Upright Frontal Face Research Articles

Understanding face detection with visual arrays and real-world scenes

ABSTRACT Face detection has been studied by presenting faces in blank displays, object arrays, and real-world scenes. This study investigated whether these display contexts differ in what they can reveal about detection, by comparing frontal-view faces with those shown in profile (Experiment 1), rotated by 90° (Experiment 2), or turned upside-down (Experiment 3). In blank displays, performance for all face conditions was equivalent, whereas upright frontal faces showed a consistent detection advantage in arrays and scenes. Experiment 4 examined which facial characteristics drive this detection advantage by rotating either the internal or external facial features by 90° while the other features remained upright. Faces with rotated internal features were detected as efficiently as their intact frontal counterparts, whereas detection was impaired when external features were rotated. Finally, Experiment 5 applied Voronoi transformations to scenes to confirm that complexity of stimulus displays modulates the detection advantage for upright faces. These experiments demonstrate that context influences what can be learned about the face detection process. In complex visual arrays and natural scenes, detection proceeds more effectively when external facial features are preserved in an upright orientation. These findings are consistent with a cognitive detection template that focuses on general face-shape information.

Coupling RetinaFace and Depth Information to Filter False Positives

Face detection is an important problem in computer vision because it enables a wide range of applications, such as facial recognition and an analysis of human behavior. The problem is challenging because of the large variations in facial appearance across different individuals and lighting and pose conditions. One way to detect faces is to utilize a highly advanced face detection method, such as RetinaFace or YOLOv7, which uses deep learning techniques to achieve high accuracy in various datasets. However, even the best face detectors can produce false positives, which can lead to incorrect or unreliable results. In this paper, we propose a method for reducing false positives in face detection by using information from a depth map. A depth map is a two-dimensional representation of the distance of objects in an image from the camera. By using the depth information, the proposed method is able to better differentiate between true faces and false positives. The method proposed by the authors is tested on a dataset of 549 images, which includes 614 upright frontal faces. The outcomes of the evaluation demonstrate that the method effectively minimizes false positives without compromising the overall detection rate. These findings suggest that incorporating depth information can enhance the accuracy of face detection.

Face Detection Ensemble with Methods Using Depth Information to Filter False Positives.

A fundamental problem in computer vision is face detection. In this paper, an experimentally derived ensemble made by a set of six face detectors is presented that maximizes the number of true positives while simultaneously reducing the number of false positives produced by the ensemble. False positives are removed using different filtering steps based primarily on the characteristics of the depth map related to the subwindows of the whole image that contain candidate faces. A new filtering approach based on processing the image with different wavelets is also proposed here. The experimental results show that the applied filtering steps used in our best ensemble reduce the number of false positives without decreasing the detection rate. This finding is validated on a combined dataset composed of four others for a total of 549 images, including 614 upright frontal faces acquired in unconstrained environments. The dataset provides both 2D and depth data. For further validation, the proposed ensemble is tested on the well-known BioID benchmark dataset, where it obtains a 100% detection rate with an acceptable number of false positives.

FACE RECOGNITION SYSTEM FOR MACHINE READABLE TRAVEL DOCUMENTS

This paper presents an upright frontal face recognition system, aimed to recognize faces on machine readable travel documents (MRTD). The system is able to handle large image databases with high processing speed and low detection and identification errors. In order to achieve high accuracy eyes are detected in the most probable regions, which narrows search area and therefore reduces computation time. Recognition is performed with the use of eigenface approach. The paper introduces eigenface basis ranking measure, which is helpful in challenging task of creating the basis for recognition purposes. To speed up identification process we split the database into males and females using high - performance AdaBoost classifier. At the end of the paper the results of the tests in speed and accuracy are given.

A novel two-stage weak classifier selection approach for adaptive boosting for cascade face detector

It is well-known for AdaBoost to select out the optimal weak classifier with the least sample-weighted error rate, which might be suboptimal for minimizing the naïve error rate. In this paper, a novel variant of AdaBoost named OtBoost is proposed to learn optimal thresholded node classifiers for cascade face detector. In OtBoost, a two-stage weak classifier selection approach based on adaptive boosting framework is applied to minimize both the sample-weighted error rate and the optimal-thresholded multi-set class-weighted error rate. Besides, a new sample set called selection set is also applied to prevent overfitting on the training set. Several upright frontal cascade face detectors are learned, which shows that the OtBoost strong classifiers have much better convergence ability than the AdaBoost ones with the cost of slightly worse generalization ability. Some OtBoost based cascade face detectors have acceptable performance on the CMU+MIT upright frontal face test set.

I know this face: Neural activity during mother' face perception in 7- to 8-month-old infants as investigated by near-infrared spectroscopy

Previously, we used near-infrared spectroscopy (NIRS) to measure infant's brain activity during face processing by detecting changes in hemodynamic responses, oxy-Hb, deoxy-Hb, and total-Hb concentrations [1,2]. We found that the right temporal cortex of the brain was activated when infants looked at upright frontal faces rather than inverted faces, and at the frontal view as well as the profile view on 8-month-olds. In the present study, we investigated 7- and 8-month-olds' brain activity related to the perception of mother's and stranger's faces by NIRS. The finding was that oxy-Hb and total-Hb concentrations in the right temporal cortex increased against the baseline during presentation of the mother's face. For strangers' faces, the total-Hb concentration in the right temporal cortex was greater than the baseline. By contrast, oxy- and total-Hb concentrations in the left temporal cortex increased only in the presentation of mother's face. The great activity in the right temporal region for faces irrespective of familiarity was consistent with a predominance of the right temporal cortex found previously in infants [1,2] as well as functional magnetic resonance imaging (fMRI) studies in adults [3,4]. In contrast to the activity in the right temporal cortex, the greater hemodynamic response in the left temporal cortex was observed only in the mother's face condition. These findings suggest that the processing of the mother's face enhances activity in bilateral temporal cortex. This is the first study to clarify the location of brain activity in infants related to the perception of their mother's face.

A multi-expert approach for wavelet-based face detection

In this work we present an upright frontal face detection system based on the multi-resolution analysis of the face. The images are decomposed into frequency sub-bands with different levels decomposition using different wavelets. We propose to use a multi-matcher where each matcher (a Radial Basis Function Support Vector Machine) is trained using a different set of features (a given sub-band or the gray values) projected onto a lower subspace by Laplacian Eigenmaps, the matchers are combined using the “Sum Rule”. The matcher selection is performed by running Sequential Forward Floating Selection. To speed up the detection, an eye detector is used to find the position of the most probable face. Among these sub-windows only the sub-windows that are classified, by the matcher trained using gray values, as “face” are classified by the multi-matcher.

Orientation analysis for rotated human face detection

In this paper, we present a framework of orientation analysis for rotated human face detection. A novel orientation histogram is constructed for statistical analysis of face images, which can show a proper symmetry with respect to the orientation of the principal axis and a local peak at its orthogonal orientation. By analyzing the orientation histogram, we can easily find the principal axis' orientation of the rotated face. Then an upright frontal face detector based on orientation analysis and other knowledge is designed to verify the given face. The experimental results illustrate the effectiveness of our framework.

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.