An area efficient FPGA implementation of moving object detection and face detection using adaptive threshold method

A hierarchical learning network for face detection with in-plane rotation

For face detection and tracking in a video sequence, many systems are now applying a technique to extract skin-color areas of faces. In these systems, the skin-color model should be built beforehand. However the skin-color changes when the lighting condition varies, when an input video camera is changed, and when the white-balance of the camera is readjusted, etc. We describe a method to a build a skin-color model for operation while a face detection system is running. When it has no skin-color model, it uses the differences between adjacent frames to extract moving objects. Once the system recognizes that the moving object is a face, it analyses the color histograms of the moving area and extract skin-color distribution. We applied this method to our face detection and tracking system. Experiments showed good results.

Moving object detection is an important and basic step in any video surveillance application. Detected object has used an input to higher level tasks such as tracking, event detection, and behavioral analysis. There are several challenges in moving object detection such as illumination changes, occlusion, shadow, bootstrap, dynamic background etc. Detection of moving object having similar color as background structure is called as camouflage, which is another big challenge. The method of detecting camouflage moving object is known as Decamouflaging. In recent years, the researchers are attracted towards the camouflage moving object detection due to its application in the military. In this review paper, different techniques using various features for camouflaged moving obj ect detection were studied.

The issue of human error, inaccurate and time-consuming of manual attendance system gradually magnified the inefficiency and obsolescence of the system. An automatic attendance management system with face detection will increase the efficiency, accuracy, and security of a system in attendance taking task. Real-Time Face Detection Attendance Management System is concerned in finding human faces through real-time with the attendance taken and saved as reference for future. Face detection system is implemented by using Haar Cascades Classifiers for the object detection. Attendance system is managed with a database management system called MySQL using SQL programming language. Real-Time Face Detection Attendance Management System able to detect front face and manage the attendance in real-time. A text box will display for the attendee to enter their name for the purpose of attendance taken when face is detected. The attendance list and image collection in the database will auto increment and update in MySQL. The accuracy of Real-Time Face Detection Attendance Management System is shown with the comparison between different front face condition in different illumination condition. The result is tested with 4 sets of the attendee’s face in different illumination and different front face condition. 94.44% accuracy of the face detection system is shown from the result taken by the system. The image acquisition for every attendee is collected and saved in the right folder. The attendance is taken with the attendee’s name, date and time in attendance database and image is save into face database. Some technology such as anti-spoofing measures, mask detection and deep learning concept are recommended to be added into the system for future improvement

The purpose of this chapter is to describe the application of the problem solving ontology component of HCVM in the area of face detection and annotation. computer-based aspects of an embedded feature-based multi-agent face detection and annotation system are described in this chapter. Unlike similar feature-based systems that start from searching for facial organs in the images and group them to find faces, the system solves the problem using the problem solving agents of the HCVM in a top-down fashion. The embedded mtilti-agent face detection system makes hypotheses of face locations and seeks evidences to verify them. The five problem solving agents follow a coarse grain to fine grain methodology and work on various features of color images. The coarse to fine top-down methodology is more akin to human perceptions than a bottom-up approach. The higher level problem solving agents like decomposition work as background knowledge for the control and decision agents resulting in improvement of the accuracy and speed of detection. It is also distinct from many other top-down systems in that no re-scaling of the images is needed in the searching process. To improve the detection rate, a unique iterative region-partitioning algorithm is developed in this multi-agent system. The problem solving agents model aspects related to skin-tone region segmentation, noise reduction, candidate face regions location and facial feature extraction/face detection, and annotation. The detection algorithm is invariant to scale and rotation to some degree. The performance of the multi-agent system has been tested with a large number of images and the results obtained thus far are very encouraging.

This paper describes the design and development of an Arduino-powered face identification and tracking robot that is lightweight, affordable, and highly effective. The project aimed to implement face detection using a mobile camera that moves along with the face with the help of servo motors. The application was built using android processing and it uses Bluetooth connectivity to connect with the Arduino board to change the positions and dimensions of camera angles. The system showed that, in appropriate illumination circumstances, its face detection system could successfully identify and track faces using the Viola-Jones algorithm. A key element of the system was the Tilt and Robotic Arm, which allowed the camera module to be adjusted in present-time to maintain the face centered of the video stream. It has potential to be used in human-computer interface systems, security and surveillance systems, and systems for detecting sleepy drivers using this technology. Future plans include expanding the functionality of the robot by adding facial recognition technology and improving the robustness and reliability of the system by optimizing the detection and tracking algorithms and using more advanced hardware components. Overall, the project demonstrates the potential of face detection and tracking robots for revolutionizing the way we interact with technology and each other.

Face detection systems are used in various computer vision-based applications such as biometrics, security, surveillance, etc. Computationally immoderate face detection methods may not be convenient for devices with inadequate resources. On the other hand, an appropriate face detection approach should be considered in order to achieve high accuracy and substantial performance. This paper deliberates different methods of facial detection and contrasts them to find a better approach for a robust facial recognition system. Five methods of face detection were used in this comparison namely, ViolaJones, Histogram of Oriented Gradient with Support Vector Machine (HOG-SVM), Multi-task Cascaded Convolutional Network (MTCNN), Single Shot Multibox Detector (SSD) and Maxmargin Object Detection (MMOD). Each method was evaluated by varying illumination intensity, angle of the face, the scale of the face and different occlusion types. Video data and WIDERFACE image samples were used for the analysis. Obtained experimental results depict that SSD performs better on the task of face detection with high accuracy and performance, while MMOD has the lowest performance and Viola-Jones gives the lowest accuracy.

The aims of this paper is to propose a novel method for solving problem face detection and tracking system based in four algorithms: block-matching (BMA), Meanshift, Camshift and Kalman filter. Firstly, BMA is applied to the different sequential test as a preprocessing stage to detect faces. Then, the face tracking system are with three modules: Meanshift, Camshift and Kalman filter. This scheme gives a better face detection and tracking. Our work increases the performance and other criteria values in the embedded system. The human is more and more interested in producing intelligence which is one of the most impressive features of natures. Researchers are trying to make intelligent machine that have various capabilities. Building a machine or robot is probably one of the most challenging problems which humans are trying to solve. Recently, many projects have started with the purpose of learning machines to track some particular objects. One of the most challenging applications in computer vision is tracking objects efficiently in video sequence. Though progress has been accomplished, the best algorithms are far from reaching the speed and the performance of system. Object or multi-object tracking (face, human, car, etc.) is a fundamental problem that merits particular attention, since it is the key to solve a number of computer vision applications.

In recent years, the numbers of Visual Surveillance systems have greatly increased, and these systems have developed into intellectual systems that automatically detect, track, and recognize objects in video. Automatic moving object detection and tracking is a very challenging task in video surveillance applications. In this regard, many methods have been proposed for Moving Object Detection and Tracking based on edge, color, texture information. Due to unpredictable characteristics of objects in foggy videos, the task of object detection remains a challenging problem. In this paper, we propose a novel scheme for moving object detection based on Log Gabor filter (LGF) and Dominant Eigen Map (DEM) approaches. Location of the moving object is obtained by performing connected component analysis. In turn, a Moving Object is Tracked based on the centroid manipulation. Number of experiments is performed using indoor and outdoor video sequences. The proposed method is tested on standard PETS datasets and many real time video sequences. Results obtained are satisfactory and are compared with existing well known traditional methods.

This letter presents hyperspectral image segmentation based on the phase-correlation measure and updating the segments using a post processing operation based on adaptive thresholding. Spectral signature of each pixel is subsampled to gain robustness against noise and spatial variability, and phase correlation is performed to measure spectral similarity. Similar and dissimilar pixels are decided according to the peak value of the phase correlation result to determine pixels that fall into the same segments. An adaptive threshold value that is determined for each segment considering in-segment similarity distribution is used to update the segment. Segmentation accuracy is increased compared to phase correlation based segmentation.

This paper introduces a new speech enhancement algorithm based on the adaptive threshold of intrinsic mode functions (IMFs) of noisy signal frames extracted by empirical mode decomposition. Adaptive threshold values are estimated by using the gamma statistical model of Teager energy operated IMFs of noisy speech and estimated noise based on symmetric Kullback–Leibler divergence. The enhanced speech signal is obtained by a semisoft thresholding function, which is utilized by threshold IMF coefficients of noisy speech. The method is tested on the NOIZEUS speech database and the proposed method is compared with wavelet-shrinkage and EMD-shrinkage methods in terms of segmental SNR improvement (SegSNR), weighted spectral slope (WSS), and perceptual evaluation of speech quality (PESQ). Experimental results show that the proposed method provides a higher SegSNR improvement in dB, lower WSS distance, and higher PESQ scores than wavelet-shrinkage and EMD-shrinkage methods. The proposed method shows better performance than traditional threshold-based speech enhancement approaches from high to low SNR levels.

In the paper, a practical method for road detection is proposed. Many features of vehicle are introduced to detect the preceding vehicles. According to the characteristics of lane marks and vehicles, the improved Sobel operator convolution kernel is introduced in the image preprocessing to enhance the robustness of the algorithm. In order to be feasible to the change of illumination and road conditions, the adaptive double threshold method is introduced to get the binary image, the edges which are needed during detection of lane marks and front vehicles are extracted with Hough Transformation and SUSAN algorithm based on adaptive threshold in different contrast ratio. In order to apply the information to implement the lane departure warming system and forward collision warming system, both distances from host vehicle to left and right lane lines and preceding vehicles are estimated according to the inverse projection. Experiment results indicate that this algorithm is feasible for different road conditions and can realize the detection and tracking of the lane lines and vehicles with robustness and efficiency simultaneously.

Visual detection and tracking of humans in complex scenes is a challenging problem with a wide range of applications, for example surveillance and human-computer interaction. In many such applications, time-synchronous views from multiple calibrated cameras are available, and both frame-view and space-level human location information is desired. In such scenarios, efficiently combining the strengths of face detection and person tracking is a viable approach that can provide both levels of information required and improve robustness. In this paper, we propose a novel vision system that detects and tracks human faces automatically, using input from multiple calibrated cameras. The method uses an Adaboost algorithm variant combined with mean shift tracking applied on single camera views for face detection and tracking, and fuses the results on multiple camera views to check for consistency and obtain the three-dimensional head estimate. We apply the proposed system to a lecture scenario in a smart room, on a corpus collected as part of the CHIL European Union integrated project. We report results on both frame-level face detection and three-dimensional head tracking. For the latter, the proposed algorithm achieves similar results with the IBM “PeopleVision” system.

Face detection is one of the most relevant applications of image processing and biometric systems. Artificial neural networks (ANN) have been used in the field of image processing and pattern recognition. There is lack of literature surveys which give overview about the studies and researches related to the using of ANN in face detection. Therefore, this research includes a general review of face detection studies and systems which based on different ANN approaches and algorithms. The strengths and limitations of these literature studies and systems were included also.

Face detection is a key problem in human-computer interaction. In this paper, we present an algorithm for rotation invariant face detection in color images of cluttered scenes. It is a hierarchical approach, which combines a skin color model, a neural network, and an upright face detector. Firstly, the skin color model is used to process the color image to segment the face-like regions from the background. Secondly, the neural network computing and an operation for locating irises are performed to acquire rotation angle of each input window in the face-like regions. Finally, we provide an upright face detector to determine whether or not the rotated window is a face. Those techniques are integrated into a face detection system. The experiments show that the algorithm is robust to different face sizes and various lighting conditions.