This paper describes an adaptation of the Local Interpretable Model-Agnostic Explanations (LIME) AI method to operate under a biometric verification setting. LIME was initially proposed for networks with the same output classes used for training, and it employs the softmax probability to determine which regions of the image contribute the most to classification. However, in a verification setting, the classes to be recognized have not been seen during training. In addition, instead of using the softmax output, face descriptors are usually obtained from a layer before the classification layer. The model is adapted to achieve explainability via cosine similarity between feature vectors of perturbated versions of the input image. The method is showcased for face biometrics with two CNN models based on MobileNetv2 and ResNet50.
The widespread use of mobile devices for various digital services has created a need for reliable and real-time person authentication. In this context, facial recognition technologies have emerged as a dependable method for verifying users due to the prevalence of cameras in mobile devices and their integration into everyday applications. The rapid advancement of deep Convolutional Neural Networks (CNNs) has led to numerous face verification architectures. However, these models are often large and impractical for mobile applications, reaching sizes of hundreds of megabytes with millions of parameters. We address this issue by developing SqueezerFaceNet, a light face recognition network which less than 1M parameters. This is achieved by applying a network pruning method based on Taylor scores, where filters with small importance scores are removed iteratively. Starting from an already small network (of 1.24M) based on SqueezeNet, we show that it can be further reduced (up to 40%) without an appreciable loss in performance. To the best of our knowledge, we are the first to evaluate network pruning methods for the task of face recognition.
One weakness of machine-learning algorithms is the need to train the models for a new task. This presents a specific challenge for biometric recognition due to the dynamic nature of databases and, in some instances, the reliance on subject collaboration for data collection. In this paper, we investigate the behavior of deep representations in widely used CNN models under extreme data scarcity for One-Shot periocular recognition, a biometric recognition task. We analyze the outputs of CNN layers as identity-representing feature vectors. We examine the impact of Domain Adaptation on the network layers' output for unseen data and evaluate the method's robustness concerning data normalization and generalization of the best-performing layer. We improved state-of-the-art results that made use of networks trained with biometric datasets with millions of images and fine-tuned for the target periocular dataset by utilizing out-of-the-box CNNs trained for the ImageNet Recognition Challenge and standard computer vision algorithms. For example, for the Cross-Eyed dataset, we could reduce the EER by 67% and 79% (from 1.70% and 3.41% to 0.56% and 0.71%) in the Close-World and Open-World protocols, respectively, for the periocular case. We also demonstrate that traditional algorithms like SIFT can outperform CNNs in situations with limited data or scenarios where the network has not been trained with the test classes like the Open-World mode. SIFT alone was able to reduce the EER by 64% and 71.6% (from 1.7% and 3.41% to 0.6% and 0.97%) for Cross-Eyed in the Close-World and Open-World protocols, respectively, and a reduction of 4.6% (from 3.94% to 3.76%) in the PolyU database for the Open-World and single biometric case.
Workplace injuries are common in today's society due to a lack of adequately worn safety equipment. A system that only admits appropriately equipped personnel can be created to improve working conditions. The goal is thus to develop a system that will improve workers' safety using a camera that will detect the usage of Personal Protective Equipment (PPE). To this end, we collected and labeled appropriate data from several public sources, which have been used to train and evaluate several models based on the popular YOLOv4 object detector. Our focus, driven by a collaborating industrial partner, is to implement our system into an entry control point where workers must present themselves to obtain access to a restricted area. Combined with facial identity recognition, the system would ensure that only authorized people wearing appropriate equipment are granted access. A novelty of this work is that we increase the number of classes to five objects (hardhat, safety vest, safety gloves, safety glasses, and hearing protection), whereas most existing works only focus on one or two classes, usually hardhats or vests. The AI model developed provides good detection accuracy at a distance of 3 and 5 meters in the collaborative environment where we aim at operating (mAP of 99/89%, respectively). The small size of some objects or the potential occlusion by body parts have been identified as potential factors that are detrimental to accuracy, which we have counteracted via data augmentation and cropping of the body before applying PPE detection.
One of the biggest challenges in machine learning is data collection. Training data is an important part since it determines how the model will behave. In object classification, capturing a large number of images per object and in different conditions is not always possible and can be very time-consuming and tedious. Accordingly, this work explores the creation of artificial images using a game engine to cope with limited data in the training dataset. We combine real and synthetic data to train the object classification engine, a strategy that has shown to be beneficial to increase confidence in the decisions made by the classifier, which is often critical in industrial setups. To combine real and synthetic data, we first train the classifier on a massive amount of synthetic data, and then we fine-tune it on real images. Another important result is that the amount of real images needed for fine-tuning is not very high, reaching top accuracy with just 12 or 24 images per class. This substantially reduces the requirements of capturing a great amount of real data.
Fires have destructive power when they break out and affect their surroundings on a devastatingly large scale. The best way to minimize their damage is to detect the fire as quickly as possible before it has a chance to grow. Accordingly, this work looks into the potential of AI to detect and recognize fires and reduce detection time using object detection on an image stream. Object detection has made giant leaps in speed and accuracy over the last six years, making real-time detection feasible. To our end, we collected and labeled appropriate data from several public sources, which have been used to train and evaluate several models based on the popular YOLOv4 object detector. Our focus, driven by a collaborating industrial partner, is to implement our system in an industrial warehouse setting, which is characterized by high ceilings. A drawback of traditional smoke detectors in this setup is that the smoke has to rise to a sufficient height. The AI models brought forward in this research managed to outperform these detectors by a significant amount of time, providing precious anticipation that could help to minimize the effects of fires further.
Selfie images enjoy huge popularity in social media. The same platforms centered around sharing this type of images offer filters to beautify them or incorporate augmented reality effects. Studies suggests that filtered images attract more views and engagement. Selfie images are also in increasing use in security applications due to mobiles becoming data hubs for many transactions. Also, video conference applications, boomed during the pandemic, include such filters. Such filters may destroy biometric features that would allow person recognition or even detection of the face itself, even if such commodity applications are not necessarily used to compromise facial systems. This could also affect subsequent investigations like crimes in social media, where automatic analysis is usually necessary given the amount of information posted in social sites or stored in devices or cloud repositories. To help in counteracting such issues, we contribute with a database of facial images that includes several manipulations. It includes image enhancement filters (which mostly modify contrast and lightning) and augmented reality filters that incorporate items like animal noses or glasses. Additionally, images with sunglasses are processed with a reconstruction network trained to learn to reverse such modifications. This is because obfuscating the eye region has been observed in the literature to have the highest impact on the accuracy of face detection or recognition. We start from the popular Labeled Faces in the Wild (LFW) database, to which we apply different modifications, generating 8 datasets. Each dataset contains 4,324 images of size 64 x 64, with a total of 34,592 images. The use of a public and widely employed face dataset allows for replication and comparison. The created database is available at https://github.com/HalmstadUniversityBiometrics/LFW-Beautified
Beautification and augmented reality filters are very popular in applications that use selfie images captured with smartphones or personal devices. However, they can distort or modify biometric features, severely affecting the capability of recognizing individuals' identity or even detecting the face. Accordingly, we address the effect of such filters on the accuracy of automated face detection and recognition. The social media image filters studied either modify the image contrast or illumination or occlude parts of the face with for example artificial glasses or animal noses. We observe that the effect of some of these filters is harmful both to face detection and identity recognition, specially if they obfuscate the eye or (to a lesser extent) the nose. To counteract such effect, we develop a method to reconstruct the applied manipulation with a modified version of the U-NET segmentation network. This is observed to contribute to a better face detection and recognition accuracy. From a recognition perspective, we employ distance measures and trained machine learning algorithms applied to features extracted using a ResNet-34 network trained to recognize faces. We also evaluate if incorporating filtered images to the training set of machine learning approaches are beneficial for identity recognition. Our results show good recognition when filters do not occlude important landmarks, specially the eyes (identification accuracy >99%, EER<2%). The combined effect of the proposed approaches also allow to mitigate the effect produced by filters that occlude parts of the face, achieving an identification accuracy of >92% with the majority of perturbations evaluated, and an EER <8%. Although there is room for improvement, when neither U-NET reconstruction nor training with filtered images is applied, the accuracy with filters that severely occlude the eye is <72% (identification) and >12% (EER)
The world is expecting an aging population and shortage of healthcare professionals. This poses the problem of providing a safe and dignified life for the elderly. Technological solutions involving cameras can contribute to safety, comfort and efficient emergency responses, but they are invasive of privacy. We use 'Griddy', a prototype with a Panasonic Grid-EYE, a low-resolution infrared thermopile array sensor, which offers more privacy. Mounted over a bed, it can determine if the user is on the bed or not without human interaction. For this purpose, two datasets were captured, one (480 images) under constant conditions, and a second one (200 images) under different variations such as use of a duvet, sleeping with a pet, or increased room temperature. We test three machine learning algorithms: Support Vector Machines (SVM), k-Nearest Neighbors (k-NN) and Neural Network (NN). With 10-fold cross validation, the highest accuracy in the main dataset is for both SVM and k-NN (99%). The results with variable data show a lower reliability under certain circumstances, highlighting the need of extra work to meet the challenge of variations in the environment.