Journal of Applied Science and Technology, Nov 20, 2018
Custody images are a standard feature of everyday Policing and are commonly used during investiga... more Custody images are a standard feature of everyday Policing and are commonly used during investigative work to establish whether the perpetrator and the suspect are the same. The process of identification relies heavily on the quality of a custody image because a low-quality image may mask identifying features. With an increased demand for high quality facial images and the requirement to integrate biometrics and machine vision technology to the field of face identification, this research presents an innovative image capture and biometric recording system called the Halo. Halo is a pioneering system which (1) uses machine vision cameras to capture high quality facial images from 8 planes of view (including CCTV simulated), (2) uses high quality video technology to Original Research Article
Drug Testing and Analysis, 2012
Gamma‐hydroxybutyric acid (GHB) is a drug‐of‐abuse that has recently become associated with drug‐... more Gamma‐hydroxybutyric acid (GHB) is a drug‐of‐abuse that has recently become associated with drug‐facilitated sexual assault, known as date rape. For this reason the drug is commonly found ‘spiked’ in alcoholic beverages. When GHB is in solution it may undergo conversion into the corresponding lactone, Gamma‐butyrolactone (GBL). Studies have been carried out to determine the detection limits of GHB and GBL in various solutions by Raman spectroscopy and to monitor the interconversion of GHB and GBL in solution with different pH conditions and temperature.In this study, a portable Raman spectrometer was used to study the interconversion of GHB and GBL in water and ethanol solutions as a function of pH, time, and temperature. The aim of this was to determine the optimum pH range for conversion in order to relate this to the pH ranges that the drug is likely to be subjected to, first in spiked beverages and secondly after ingestion in the digestive system. The aim was also to identify a ...
Current Journal of Applied Science and Technology, 2018
Custody images are a standard feature of everyday Policing and are commonly used during investiga... more Custody images are a standard feature of everyday Policing and are commonly used during investigative work to establish whether the perpetrator and the suspect are the same. The process of identification relies heavily on the quality of a custody image because a low-quality image may mask identifying features. With an increased demand for high quality facial images and the requirement to integrate biometrics and machine vision technology to the field of face identification, this research presents an innovative image capture and biometric recording system called the Halo. Halo is a pioneering system which (1) uses machine vision cameras to capture high quality facial images from 8 planes of view (including CCTV simulated), (2) uses high quality video technology to Original Research Article
Craniofacial anthropometry plays an important role in facial structure. This review paper evaluat... more Craniofacial anthropometry plays an important role in facial structure. This review paper evaluates existing research surrounding population norms of studied facial parameters. The purpose is two-fold: (1) to determine variations in facial measurements due to demi-group or ethnic variations based on traditional (direct) caliper based and image based (indirect) anthropometric methods. (2) to compare where possible, measured facial parameters between referenced studies. Inter and intra-population variations in addition to sexual dimorphism of facial parameters such as the nose and eyes, singularly or in combination with one another, have been concluded. Ocular measurements have exhibited ethnic variations between males and females of the Saudi, Turkish, Egyptian and Iranian group. Moreover, demic variations are reported when the native language has been used a key criterion. It has been concluded that with the current state of migration and inter-demic marriages, the study of homogeno...
2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), 2019
The nose is the most central feature on the face which is known to exhibit both gender and ethnic... more The nose is the most central feature on the face which is known to exhibit both gender and ethnic differences. It is a robust feature, invariant to expression and known to contain depth information. In this paper we address the topic of binary ethnicity classificiation from images of the nose, using a novel dataset of South Asian, Pakistani images. To the best of our knowledge, we are one of the first to attempt demographic (ethnicity) based identification based solely on information from the nose.A two-category (Pakistani vs Non-Pakistani) task was used in combination with Deep learning (ResNet) based and VGG-based pre-trained models. A series of experiments were conducted using ResNet-50, ResNet-101, ResNet-152, VGG-Face, VGG-16 and VGG-19, for feature extraction and a Linear Support Vector Machine for classification. The experimental results demonstrate ResNet-50 achieves the highest performance accuracy of 94.1%. In comparison, the highest score for the VGG-based models (VGG-16)...
2019 International Conference on Cyberworlds (CW), Oct 1, 2019
Demographic-based identification plays an active role in the field of face identification. Over t... more Demographic-based identification plays an active role in the field of face identification. Over the past decade, machine learning algorithms have been used to investigate challenges surrouding ethnic classification for specific populations, such as African, Asian and Caucasian people. Ethnic classification for individuals of South Asian, Pakistani heritage, however, remains to be addressed. The present paper addresses a two-category (Pakistani Vs Non-Pakistani) classification task from a novel, purpose-built dataset. To the best of our knowledge, this work is the first to report a machine learning ethnic classification task with South Asian (Pakistani) faces. We conduted a series of experiments using deep learning algorithms (ResNet-50, ResNet-101 and ResNet-152) for feature extraction and a linear support vector machine (SVM) for classification. The experimental results demonstrate ResNet-101 achieves the highest performance accuracy of 99.2% for full-face ethnicity classification, followed closely by 91.7% and 95.7% for the nose and mouth respectively.
2017 International Conference on Cyberworlds (CW)
2017 International Conference on Cyberworlds (CW), Sep 1, 2017
Uploads
Papers by Shelina K H A L I D Jilani