Face Detection in Natural Scenes

Perception ◽  
1996 ◽  
Vol 25 (1_suppl) ◽  
pp. 67-67 ◽  
Author(s):  
H Hill ◽  
R Watt
Keyword(s):  
Face Detection ◽  
Face Processing ◽  
Feature Detection ◽  
Processing System ◽  
Decision Task ◽  
Natural Scenes ◽  
Natural Scene ◽  
Energy Models ◽  
The Face ◽  
And Performance

The first task of any face processing system is detection of the face. We studied how the human visual system achieves face detection using a 2AFC task in which subjects were required to detect a face in the image of a natural scene. Luminance noise was added to the stimuli and performance was measured as a function of orientation and orientation bandwidth of the noise. Sensitivity levels and the effects of orientation bandwidth were similar for horizontally and vertically oriented noise. Performance was reduced for the smallest orientation bandwidth (5.6°) noise but sensitivity did not decrease further with increasing bandwidth until a point between 45° and 90°. The results suggest that important information may be oriented close to the vertical and horizontal. To test whether the results were specific to the task of face detection the same noise was added to the images in a man-made natural decision task. Equivalent levels of noise were found to be more disruptive and the effect of orientation bandwidth was different. The results are discussed in terms of models of face processing making use of oriented filters (eg Watt and Dakin, 1993 Perception22 Supplement, 12) and local energy models of feature detection (Morrone and Burr, 1988 Proceedings of the Royal Society of London B235 221 – 245).

scholarly journals Greater sensitivity of the cortical face processing system to perceptually-equated face detection

2016 ◽  
Vol 1631 ◽  
pp. 13-21 ◽  
Author(s):  
S. Maher ◽  
T. Ekstrom ◽  
Y. Tong ◽  
L.D. Nickerson ◽  
B. Frederick ◽  
...  
Keyword(s):  
Face Detection ◽  
Face Processing ◽  
Processing System

scholarly journals Does Prosopagnosia Take the Eyes Out of Face Representations? Evidence for a Defect in Representing Diagnostic Facial Information following Brain Damage

2005 ◽  
Vol 17 (10) ◽  
pp. 1652-1666 ◽  
Author(s):  
Roberto Caldara ◽  
Philippe Schyns ◽  
Eugéne Mayer ◽  
Marie L. Smith ◽  
Frédéric Gosselin ◽  
...  
Keyword(s):  
Brain Damage ◽  
Face Processing ◽  
Processing System ◽  
Facial Information ◽  
Spatial Frequencies ◽  
The Face ◽  
Occipitotemporal Cortex ◽  
Response Classification ◽  
Unfamiliar Faces ◽  
Normal Controls

One of the most impressive disorders following brain damage to the ventral occipitotemporal cortex is prosopagnosia, or the inability to recognize faces. Although acquired prosopagnosia with preserved general visual and memory functions is rare, several cases have been described in the neuropsychological literature and studied at the functional and neural level over the last decades. Here we tested a brain-damaged patient (PS) presenting a deficit restricted to the category of faces to clarify the nature of the missing and preserved components of the face processing system when it is selectively damaged. Following learning to identify 10 neutral and happy faces through extensive training, we investigated patient PS's recognition of faces using Bubbles, a response classification technique that sampled facial information across the faces in different bandwidths of spatial frequencies [Gosselin, F., & Schyns, P. E., Bubbles: A technique to reveal the use of information in recognition tasks. Vision Research, 41, 2261-2271, 2001]. Although PS gradually used less information (i.e., the number of bubbles) to identify faces over testing, the total information required was much larger than for normal controls and decreased less steeply with practice. Most importantly, the facial information used to identify individual faces differed between PS and controls. Specifically, in marked contrast to controls, PS did not use the optimal eye information to identify familiar faces, but instead the lower part of the face, including the mouth and the external contours, as normal observers typically do when processing unfamiliar faces. Together, the findings reported here suggest that damage to the face processing system is characterized by an inability to use the information that is optimal to judge identity, focusing instead on suboptimal information.

Representations in learning new faces: Evidence from prosopagnosia

1996 ◽  
Vol 2 (3) ◽  
pp. 240-248 ◽  
Author(s):  
Michael R. Polster ◽  
Steven Z. Rapcsak
Keyword(s):  
Left Hemisphere ◽  
Face Processing ◽  
Processing System ◽  
Poor Performance ◽  
Facial Features ◽  
Study Phase ◽  
Learning Tasks ◽  
The Face ◽  
Feature Based ◽  
Pictorial Representations

AbstractWe report the performance of a prosopagnosic patient on face learning tasks under different encoding instructions (i.e., levels of processing manipulations). R.J. performs at chance when given no encoding instructions or when given “shallow” encoding instructions to focus on facial features. By contrast, he performs relatively well with “deep” encoding instructions to rate faces in terms of personality traits or when provided with semantic and name information during the study phase. We propose that the improvement associated with deep encoding instructions may be related to the establishment of distinct visually derived and identity-specific semantic codes. The benefit associated with deep encoding in R.J., however, was found to be restricted to the specific view of the face presented at study and did not generalize to other views of the same face. These observations suggest that deep encoding instructions may enhance memory for concrete or pictorial representations of faces in patients with prosopagnosia, but that these patients cannot compensate for the inability to construct abstract structural codes that normally allow faces to be recognized from different orientations. We postulate further that R.J.'s poor performance on face learning tasks may be attributable to excessive reliance on a feature-based left hemisphere face processing system that operates primarily on view-specific representations. (JINS, 1996, 2, 240–248.)

Fuzzy-Face

1998 ◽  
Vol 06 (03) ◽  
pp. 281-298 ◽  
Author(s):  
Terry Huntsberger ◽  
John Rose ◽  
Shashidhar Ramaka
Keyword(s):  
Face Processing ◽  
Gender Discrimination ◽  
Computational Models ◽  
Experimental Studies ◽  
Processing System ◽  
Facial Hair ◽  
Lighting Conditions ◽  
Face Images ◽  
The Face ◽  
Strong Motivation

The human face is one of the most important patterns our visual system receives. It establishes a person's identity and also plays a significant role in everyday communication. Humans can recognize familiar faces under varying lighting conditions, different scales, and even after the face has changed due to aging, hair style, glasses, or facial hair. Our ease at recognizing faces is a strong motivation for the investigation of computational models of face processing. This paper presents a newly developed face processing system called Fuzzy-Face that combines wavelet pre-processing of input with a fuzzy self-organizing feature map algorithm. The wavelet-derived face space is partitioned into fuzzy sets which are characterized by face exemplars and membership values to those exemplars. This system learns faces using relatively few training epochs, has total recall for faces it has been shown, generalizes to face images that are acquired under different lighting conditions, and has rudimentary gender discrimination capabilities. We also include the results of some experimental studies.

scholarly journals A causal relationship between face-patch activity and face-detection behavior

eLife ◽  
2017 ◽  
Vol 6 ◽  
Author(s):  
Srivatsun Sadagopan ◽  
Wilbert Zarco ◽  
Winrich A Freiwald
Keyword(s):  
Object Detection ◽  
Causal Relationship ◽  
Face Detection ◽  
Real World ◽  
Face Processing ◽  
Detection Task ◽  
Natural Scenes ◽  
Critical Importance ◽  
Primate Brain

The primate brain contains distinct areas densely populated by face-selective neurons. One of these, face-patch ML, contains neurons selective for contrast relationships between face parts. Such contrast-relationships can serve as powerful heuristics for face detection. However, it is unknown whether neurons with such selectivity actually support face-detection behavior. Here, we devised a naturalistic face-detection task and combined it with fMRI-guided pharmacological inactivation of ML to test whether ML is of critical importance for real-world face detection. We found that inactivation of ML impairs face detection. The effect was anatomically specific, as inactivation of areas outside ML did not affect face detection, and it was categorically specific, as inactivation of ML impaired face detection while sparing body and object detection. These results establish that ML function is crucial for detection of faces in natural scenes, performing a critical first step on which other face processing operations can build.

scholarly journals Efficient Face Recognition System for Operating in Unconstrained Environments

2021 ◽  
Vol 7 (9) ◽  
pp. 161
Author(s):  
Alejandra Sarahi Sanchez-Moreno ◽  
Jesus Olivares-Mercado ◽  
Aldo Hernandez-Suarez ◽  
Karina Toscano-Medina ◽  
Gabriel Sanchez-Perez ◽  
...  
Keyword(s):  
Real Time ◽  
Face Detection ◽  
High Speed ◽  
Learning Algorithm ◽  
Facial Recognition ◽  
Processing System ◽  
Recognition System ◽  
Support Vector ◽  
The Face ◽  
Facial Recognition System

Facial recognition is fundamental for a wide variety of security systems operating in real-time applications. Recently, several deep neural networks algorithms have been developed to achieve state-of-the-art performance on this task. The present work was conceived due to the need for an efficient and low-cost processing system, so a real-time facial recognition system was proposed using a combination of deep learning algorithms like FaceNet and some traditional classifiers like SVM, KNN, and RF using moderate hardware to operate in an unconstrained environment. Generally, a facial recognition system involves two main tasks: face detection and recognition. The proposed scheme uses the YOLO-Face method for the face detection task which is a high-speed real-time detector based on YOLOv3, while, for the recognition stage, a combination of FaceNet with a supervised learning algorithm, such as the support vector machine (SVM), is proposed for classification. Extensive experiments on unconstrained datasets demonstrate that YOLO-Face provides better performance when the face under an analysis presents partial occlusion and pose variations; besides that, it can detect small faces. The face detector was able to achieve an accuracy of over 89.6% using the Honda/UCSD dataset which runs at 26 FPS with darknet-53 to VGA-resolution images for classification tasks. The experimental results have demonstrated that the FaceNet+SVM model was able to achieve an accuracy of 99.7% using the LFW dataset. On the same dataset, FaceNet+KNN and FaceNet+RF achieve 99.5% and 85.1%, respectively; on the other hand, the FaceNet was able to achieve 99.6%. Finally, the proposed system provides a recognition accuracy of 99.1% and 49 ms runtime when both the face detection and classifications stages operate together.

scholarly journals Evaluating the organizational structure and specificity of network topology within the face processing system

2019 ◽  
Vol 40 (9) ◽  
pp. 2581-2595 ◽  
Author(s):  
Daniel B. Elbich ◽  
Peter C.M. Molenaar ◽  
K. Suzanne Scherf
Keyword(s):  
Organizational Structure ◽  
Network Topology ◽  
Face Processing ◽  
Processing System ◽  
The Face

scholarly journals Build-up of serial dependence in color working memory

2018 ◽  
Author(s):  
João Barbosa ◽  
Albert Compte
Keyword(s):  
Visual Features ◽  
Experimental Session ◽  
Natural Scenes ◽  
Strongly Correlated ◽  
Natural Scene ◽  
Serial Dependence ◽  
Natural Scene Statistics ◽  
Short Term ◽  
Total N ◽  
The Face

AbstractSerial dependence, how recent experiences bias our current estimations, has been described experimentally during delayed-estimation of many different visual features, with subjects tending to make estimates biased towards previous ones. It has been proposed that these attractive biases help perception stabilization in the face of correlated natural scene statistics as an adaptive mechanism, although this remains mostly theoretical. Color, which is strongly correlated in natural scenes, has never been studied with regard to its serial dependencies. Here, we found significant serial dependence in 6 out of 7 datasets with behavioral data of humans (total n=111) performing delayed-estimation of color with uncorrelated sequential stimuli. Consistent with a drifting memory model, serial dependence was stronger when referenced relative to previous report, rather than to previous stimulus. In addition, it built up through the experimental session, suggesting metaplastic mechanisms operating at a slower time scale than previously proposed (e.g. short-term synaptic facilitation). Because, in contrast with natural scenes, stimuli were temporally uncorrelated, this build-up casts doubt on serial dependencies being an ongoing adaptation to the stable statistics of the environment.

scholarly journals Spatiotemporal Dynamics of Covert Versus Overt Processing of Happy, Fearful and Sad Facial Expressions

2021 ◽  
Vol 11 (7) ◽  
pp. 942
Author(s):  
Antonio Maffei ◽  
Jennifer Goertzen ◽  
Fern Jaspers-Fayer ◽  
Killian Kleffner ◽  
Paola Sessa ◽  
...  
Keyword(s):  
Face Processing ◽  
Univariate Analysis ◽  
Processing System ◽  
Intermediate Stage ◽  
Task Demands ◽  
Event Related Potential ◽  
Voluntary Attention ◽  
Affective Content ◽  
Fearful Faces ◽  
The Face

Behavioral and electrophysiological correlates of the influence of task demands on the processing of happy, sad, and fearful expressions were investigated in a within-subjects study that compared a perceptual distraction condition with task-irrelevant faces (e.g., covert emotion task) to an emotion task-relevant categorization condition (e.g., overt emotion task). A state-of-the-art non-parametric mass univariate analysis method was used to address the limitations of previous studies. Behaviorally, participants responded faster to overtly categorized happy faces and were slower and less accurate to categorize sad and fearful faces; there were no behavioral differences in the covert task. Event-related potential (ERP) responses to the emotional expressions included the N170 (140–180 ms), which was enhanced by emotion irrespective of task, with happy and sad expressions eliciting greater amplitudes than neutral expressions. EPN (200–400 ms) amplitude was modulated by task, with greater voltages in the overt condition, and by emotion, however, there was no interaction of emotion and task. ERP activity was modulated by emotion as a function of task only at a late processing stage, which included the LPP (500–800 ms), with fearful and sad faces showing greater amplitude enhancements than happy faces. This study reveals that affective content does not necessarily require attention in the early stages of face processing, supporting recent evidence that the core and extended parts of the face processing system act in parallel, rather than serially. The role of voluntary attention starts at an intermediate stage, and fully modulates the response to emotional content in the final stage of processing.

Sign in / Sign up

Export Citation Format

Share Document