Smile detection in the wild with deep convolutional neural networks

Chen, Junkai; Ou, Qihao; Chi, Zheru; Hong, Fei

doi:10.1007/s00138-016-0817-z

Cited by 57 publications

(50 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some of the previous methods manually process the input image to detect the face (when an automatic detector fails) [13] or register the face based on the eye positions [21]. Prior studies that do not provide the details of the methods they utilise for face detection [21,31] and registration [3,10,13] remain questionable in terms of manual interventions to the input image.…”

Section: Related Workmentioning

confidence: 99%

“…Therefore, an increasing number of studies have focused on smile detection instead of the recognition of the six basic emotions of happiness, sadness, surprise, anger, fear and disgust. Research on smile detection is mainly divided into two categories, using learned convolution filters [3,11,31] based on deep learning, or using hand-crafted visual features [10,13,14,21]. In the best performing methods, the extracted features are combined with deep learning (CNN) classifiers [11,31] or other machine learning techniques, such as Support Vector Machine (SVM) [10,14], AdaBoost [3,21], and Extreme Learning Machine [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SmileNet: Registration-Free Smiling Face Detection In The Wild

Jang

Güneş

Patras

2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

We present a novel smiling face detection framework called SmileNet for detecting faces and recognising smiles in the wild. SmileNet uses a Fully Convolutional Neural Network (FCNN) to detect multiple smiling faces in a given image of varying resolution. Our contributions are threefold: 1) SmileNet is the first smiling face detection network that does not require pre-processing such as face detection and registration in advance to generate a normalised (cropped and aligned) input image; 2) the proposed SmileNet is a simple and single FCNN architecture simultaneously performing face detection and smile recognition, which are conventionally treated as separate consecutive pipelines; and 3) SmileNet ensures real-time processing speed (21.15 FPS) even when detecting multiple smiling faces in a given image (300 × 300). Experimental results show that SmileNet can deliver state-of-the-art performance (95.76%), even under occlusions, and variances of pose, scale, and illumination.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

SmileNet: Registration-Free Smiling Face Detection In The Wild

Jang

Güneş

Patras

2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

show abstract

“…A soft voting criteria is defined for the prediction of multiple neural networks (NN), claiming an average error of 2.8 meters. In this sense, convolutional neural networks (CNN), which are commonly used to classify images [23][24][25], are proposed to develop ILS. Al-homayani et al [26] propose the use of CNNs to develop an ILS, using a smartphone as sensor and a matrix of magnetic data points as CNN input.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Indoor Location Through Magnetic Field Data: An Approach Based On Convolutional Neural Networks

Galván-Tejada

Zanella-Calzada

García-Domínguez

et al. 2020

IJGI

View full text Add to dashboard Cite

Estimation of indoor location represents an interesting research topic since it is a main contextual variable for location bases services (LBS), eHealth applications and commercial systems, among others. For instance, hospitals require location data of their employees, as well as the location of their patients to offer services based on these locations at the correct moments of their needs. Several approaches have been proposed to tackle this problem using different types of artificial or natural signals (i.e., wifi, bluetooth, rfid, sound, movement,etc).In this work, it is proposed the development of an indoor location estimator system, relying in the data provided by the magnetic field of the rooms, which has been demonstrated that is unique and quasi-stationary. For this purpose, it is analyzed the spectral evolution of the magnetic field data viewed as a bidimensional heatmap, avoiding temporal dependencies. A Fourier transform is applied to the bidimensional heatmap of the magnetic field data to feed a convolutional neural network (CNN) to generate a model to estimate the user's location in a building. The evaluation of the CNN model to deploy an indoor location system (ILS) is done through measuring the Receiver Operating Characteristic (ROC) curve to observe the behavior in terms of sensitivity and specificity. Our experiments achieve a 0.99 Area Under the Curve (AUC) in the training data-set and a 0.74 in a total blind data set.

show abstract

“…Deep learning convolutional neural networks [24,25], inspired by the primate visual cortex [26], have gained much interest in the past few years, owing to their ability to classify a vast number of objects, with a certain probability (confidence percentage), that outperforms the capability of humans [27,28]. These types of networks have been implemented in real-time [23] and have been used in areas such as speech recognition [29], facial recognition [30], smile detection [31], video classification [32] and for identifying the songs of different birds [33,34]. The ability to remotely update neural networks without requiring hardware modifications (and with minimal local processing power) is potentially cost effective and advantageous for global distribution [35].…”

Section: Introductionmentioning

confidence: 99%

Fibre-optic based particle sensing via deep learning

et al. 2019

View full text Add to dashboard Cite

We demonstrate the capability for the identification of single particles, via a neural network, directly from the backscattered light collected by a 30-core optical fibre, when particles are illuminated using a single mode fibre-coupled laser light source. The neural network was shown to be able to determine the specific species of pollen with ∼97% accuracy, along with the distance between the end of the 30core sensing fibre and the particles, with an associated error of±6 μm. The ability to be able to classify particles directly from backscattered light using an optical fibre has potential in environments in which transmission imaging is neither possible nor suitable, such as sensing over opaque media, in the deep sea or outer space.

show abstract

Smile detection in the wild with deep convolutional neural networks

Cited by 57 publications

References 28 publications

SmileNet: Registration-Free Smiling Face Detection In The Wild

SmileNet: Registration-Free Smiling Face Detection In The Wild

Estimation of Indoor Location Through Magnetic Field Data: An Approach Based On Convolutional Neural Networks

Fibre-optic based particle sensing via deep learning

Contact Info

Product

Resources

About