On Detecting Domestic Abuse via Faces
18 Jun 2018-pp 2173-2179
TL;DR: The results on the proposed database show that deep learning based framework is effective in detecting domestic injuries and a novel framework using activation maps of deep learning features for determining whether an image belongs to domestic violence class or not is presented.
Abstract: Domestic violence is considered a major social problem worldwide. Different countries have enacted the law to contain and protect the victims of domestic violence. In order to understand the nature of domestic violence, medical professionals and researchers have performed manual analysis of facial injuries. The aim of these studies is to find commonly affected facial regions, to determine the types of maxillofacial trauma associated with domestic violence, and to distinguish the injuries of domestic violence from accidents. Analysis of these injuries assist the service providers in providing proper treatment to the victims as well as facilitate law enforcement investigation. This paper automates the process of analyzing the facial injuries to distinguish the victims of domestic abuse from others. For this purpose, Domestic Violence Face database of 450 subjects with two classes namely, Domestic Violence and Non-Domestic Violence, is prepared. The paper also presents a novel framework using activation maps of deep learning features for determining whether an image belongs to domestic violence class or not. The results on the proposed database show that deep learning based framework is effective in detecting domestic injuries.
Citations
More filters
01 Sep 2019
TL;DR: In this article, a Subclass Contrastive Loss (SCL) was proposed for face recognition in the presence of facial injuries such as swelling, bruises, blood clots, laceration, and avulsion.
Abstract: Deaths and injuries are common in road accidents, violence, and natural disaster. In such cases, one of the main tasks of responders is to retrieve the identity of the victims to reunite families and ensure proper identification of deceased/injured individuals. Apart from this, identification of unidentified dead bodies due to violence and accidents is crucial for the police investigation. In the absence of identification cards, current practices for this task include DNA profiling and dental profiling. Face is one of the most commonly used and widely accepted biometric modalities for recognition. However, face recognition is challenging in the presence of facial injuries such as swelling, bruises, blood clots, laceration, and avulsion which affect the features used in recognition. In this paper, for the first time, we address the problem of injured face recognition and propose a novel Subclass Contrastive Loss (SCL) for this task. A novel database, termed as Injured Face (IF) database, is also created to instigate research in this direction. Experimental analysis shows that the proposed loss function surpasses existing algorithm for injured face recognition.
4 citations
01 Jan 2021
TL;DR: In this paper, a Subclass Injured Face Identification (SCIFI) loss was proposed to learn feature representation agnostic to injury variations, which is used in learning feature representation for face recognition.
Abstract: Deaths and injuries are common in road accidents, violence, and natural disaster. In accidents and natural disasters scenarios, one of the tasks of responders is to retrieve the identity of the victims to reunite families or ensure proper identification of deceased persons. Apart from this, the identification of unidentified dead bodies due to violence and accidents is crucial for the police investigation. In the absence of identification cards, different forensic techniques such as DNA profiling and dental profiling may be used for identification. In this research, we present face recognition as a fast and viable approach for recognizing individuals with injuries. Face, which can be captured easily, is one of the most commonly used and widely accepted biometric modalities. However, face recognition is challenging in the presence of injuries as facial injuries change the appearance and geometric properties of the face due to swelling, bruises, blood clots, and accidental cuts. These changes introduce large intra-class variations among the same subject and small inter-class separability among different subjects. To address the challenge, we propose a novel Subclass Injured Face Identification (SCIFI) loss which is used in learning feature representation agnostic to injury variations. Additionally, an extended Injured Face (IF-V2) database of 150 subjects is presented to evaluate the performance of face recognition models. Multiple experiments and comparisons are performed to showcase the efficacy of the proposed SCIFI loss based face recognition.
3 citations
TL;DR: A systematic review of some of the efforts that can help address the problem of violence against women and children is presented in this paper, which describes the current state-of-theart of these contributions and identifies trends, architectures, technologies, and current open challenges.
Abstract: Violence against women and children is a public health issue of pandemic proportions. It is estimated that one in every three women worldwide has experienced physical, emotional, or sexual violence. Similarly, each year one out of two children are victims of some form of violence including domestic aggression and bullying. Due to the widespread use of the Internet and social media, women and children are now vulnerable to other types of violence such as cyber-bullying and online sexual or emotional harassment. To help alleviate this social problem, the use of computer science and related technologies has been leveraged in recent years. The Internet of Things, artificial intelligence, ubiquitous and mobile computing, pattern recognition, cloud computing and similar technologies, have been used to formulate solutions to detect and prevent violent acts against women and children. In this paper, a systematic review of some of the efforts that can help address the problem of violence against women and children is presented. This paper describes the current state-of-the-art of these contributions and identifies trends, architectures, technologies, and current open challenges. The survey was developed using a literature review of academic documents published from 2010 to 2020. The contributions were categorized into four application domains: online detection, offline detection, safety, and education. These contributions were further categorized based on the computer science approaches and technologies used: artificial intelligence, Internet of Things, and digital serious games.
3 citations
01 Apr 2021
TL;DR: In this paper, the authors proposed a facial vector-based algorithm for filling admission forms with the help of face recognition, which could severely cut down the delays in hospital admission and treatment.
Abstract: When the person met with an accident is brought to the hospital, there are many official formalities (e.g., admission form to be filled) before the treatment that can be started. In some severe cases, these formalities can delay the treatment, which could be fatal to the patient. The automated system which can fill these forms with the help of face recognition could severely cut down the delays. But, in some cases, the injury and the blood on to the face fail facial recognition. To overcome this problem, we have proposed a facial vector-based algorithm. In the current work, we have also demonstrated, sending the SMS to the concerned authorities (police) and even to the relatives of the patient automatically using GSM modules. The patient’s information was received from centralized databases of different hospitals that are linked through the internet. We have tested the algorithm on more than 213K images from different databases like celebA, LFW, UCFI. We found that the maximum accuracy of our system was 98.23%. As a proof-of-concept, we tried testing on 51 real-time patient images and found that the accuracy is 94.11%. This automated form filling not only reduced the delay in hospital admission, but also also helped in treatment, because of the auto-filled medical history.
1 citations
TL;DR: In this paper , the most used automatic algorithm for unsupervised ML in DV research was latent Dirichlet allocation (LDA) for topic modeling, while three purposes of ML and challenges were delineated and are discussed.
Abstract: Domestic violence (DV) is a public health crisis that threatens both the mental and physical health of people. With the unprecedented surge in data available on the internet and electronic health record systems, leveraging machine learning (ML) to detect obscure changes and predict the likelihood of DV from digital text data is a promising area health science research. However, there is a paucity of research discussing and reviewing ML applications in DV research. Methods: We extracted 3588 articles from four databases. Twenty-two articles met the inclusion criteria. Results: Twelve articles used the supervised ML method, seven articles used the unsupervised ML method, and three articles applied both. Most studies were published in Australia (n = 6) and the United States (n = 4). Data sources included social media, professional notes, national databases, surveys, and newspapers. Random forest (n = 9), support vector machine (n = 8), and naïve Bayes (n = 7) were the top three algorithms, while the most used automatic algorithm for unsupervised ML in DV research was latent Dirichlet allocation (LDA) for topic modeling (n = 2). Eight types of outcomes were identified, while three purposes of ML and challenges were delineated and are discussed. Conclusions: Leveraging the ML method to tackle DV holds unprecedented potential, especially in classification, prediction, and exploration tasks, and particularly when using social media data. However, adoption challenges, data source issues, and lengthy data preparation times are the main bottlenecks in this context. To overcome those challenges, early ML algorithms have been developed and evaluated on DV clinical data.
1 citations
References
More filters
Proceedings Article•
04 Sep 2014TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
55,235 citations
"On Detecting Domestic Abuse via Fac..." refers methods in this paper
...Features extracted using LBP, HOG, pre-trained VGGFace, and pre-trained VGG16 are used to train four different classifiers: Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), Naive Bayes (NB), and Random Decision Forest (RDF)....
[...]
...To evaluate the baseline performance on the DVF database, two deep learning models, VGGFace [16], VGG16 [18], and two handcrafted feature extraction algorithms, Local Binary Pattern (LBP) [14] and Histogram of Oriented Gradient (HOG) [7] are used....
[...]
...ROC curves of the proposed framework, pre-trained VGGFace, and VGG16 model are shown in Figure 5b....
[...]
Proceedings Article•
01 Jan 2015TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
49,914 citations
20 Jun 2005
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Abstract: We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.
31,952 citations
"On Detecting Domestic Abuse via Fac..." refers methods in this paper
...Features extracted using LBP, HOG, pre-trained VGGFace, and pre-trained VGG16 are used to train four different classifiers: Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), Naive Bayes (NB), and Random Decision Forest (RDF)....
[...]
...To evaluate the baseline performance on the DVF database, two deep learning models, VGGFace [16], VGG16 [18], and two handcrafted feature extraction algorithms, Local Binary Pattern (LBP) [14] and Histogram of Oriented Gradient (HOG) [7] are used....
[...]
01 Dec 2001
TL;DR: A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.
Abstract: This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the "integral image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields extremely efficient classifiers. The third contribution is a method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. The cascade can be viewed as an object specific focus-of-attention mechanism which unlike previous approaches provides statistical guarantees that discarded regions are unlikely to contain the object of interest. In the domain of face detection the system yields detection rates comparable to the best previous systems. Used in real-time applications, the detector runs at 15 frames per second without resorting to image differencing or skin color detection.
18,620 citations
"On Detecting Domestic Abuse via Fac..." refers methods in this paper
...Viola-Jones face detector [21] is applied to all the images to segment the facial region....
[...]
TL;DR: This paper evaluates the performance both of some texture measures which have been successfully used in various applications and of some new promising approaches proposed recently.
6,650 citations
"On Detecting Domestic Abuse via Fac..." refers methods in this paper
...For instance, 80% samples pertaining to domestic violence class are misclassified as non-domestic violence using LBP-RDF....
[...]
...Features extracted using LBP, HOG, pre-trained VGGFace, and pre-trained VGG16 are used to train four different classifiers: Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), Naive Bayes (NB), and Random Decision Forest (RDF)....
[...]
...To evaluate the baseline performance on the DVF database, two deep learning models, VGGFace [16], VGG16 [18], and two handcrafted feature extraction algorithms, Local Binary Pattern (LBP) [14] and Histogram of Oriented Gradient (HOG) [7] are used....
[...]