Limits...
Facial expression recognition and histograms of oriented gradients: a comprehensive study.

Carcagnì P, Del Coco M, Leo M, Distante C - Springerplus (2015)

Bottom Line: This paper proposes a comprehensive study on the application of histogram of oriented gradients (HOG) descriptor in the FER problem, highlighting as this powerful technique could be effectively exploited for this purpose.The first experimental phase was aimed at proving the suitability of the HOG descriptor to characterize facial expression traits and, to do this, a successful comparison with most commonly used FER frameworks was carried out.As a final phase, a test on continuous data streams was carried out on-line in order to validate the system in real-world operating conditions that simulated a real-time human-machine interaction.

View Article: PubMed Central - PubMed

Affiliation: National Research Council of Italy, Institute of Applied Sciences and Intelligent Systems, Via della Libertà, 3, 73010 Arnesano , LE Italy.

ABSTRACT
Automatic facial expression recognition (FER) is a topic of growing interest mainly due to the rapid spread of assistive technology applications, as human-robot interaction, where a robust emotional awareness is a key point to best accomplish the assistive task. This paper proposes a comprehensive study on the application of histogram of oriented gradients (HOG) descriptor in the FER problem, highlighting as this powerful technique could be effectively exploited for this purpose. In particular, this paper highlights that a proper set of the HOG parameters can make this descriptor one of the most suitable to characterize facial expression peculiarities. A large experimental session, that can be divided into three different phases, was carried out exploiting a consolidated algorithmic pipeline. The first experimental phase was aimed at proving the suitability of the HOG descriptor to characterize facial expression traits and, to do this, a successful comparison with most commonly used FER frameworks was carried out. In the second experimental phase, different publicly available facial datasets were used to test the system on images acquired in different conditions (e.g. image resolution, lighting conditions, etc.). As a final phase, a test on continuous data streams was carried out on-line in order to validate the system in real-world operating conditions that simulated a real-time human-machine interaction.

No MeSH data available.


Examples of expressions for the CK+ dataset. An Anger, Di Disgusted, Fe Fearful, Ha Happy, Ne Neutral, Sa Sad, Su Surprised
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4628009&req=5

Fig4: Examples of expressions for the CK+ dataset. An Anger, Di Disgusted, Fe Fearful, Ha Happy, Ne Neutral, Sa Sad, Su Surprised

Mentions: In order to extract, from the available sequences, a balanced (i.e. quite the same number of instances for each considered expression) subset of images containing expressive faces, the following images were selected: the last image for the sequences related to the expression of anger, disgust and happiness; the last image for the first 68 sequences related to expression of surprise; the last and the fourth from the last images for the sequences related to the expressions of fear and sadness. At the end, a subset of 347 images was obtained with the following distribution among the considered classes of expressions: anger (45), disgust (59), fear (50), happiness (69), sadness (56) and surprise (68). An additional configuration of the previous subset was also introduced in order to test the performance with 7 classes and in this case 60 facial images, with neutral expression, were added to the aforementioned ones. In the last years a new dataset for FER analysis, named as Radboud Faces Database (RFD) Langner et al. (2010), has been introduced. The dataset contains images of 67 subjects performing 8 facial expressions (anger, disgust, fear, happiness, contemptuous, sadness, surprise and neutral) with 3 gaze directions and 5 different face orientations. The frontal facial image, with frontal gaze direction, was selected for each subject. In this way 2 subsets were obtained: the first one with 7 expressions (anger, contemptuous, disgusted, fearful, happy, sad, surprised) for a total of 469 images and the second one where 67 instances of the neutral expression were added to the previous ones (for a total of 536 images). In Figs. 4 and 5 some examples in the considered subsets of images are reported.Fig. 4


Facial expression recognition and histograms of oriented gradients: a comprehensive study.

Carcagnì P, Del Coco M, Leo M, Distante C - Springerplus (2015)

Examples of expressions for the CK+ dataset. An Anger, Di Disgusted, Fe Fearful, Ha Happy, Ne Neutral, Sa Sad, Su Surprised
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4628009&req=5

Fig4: Examples of expressions for the CK+ dataset. An Anger, Di Disgusted, Fe Fearful, Ha Happy, Ne Neutral, Sa Sad, Su Surprised
Mentions: In order to extract, from the available sequences, a balanced (i.e. quite the same number of instances for each considered expression) subset of images containing expressive faces, the following images were selected: the last image for the sequences related to the expression of anger, disgust and happiness; the last image for the first 68 sequences related to expression of surprise; the last and the fourth from the last images for the sequences related to the expressions of fear and sadness. At the end, a subset of 347 images was obtained with the following distribution among the considered classes of expressions: anger (45), disgust (59), fear (50), happiness (69), sadness (56) and surprise (68). An additional configuration of the previous subset was also introduced in order to test the performance with 7 classes and in this case 60 facial images, with neutral expression, were added to the aforementioned ones. In the last years a new dataset for FER analysis, named as Radboud Faces Database (RFD) Langner et al. (2010), has been introduced. The dataset contains images of 67 subjects performing 8 facial expressions (anger, disgust, fear, happiness, contemptuous, sadness, surprise and neutral) with 3 gaze directions and 5 different face orientations. The frontal facial image, with frontal gaze direction, was selected for each subject. In this way 2 subsets were obtained: the first one with 7 expressions (anger, contemptuous, disgusted, fearful, happy, sad, surprised) for a total of 469 images and the second one where 67 instances of the neutral expression were added to the previous ones (for a total of 536 images). In Figs. 4 and 5 some examples in the considered subsets of images are reported.Fig. 4

Bottom Line: This paper proposes a comprehensive study on the application of histogram of oriented gradients (HOG) descriptor in the FER problem, highlighting as this powerful technique could be effectively exploited for this purpose.The first experimental phase was aimed at proving the suitability of the HOG descriptor to characterize facial expression traits and, to do this, a successful comparison with most commonly used FER frameworks was carried out.As a final phase, a test on continuous data streams was carried out on-line in order to validate the system in real-world operating conditions that simulated a real-time human-machine interaction.

View Article: PubMed Central - PubMed

Affiliation: National Research Council of Italy, Institute of Applied Sciences and Intelligent Systems, Via della Libertà, 3, 73010 Arnesano , LE Italy.

ABSTRACT
Automatic facial expression recognition (FER) is a topic of growing interest mainly due to the rapid spread of assistive technology applications, as human-robot interaction, where a robust emotional awareness is a key point to best accomplish the assistive task. This paper proposes a comprehensive study on the application of histogram of oriented gradients (HOG) descriptor in the FER problem, highlighting as this powerful technique could be effectively exploited for this purpose. In particular, this paper highlights that a proper set of the HOG parameters can make this descriptor one of the most suitable to characterize facial expression peculiarities. A large experimental session, that can be divided into three different phases, was carried out exploiting a consolidated algorithmic pipeline. The first experimental phase was aimed at proving the suitability of the HOG descriptor to characterize facial expression traits and, to do this, a successful comparison with most commonly used FER frameworks was carried out. In the second experimental phase, different publicly available facial datasets were used to test the system on images acquired in different conditions (e.g. image resolution, lighting conditions, etc.). As a final phase, a test on continuous data streams was carried out on-line in order to validate the system in real-world operating conditions that simulated a real-time human-machine interaction.

No MeSH data available.