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.


HOG optimization results (RFD with 8 expressions): the x-axis reports the cell size in pixel and the y-axis refers to the average recall percentage
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

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

Fig11: HOG optimization results (RFD with 8 expressions): the x-axis reports the cell size in pixel and the y-axis refers to the average recall percentage

Mentions: In this subsection, the optimization of the HOG parameters (already carried out for the 6-expressions CK+ dataset and reported in "Experimental results: phase 1") is extended to the remaining 3 datasets described in "Experimental data setup": the CK+ with 7 expressions and the RFD with 7 and 8 expressions. This experimental step was carried out in order to verify that the best configuration of HOG parameters revealed in "Experimental results: phase 1" keeps still valid also for a different testing set. The plots relative to the 3 related additional experiments are shown in Figs. 9, 10 and 11 and they demonstrate that a cell size of 7 pixels and 7 orientation bins is again the best HOG parameters configuration to obtain the highest FER performance. This is a very important result, since it allows the proposed pipeline to be used without any initial parameter setting, even in the presence of different operative contexts. In other words, given the preliminary image registration, the FER proposed solution becomes parameter independent and then suitable to be used as a black-box.Fig. 9


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

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

HOG optimization results (RFD with 8 expressions): the x-axis reports the cell size in pixel and the y-axis refers to the average recall percentage
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

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

Fig11: HOG optimization results (RFD with 8 expressions): the x-axis reports the cell size in pixel and the y-axis refers to the average recall percentage
Mentions: In this subsection, the optimization of the HOG parameters (already carried out for the 6-expressions CK+ dataset and reported in "Experimental results: phase 1") is extended to the remaining 3 datasets described in "Experimental data setup": the CK+ with 7 expressions and the RFD with 7 and 8 expressions. This experimental step was carried out in order to verify that the best configuration of HOG parameters revealed in "Experimental results: phase 1" keeps still valid also for a different testing set. The plots relative to the 3 related additional experiments are shown in Figs. 9, 10 and 11 and they demonstrate that a cell size of 7 pixels and 7 orientation bins is again the best HOG parameters configuration to obtain the highest FER performance. This is a very important result, since it allows the proposed pipeline to be used without any initial parameter setting, even in the presence of different operative contexts. In other words, given the preliminary image registration, the FER proposed solution becomes parameter independent and then suitable to be used as a black-box.Fig. 9

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.