Next-Gen Facial Recognition for Criminal Detection: Leveraging Advanced Machine Learning Techniques

The main precondition for applications such as face recognition and face de-identification for privacy protection is efficient face detection in real scenes. In this paper, we propose a hybrid cascade model for face detection in the wild. The cascaded two-stage model is based on the fast normalized pixel difference (NPD) detector at the first stage, and a deep convolutional neural network (CNN) at the second stage. The outputs of the NPD detector are characterized by a very small number of false negative (FN) and a much higher number of false positive face (FP) detections. The FP detections are typically an order of magnitude higher than the FN ones. This very high number of FPs has a negative impact on recognition and/or de-identification processing time and on the naturalness of the de-identified images. To reduce the large number of FP face detections, a CNN is used at the second stage. The CNN is applied only on vague face region candidates obtained by the NPD detector that have an NPD score in the interval between two experimentally determined thresholds. The experimental results on the Annotated Faces in the Wild (AFW) test set and the Face Detection Dataset and Benchmark (FDDB) show that the hybrid cascade model significantly reduces the number of FP detections while the number of FN detections are only slightly increased.

Multi-label learning based deep transfer neural network for facial attribute classification

This paper proposes a face verification system that runs on Android mobile devices. In this system, facial image is captured by a built-in camera on the Android device firstly, and then face detection is implemented using Haar-like features and AdaBoost learning algorithm. The proposed system verify the detected face using histogram based features, which are generated by binary Vector Quantization (VQ) histogram using DCT coefficients in low frequency domains, as well as Improved Local Binary Pattern (Improved LBP) histogram in spatial domain. Verification results with different type of histogram based features are first obtained separately and then combined by weighted averaging. We evaluate our proposed algorithm by using publicly available ORL database and facial images captured by an Android tablet.

There is an abnormal increase in the crime rate and also the number of criminals are increasing, this leads towards a great concern about the security issues. Crime preventions and criminal identification are the primary issues before the police personnel, since property and lives protection are the basic concerns of the police but to combat the crime, the availability of police personnel is limited. With the advent of security technology, cameras especially CCTV have been installed in many public and private areas to provide surveillance activities. The footage of the CCTV can be used to identify suspects on scene. This Real time criminal identification system based on face recognition works with a fully automated facial recognition system. Haar feature-based cascade classifier and OpenCV LBPH (Local Binary Pattern Histograms) Algorithms are used for Face detection and recognition. This system will be able to detect face and recognize face automatically in real time. An accurate location of the face is still a challenging task. This Framework has been widely used by researchers in order to detect the location of faces and objects in a given image. Face detection classifiers are shared by public communities, such as OpenCV. The automatically tagging feature adds a new dimension to sharing pictures among the people who are in the picture and also gives the idea to other people about who the person is in the image. In our project, we have studied and implemented a pretty simple but very effective face detection using CNN algorithm which takes human skin color into account. Our aim, which we believe we have reached, was to develop a system that can be used by police or investigation department to recognize criminal from their faces. The method of face recognition used is fast, robust, reasonably simple and accurate with a relatively simple and easy to understand algorithms and technique. Key Words: Face Detection, MTCNN, Deep Learning, Real-Time Surveillance, Criminal Identification, CNN

Optimization strategies for neural network deployment on FPGA: An energy-efficient real-time face detection use case

Deep neural networks (DNNs) find extensive applications across diverse domains, including Speech Recognition, Face Detection, and Image Classification. While the conventional approach relies on Graphics Processing Units (GPUs) for DNN implementation, it prioritizes speed at the expense of efficiency. In the pursuit of reduced power consumption and enhanced efficiency, we advocate for the adoption of application-specific hardware computing. This paper introduces a run-time reconfigurable DNN accelerator SoC (DNN-AS) architecture, seamlessly integrated into the instruction-extended RISC-V platform. The meticulously crafted application-specific extension instruction set is tailored to expedite high-frequency DNN operations. To optimize circuit structure, we have devised an 8-bit dynamic fixed-point (DFP) scheme within the DNN-AS. Furthermore, we conduct a comparative accuracy analysis between DFP and the PyTorch float implementation. Our results demonstrate that DNN-AS exhibits minimal accuracy loss, with Top 1 accuracy deviations of only up to 0.53%, 0.31%, and 0.68% for RESNET34, RESNET50, and RESNET101, respectively. Finally, we juxtapose the overall simulated results with other platforms, revealing that our design has achieved remarkable improvements in throughput per joule (GOP/J), ranging from 8.4x to 1897x compared to Field-Programmable Gate Arrays (FPGAs) and GPU.

Face-selective neurons are observed in the primate visual pathway and are considered as the basis of face detection in the brain. However, it has been debated as to whether this neuronal selectivity can arise innately or whether it requires training from visual experience. Here, using a hierarchical deep neural network model of the ventral visual stream, we suggest a mechanism in which face-selectivity arises in the complete absence of training. We found that units selective to faces emerge robustly in randomly initialized networks and that these units reproduce many characteristics observed in monkeys. This innate selectivity also enables the untrained network to perform face-detection tasks. Intriguingly, we observed that units selective to various non-face objects can also arise innately in untrained networks. Our results imply that the random feedforward connections in early, untrained deep neural networks may be sufficient for initializing primitive visual selectivity.

Deep neural networks are efficient methods of recognizing image patterns and have been largely implemented in computer vision applications. Object detection has many applications in computer vision, including face and vehicle detection, video surveillance, and plant leaf detection. An automatic flower identification system over categories is still challenging due to similarities among classes and intraclass variation, so the deep learning model requires more precisely labeled and high-quality data. In this proposed work, an optimized and generalized deep convolutional neural network using Faster-Recurrent Convolutional Neural Network (Faster-RCNN) and Single Short Detector (SSD) is used for detecting, localizing, and classifying flower objects. We prepared 2000 images for various pretrained models, including ResNet 50, ResNet 101, and Inception V2, as well as Mobile Net V2. In this study, 70% of the images were used for training, 25% for validation, and 5% for testing. The experiment demonstrates that the proposed Faster-RCNN model using the transfer learning approach gives an optimum mAP score of 83.3% with 300 and 91.3% with 100 proposals on ten flower classes. In addition, the proposed model could identify, locate, and classify flowers and provide essential details that include flower name, class classification, and multilabeling techniques.

Criminal face identification system using deep learning algorithm multi-task cascade neural network (MTCNN)

A typical automated face recognition system is composed of three main component tasks: face detection and alignment (FDA), face presentation attack detection (FPAD), and face representation and matching (FRM). These tasks are often treated as standalone problems and deep neural network (DNN)-based solutions have been proposed to address them individually. However, in resource-constrained sce-narios it would be ideal to have a unified DNN model that can perform all the three tasks together. As a first step towards realizing this goal, this work attempts to perform joint FRM and FPAD based on a single Vision Transformer (ViT) backbone. Recent work demonstrating the ability of ViT to extract a diverse set of feature representations gives rise to the tantalising possibility of building an end-to-end face recognition system using a single ViT model. The standard approach for designing multi-task DNNs is to implement different classification heads (e.g., for FRM and FPAD) based on a common stem/base and learn these heads either individually or jointly. A key contribution of this work is to demonstrate that this naive multi-head approach results in sub-optimal performance for either FRM or FPAD, because the features required by these tasks are very different. While good FPAD performance depends on accurately characterizing the micro textures, face matching demands attention towards more global characteris-tics. Hence, we propose a novel feature ensemble approach, where an ensemble of local features extracted from the in-termediate blocks of a ViT are utilized for FPAD, while face matching is performed based on the ViT class token. Exper-iments demonstrate that the proposed ViT feature ensemble approach is able to achieve good performance for both face matching and FPAD compared to the multi-head approach.

Automated image classification is an essential task of the computer vision field. The tagging of images into a set of predefined groups is referred to as image classification. The implementation of computer vision to automate image classification would be beneficial because manual image evaluation and identification can be time-consuming, particularly when there are many images of different classes. Deep learning approaches are proven to overperform existing machine learning techniques in many fields in recent years, and computer vision is one of the most notable examples. The very deep neural network (VDCNN) is a powerful deep learning model for image classification, and this paper examines it briefly using MNIST handwritten digit dataset. This dataset is used to prove the efficacy of very deep neural networks over other deep learning models. The proposed study aims to comprehend the very deep neural network architecture used to accomplish a handwritten digit recognition task. The feasibility of the proposed model is evaluated using mean accuracy, validation accuracy, and standard deviation. The study results of the very deep neural network model are compared to a convolutional neural network and convolutional neural network with batch normalization. According to the results of the comparison study, very deep neural networks achieve high accuracy of 99.1% for a handwritten dataset. The outcome of the proposed work is used to interpret how well a very deep neural network performs when compared to the other two models of deep neural networks. This proposed architecture may be used to automate the classification of handwritten digits dataset.

In video surveillance, low resolution in face recognition is a major problem. Various Super Resolution (SR) approaches are introduced to perform the high resolution of face video recognition from low resolution videos. However, enhancing the resolution of face videos and reconstructing the high frequency data is a major problem in research area. Therefore, an effective face video Super Resolution method-based on Deep Convolutional Neural Network (Deep CNN) is introduced in this paper to achieve the face resolution effectively. Initially, the input video collected from the database is passed into the frame extraction stage, where the video frames are extracted and the face detection is carried out using the Viola Jones algorithm. Moreover, the detected image frame is processed by the Deep Convolutional Neural Network (Deep CNN) to enhance the image resolution. Deep CNN is highly effective in performing super resolution in face videos. However, the proposed Deep Convolutional Neural Network attains better performance using the metrics, like Second Derivative like Measure of Enhancement (SDME) as 0.9743 using video-1, and Feature SIMilarity index (FSIM) as 53.843 for video-4, respectively.

The use of face masks is an important part of life in the midst of the Covid-19 pandemic which has been designated as a global pandemic, people are urged to cover their faces when in public areas to avoid the spread of the virus. The use of these face masks has raised serious questions regarding face detection systems. This study used Deep Neural Network and Tensorflow methods to detect faces both using masks and without masks. This study used two datasets, a face collection dataset without a mask and a face group using a mask. The result of this study was the detection of faces with masks trained on the dataset achieved 98% accuracy in training, and for testing got 100% accuracy on faces without masks, and 99.99% accuracy for face with mask.

Faces are a crucial environmental trigger. They communicate information about several key features, including identity. However, the 2019 coronavirus pandemic (COVID-19) significantly affected how we process faces. To prevent viral spread, many governments ordered citizens to wear masks in public. In this research, we focus on identifying individuals from images or videos by comparing facial features, identifying a person's biometrics, and reducing the weaknesses of person recognition technology, for example when a person does not look directly at the camera, the lighting is poor, or the person has effectively covered their face. Consequently, we propose a hybrid approach of detecting either a person with or without a mask, a person who covers large parts of their face, and a person based on their gait via deep and machine learning algorithms. The experimental results are excellent compared to the current face and gait detectors. We achieved success of between 97% and 100% in the detection of face and gait based on F1 score, precision, and recall. Compared to the baseline CNN system, our approach achieves extremely high recognition accuracy.

Task-driven semantic video/image coding has drawn considerable attention with the development of intelligent media applications, such as license plate detection, face detection, and medical diagnosis, which focuses on maintaining the semantic information of videos/images. Deep neural network (DNN)-based codecs have been studied for this purpose due to their inherent end-to-end optimization mechanism. However, the traditional hybrid coding framework cannot be optimized in an end-to-end manner, which makes task-driven semantic fidelity metric unable to be automatically integrated into the rate-distortion optimization process. Therefore, it is still attractive and challenging to implement task-driven semantic coding with the traditional hybrid coding framework, which should still be widely used in practical industry for a long time. To solve this challenge, we design semantic maps for different tasks to extract the pixelwise semantic fidelity for videos/images. Instead of directly integrating the semantic fidelity metric into traditional hybrid coding framework, we implement task-driven semantic coding by implementing semantic bit allocation based on reinforcement learning (RL). We formulate the semantic bit allocation problem as a Markov decision process (MDP) and utilize one RL agent to automatically determine the quantization parameters (QPs) for different coding units (CUs) according to the task-driven semantic fidelity metric. Extensive experiments on different tasks, such as classification, detection and segmentation, have demonstrated the superior performance of our approach by achieving an average bitrate saving of 34.39% to 52.62% over the High Efficiency Video Coding (H.265/HEVC) anchor under equivalent task-related semantic fidelity.