Neural Network Based Face Detection Research Articles

An automatic screening method for strabismus detection based on image processing.

PurposeThis study aims to provide an automatic strabismus screening method for people who live in remote areas with poor medical accessibility.Materials and methodsThe proposed method first utilizes a pretrained convolutional neural network-based face-detection model and a detector for 68 facial landmarks to extract the eye region for a frontal facial image. Second, Otsu’s binarization and the HSV color model are applied to the image to eliminate the influence of eyelashes and canthi. Then, the method samples all of the pixel points on the limbus and applies the least square method to obtain the coordinate of the pupil center. Lastly, we calculated the distances from the pupil center to the medial and lateral canthus to measure the deviation of the positional similarity of two eyes for strabismus screening.ResultWe used a total of 60 frontal facial images (30 strabismus images, 30 normal images) to validate the proposed method. The average value of the iris positional similarity of normal images was smaller than one of the strabismus images via the method (p-value<0.001). The sample mean and sample standard deviation of the positional similarity of the normal and strabismus images were 1.073 ± 0.014 and 0.039, as well as 1.924 ± 0.169 and 0.472, respectively.ConclusionThe experimental results of 60 images show that the proposed method is a promising automatic strabismus screening method for people living in remote areas with poor medical accessibility.

Single-Shot Scale-Aware Network for Real-Time Face Detection

In this work, we describe a single-shot scale-aware convolutional neural network based face detector (SFDet). In comparison with the state-of-the-art anchor-based face detection methods, the main advantages of our method are summarized in four aspects. (1) We propose a scale-aware detection network using a wide scale range of layers associated with appropriate scales of anchors to handle faces with various scales, and describe a new equal density principle to ensure anchors with different scales to be evenly distributed on the image. (2) To improve the recall rates of faces with certain scales (e.g., the scales of the faces are quite different from the scales of designed anchors), we design a new anchor matching strategy with scale compensation. (3) We introduce an IoU-aware weighting scheme for each training sample in classification loss calculation to encode samples accurately in training process. (4) Considering the class imbalance issue, a max-out background strategy is used to reduce false positives. Several experiments are conducted on public challenging face detection datasets, i.e., WIDER FACE, AFW, PASCAL Face, FDDB, and MAFA, to demonstrate that the proposed method achieves the state-of-the-art results and runs at 82.1 FPS for the VGA-resolution images.

FaceHunter: A multi-task convolutional neural network based face detector

In this paper, we propose a new multi-task Convolutional Neural Network (CNN) based face detector, which is named FaceHunter for simplicity. The main idea is to make the face detector achieve a high detection accuracy and obtain much reliable face boxes. Reliable face boxes output will be much helpful for further face image analysis. To reach this goal, we design a deep CNN network with a multi-task loss, i.e., one is for discriminating face and non-face, and another is for face box regression. An adaptive pooling layer is added before full connection to make the network adaptive to variable candidate proposals, and the truncated SVD is applied to compress the parameters of the fully connected layers. To further speed up the detector, the convolutional feature map is directly used to generate the candidate proposals by using Region Proposal Network (RPN). The proposed FaceHunter is evaluated on the AFW dataset, FDDB dataset and Pascal Faces respectively, and extensive experiments demonstrate its powerful performance against several state-of-the-art detectors.

A Real-time Model for Multiple Human Face Tracking from Low-resolution Surveillance Videos

This article discusses a novel approach of multiple-face tracking from low-resolution surveillance videos. There has been significant research in the field of face detection using neural-network based training. Neural network based face detection methods are highly accurate, albeit computationally intensive. Hence neural network based approaches are not suitable for real-time applications. The proposed approach approximately detects faces in an image solely using the color information. It detects skin region in an image and finds existence of eye and mouth region in the skin region. If it finds so, it marks the skin region as a face and fits an oriented rectangle to the face. The approach requires low computation and hence can be applied on subsequent frames from a video. The proposed approach is tested on FERET face database images, on different images containing multiple faces captured in unconstrained environments, and on frames extracted from IP surveillance camera.

Appearance-based face detection with artificial neural networks

The rapid and successful detection of a face in an image is a prerequisite to a fully automated face recognition system. A new neural network-based face detection system is presented, which is the outcome of a comparative study of two neural network models of different architecture and complexity. The fundamental difference in the construction of the two models is the need to address the problem either by using a general solution based on the full-face image or by composing the solution through the resolution of specific characteristics of the face. The algorithm is based on the assumption that there exists contrast in brightness between specific regions of the human face. The proposed neural network system is reliable and of reduced error rate. Specifically, we show that the second approach, even though more complicated, exhibits better performance in terms of detection and false - positive rates. Moreover, it can detect successfully faces that are slightly rotated out of the image plane.

Human face detection with neural networks and the DIRECT algorithm

Based on Rowley’s approach, this article proposes a new architecture that uses a specific optimization technique, the DIRECT (DIviding RECTangle) algorithm, to improve the efficiency of face detection in images. The system consists of two main parts: a neural network-based face detection arbitrator, and a search strategy based on an integer-handling DIRECT algorithm. By the architecture, the number of arbitrations is dramatically reduced, and human faces, if they are present in an image, are not restricted to predetermined resolutions and aspect ratios. Experimental results show that the proposed architecture is efficient in terms of both speed and robustness.

IDENTIFYING INDIVIDUALS FROM A VIDEO SEQUENCE BY COMBINATION OF DCT AND ARTIFICIAL NEURAL NETWORKS

The goal of this project is to create neural network-based face detection system to identify people from a video sequence. A database containing the images of the people to be identified in the video sequence is created. Using the face detection code the faces inside the video sequence are cropped for recognition. It will eliminate background influence as much as possible. The face space is described by a set of feature vectors obtained using the discrete cosine transform (DCT).This DCT feature vector is then fed into Artificial Neural Networks(ANN) which are used to recognize the faces through learning correct classification.

A Multiobject Tracking Framework for Interactive Multimedia Applications

Automatic initialization and tracking of multiple people and their body parts is one of the first steps in designing interactive multimedia applications. The key problems in this context are robust detection and tracking of people and their body parts in an unconstrained environment. This paper presents an integrated framework to address detection and tracking of multiple objects in a computationally efficient manner. In particular, a neural network-based face detector was employed to detect faces and compute person specific statistical model for skin color from the face regions. A probabilistic model was proposed to fuse the color and motion information to localize the moving body parts (hands). Multiple hypothesis tracking (MHT) algorithm was adopted to track face and hands. In real world scenes extracted features (face and hands) usually contain spurious measurements that create unconvincing trajectories and needless computations. To deal with this problem a path coherence function was incorporated along with MHT to reduce the number of hypotheses, which in turn reduces the computational cost and improves the structure of trajectories. The performance of the framework was validated using experiments on synthetic and real sequence of images.

Combining Genetic Search into Neural Network Based Face Detection

Combining Genetic Search into Neural Network Based Face Detection

Neural network-based face detection

We present a neural network-based upright frontal face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We present a straightforward procedure for aligning positive face examples for training. To collect negative examples, we use a bootstrap algorithm, which adds false detections into the training set as training progresses. This eliminates the difficult task of manually selecting nonface training examples, which must be chosen to span the entire space of nonface images. Simple heuristics, such as using the fact that faces rarely overlap in images, can further improve the accuracy. Comparisons with several other state-of-the-art face detection systems are presented, showing that our system has comparable performance in terms of detection and false-positive rates.