Neonatal Facial Pain Assessment Combining Hand-Crafted and Deep Features

In this paper we evaluate the combination of hand-crafted and deep learning-based features for neonatal pain assessment. To this end we consider two hand-crafted descriptors, i.e. Local Binary Patterns (LBP) and Histogram of Oriented Gradients (HOG), and features extracted from two pre-trained Convolutional Neural Networks (CNNs). Experimental results on the publicly available Infant Classification Of Pain Expressions (COPE) database show competitive results compared to previous methods.

[1]  Sheryl Brahnam,et al.  Machine assessment of neonatal facial expressions of acute pain , 2007, Decis. Support Syst..

[2]  Loris Nanni,et al.  Neonatal Facial Pain Detection Using NNSOA and LSVM , 2008, IPCV.

[3]  Raimondo Schettini,et al.  Adaptive Color Constancy Using Faces , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Tal Hassner,et al.  Emotion Recognition in the Wild via Convolutional Neural Networks and Mapped Binary Patterns , 2015, ICMI.

[5]  Paolo Napoletano,et al.  Combining local binary patterns and local color contrast for texture classification under varying illumination. , 2014, Journal of the Optical Society of America. A, Optics, image science, and vision.

[6]  Paolo Napoletano,et al.  Illuminant Invariant Descriptors for Color Texture Classification , 2013, CCIW.

[7]  Paolo Napoletano,et al.  Intensity and color descriptors for texture classification , 2013, Electronic Imaging.

[8]  Sheryl Brahnam,et al.  Machine recognition and representation of neonatal facial displays of acute pain , 2006, Artif. Intell. Medicine.

[9]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Loris Nanni,et al.  A local approach based on a Local Binary Patterns variant texture descriptor for classifying pain states , 2010, Expert Syst. Appl..

[11]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[12]  Raimondo Schettini,et al.  Robust smile detection using convolutional neural networks , 2016, J. Electronic Imaging.

[13]  A. S. Malowany,et al.  Identification of pain from infant cry vocalizations using artificial neural networks (ANNs) , 1995, SPIE Defense + Commercial Sensing.

[14]  V. Lindh,et al.  Heel lancing in term new-born infants: an evaluation of pain by frequency domain analysis of heart rate variability , 1999, Pain.

[15]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[16]  Loris Nanni,et al.  Introduction to Neonatal Facial Pain Detection Using Common and Advanced Face Classification Techniques , 2007, Advanced Computational Intelligence Paradigms in Healthcare.

[17]  Andrew Zisserman,et al.  Deep Face Recognition , 2015, BMVC.

[18]  Davis E. King,et al.  Dlib-ml: A Machine Learning Toolkit , 2009, J. Mach. Learn. Res..

[19]  Mohd Nazri Rejab,et al.  A computational model of the infant pain impressions with Gaussian and Nearest Mean Classifier , 2013, 2013 IEEE International Conference on Control System, Computing and Engineering.

[20]  Paolo Napoletano,et al.  Local Angular Patterns for Color Texture Classification , 2015, ICIAP Workshops.

[21]  Corneliu Florea,et al.  Pain intensity estimation by a self-taught selection of histograms of topographical features , 2015, Image Vis. Comput..

[22]  Raimondo Schettini,et al.  Local detectors and compact descriptors for visual search: A quantitative comparison , 2015, Digit. Signal Process..