Albert Cruz - Academia.edu (original) (raw)
Papers by Albert Cruz
Communication between humans is complex and is not limited to verbal signals; emotions are convey... more Communication between humans is complex and is not limited to verbal signals; emotions are conveyed with gesture, pose and facial expression. Facial Emotion Recognition and Analysis (FERA), the techniques by which non-verbal communication is quantified, is an ...
2014 Ieee International Conference on Image Processing, Oct 1, 2014
ABSTRACT Facial emotion recognition in unconstrained settings is a difficult task. They key probl... more ABSTRACT Facial emotion recognition in unconstrained settings is a difficult task. They key problems are that people express their emotions in ways that are different from other people, and, for large datasets, there are not enough examples of a specific person to model his/her emotion. A model for predicting emotions will not generalize well to predicting the emotions of a person who has not been encountered during the training. We propose a system that addresses these issues by matching a face video to references of emotion. It does not require examples from the person in the video being queried. We compute the matching scores without requiring fine registration. The method is called one-shot emotion score. We improve classification rate of interdataset experiments over a baseline system by 23% when training on MMI and testing on CK+.
Proceedings of the 4th International Conference on Affective Computing and Intelligent Interaction Volume Part Ii, Oct 9, 2011
Communication between humans is complex and is not limited to verbal signals; emotions are convey... more Communication between humans is complex and is not limited to verbal signals; emotions are conveyed with gesture, pose and facial expression. Facial Emotion Recognition and Analysis (FERA), the techniques by which non-verbal communication is quantified, is an ...
Bioinformatics grant DGE 0903667. Portions of this dissertation appeared in "Facial emotion recog... more Bioinformatics grant DGE 0903667. Portions of this dissertation appeared in "Facial emotion recognition with anisotropic inhibited Gabor energy histograms", "Vision and attention theory based sampling for continuous facial emotion recognition" and "Scorebased facial emotion recognition" by A. Cruz et al. © 2013, 2014 the IEEE. v To my parents, Amethyst C. Cureg and Roberto V. Cruz, and to Laura E. Blough for all the support and never doubting my brilliance, and to the memory of Suresh Kumar When facial emotion recognition is performed in unconstrained settings, humans outperform state-of-the-art algorithms. The major technical problems of a state-of-the-art system are that: (1) frames in the training data are used build a model for prediction of emotion, including the frames that are redundant or not necessary to describe a person's emotions. (2) The Gabor filter, a frequently used feature descriptor in the field of computer vision, captures background texture as important edge information when it is noise. Additionally, the amount of computer memory required to describe faces using the Gabor filter is undesirably high. (3) Most of the current algorithms do not generalize to unconstrained data because each person expresses his/her emotions in different ways, and the persons in the testing data are not the same persons encountered in the training data.
2012 19th Ieee International Conference on Image Processing, Sep 1, 2012
Facial emotion recognition from video is an exemplar case where both humans and computers underpe... more Facial emotion recognition from video is an exemplar case where both humans and computers underperform. In recent emotion recognition competitions, top approaches were using either geometric relationships that best captured facial dynamics or an accurate registration technique to develop appearance features. These two methods capture two different types of facial information similarly to how the human visual system divides information when perceiving faces. In this paper, we propose a biologically-inspired fusion approach that emulates this process. The efficacy of the approach is tested with the Audio/Visual Emotion Challenge 2011 data set, a non-trivial data set where state-of-the-art approaches perform under chance. The proposed approach increases classification rates by 18.5% on publicly available data.
Clinical Ophthalmology, 2013
To compare the visual acuity and quality of vision achieved with three widely-used intraocular le... more To compare the visual acuity and quality of vision achieved with three widely-used intraocular lenses (IOLs) in subjects with bilateral cataracts. This three-arm, parallel, prospective, partially masked, single-surgeon study randomized 78 subjects to receive bilateral Crystalens® Advanced Optics (AO) accommodating IOLs, AcrySof® IQ ReSTOR® +3.0 multifocal IOLs, or TECNIS® Multifocal IOLs. Examinations were assessed through days 120 to 180. The Crystalens AO group had statistically significantly better monocular and binocular, high-contrast (HC) and low-contrast (LC) uncorrected intermediate visual acuity, HC and LC distance-corrected intermediate visual acuity, and significantly fewer monocular and binocular halos and starbursts than did the ReSTOR and TECNIS groups. Monocular and binocular, HC and LC uncorrected near visual acuity exhibited no significant differences among the three lenses. For monocular and binocular HC distance-corrected near visual acuity, the Crystalens AO performed significantly better than the TECNIS and was not significantly different from the ReSTOR. For monocular and binocular LC distance-corrected near visual acuity, the Crystalens AO performed significantly better than both the ReSTOR and the TECNIS. Contrast sensitivity was clinically similar between groups. The Crystalens AO produced statistically fewer halos and starbursts. All three IOLs had excellent uncorrected acuity results at all distances and had good safety, confirming the established safety and effectiveness of these IOLs. Distance and near vision were similar between all three IOLs, and the Crystalens AO provided statistically significantly better intermediate vision.
IEEE Transactions on Affective Computing, 2014
Daimon, Apr 26, 2013
Psyche's notion in Aristotle offers an interpretative frame capable of gather up and nourish a gr... more Psyche's notion in Aristotle offers an interpretative frame capable of gather up and nourish a group of contemporary approaches that study the mind-body problem. The fact that Aristotle's notion of psyche, or soul, took into account vital functions that are not mental, as digestion or reproduction, makes easier an approach to the naturalistic, and at the same time non reductionist, theory of Aristotle about relations between mind and body. Nowadays, neuroscience studies have reopened this debate and have made necessary a new synthesis where different disciplines meet.
ROP1, a Rho family GTPase enzyme, activates the downstream target RIC4. RIC4 is an accurate repor... more ROP1, a Rho family GTPase enzyme, activates the downstream target RIC4. RIC4 is an accurate reporter of ROP1 activity, which is periodically localized at the apex of the plasma membrane in pollen tubes. It allows the positive feedback relationship between pollen tube growth and ROP1 activity to be established based on its observed behavior. It regulates the growth of filamentous
Themata Revista De Filosofia, 2012
Teaching,mathematical,reasoning,is a challenge,for most,result-oriented,teachers.,In general, man... more Teaching,mathematical,reasoning,is a challenge,for most,result-oriented,teachers.,In general, many strategies can be employed, including problem-based learning, technology-based learning, game-based learning, community-based learning, work- based learning, inquiry-based learning, project-based learning, team-based learning, web-based learning and participatory learning. However, none of these strategies may,address,the central,problem,of mistakes,made,with,inappropriate,application,of intuition,in mathematical,problem,solving. This paper,emphasizes,an agile method,of teaching,rapid,reconciliation,of intuition,and,controlled,mathematical,reasoning,to engineering,students,in order to overcome,inappropriate,use,of the intuitive,mode,of cognitive function. This emphasis
Lecture Notes in Computer Science, 2011
Communication between humans is complex and is not limited to verbal signals; emotions are convey... more Communication between humans is complex and is not limited to verbal signals; emotions are conveyed with gesture, pose and facial expression. Facial Emotion Recognition and Analysis (FERA), the techniques by which non-verbal communication is quantified, is an ...
Revista Del Congres Internacional De Docencia Universitaria I Innovacio, Mar 16, 2015
Page 1. Walden University COLLEGE OF MANAGEMENT AND TECHNOLOGY This is to certify that the doctor... more Page 1. Walden University COLLEGE OF MANAGEMENT AND TECHNOLOGY This is to certify that the doctoral dissertation by Albert P. Cruz has been found to be complete and satisfactory in all respects, and that any and all ...
2012 19th IEEE International Conference on Image Processing, 2012
Facial emotion recognition from video is an exemplar case where both humans and computers underpe... more Facial emotion recognition from video is an exemplar case where both humans and computers underperform. In recent emotion recognition competitions, top approaches were using either geometric relationships that best captured facial dynamics or an accurate registration technique to develop appearance features. These two methods capture two different types of facial information similarly to how the human visual system divides information when perceiving faces. In this paper, we propose a biologically-inspired fusion approach that emulates this process. The efficacy of the approach is tested with the Audio/Visual Emotion Challenge 2011 data set, a non-trivial data set where state-of-the-art approaches perform under chance. The proposed approach increases classification rates by 18.5% on publicly available data.
Communication between humans is complex and is not limited to verbal signals; emotions are convey... more Communication between humans is complex and is not limited to verbal signals; emotions are conveyed with gesture, pose and facial expression. Facial Emotion Recognition and Analysis (FERA), the techniques by which non-verbal communication is quantified, is an ...
2014 Ieee International Conference on Image Processing, Oct 1, 2014
ABSTRACT Facial emotion recognition in unconstrained settings is a difficult task. They key probl... more ABSTRACT Facial emotion recognition in unconstrained settings is a difficult task. They key problems are that people express their emotions in ways that are different from other people, and, for large datasets, there are not enough examples of a specific person to model his/her emotion. A model for predicting emotions will not generalize well to predicting the emotions of a person who has not been encountered during the training. We propose a system that addresses these issues by matching a face video to references of emotion. It does not require examples from the person in the video being queried. We compute the matching scores without requiring fine registration. The method is called one-shot emotion score. We improve classification rate of interdataset experiments over a baseline system by 23% when training on MMI and testing on CK+.
Proceedings of the 4th International Conference on Affective Computing and Intelligent Interaction Volume Part Ii, Oct 9, 2011
Communication between humans is complex and is not limited to verbal signals; emotions are convey... more Communication between humans is complex and is not limited to verbal signals; emotions are conveyed with gesture, pose and facial expression. Facial Emotion Recognition and Analysis (FERA), the techniques by which non-verbal communication is quantified, is an ...
Bioinformatics grant DGE 0903667. Portions of this dissertation appeared in "Facial emotion recog... more Bioinformatics grant DGE 0903667. Portions of this dissertation appeared in "Facial emotion recognition with anisotropic inhibited Gabor energy histograms", "Vision and attention theory based sampling for continuous facial emotion recognition" and "Scorebased facial emotion recognition" by A. Cruz et al. © 2013, 2014 the IEEE. v To my parents, Amethyst C. Cureg and Roberto V. Cruz, and to Laura E. Blough for all the support and never doubting my brilliance, and to the memory of Suresh Kumar When facial emotion recognition is performed in unconstrained settings, humans outperform state-of-the-art algorithms. The major technical problems of a state-of-the-art system are that: (1) frames in the training data are used build a model for prediction of emotion, including the frames that are redundant or not necessary to describe a person's emotions. (2) The Gabor filter, a frequently used feature descriptor in the field of computer vision, captures background texture as important edge information when it is noise. Additionally, the amount of computer memory required to describe faces using the Gabor filter is undesirably high. (3) Most of the current algorithms do not generalize to unconstrained data because each person expresses his/her emotions in different ways, and the persons in the testing data are not the same persons encountered in the training data.
2012 19th Ieee International Conference on Image Processing, Sep 1, 2012
Facial emotion recognition from video is an exemplar case where both humans and computers underpe... more Facial emotion recognition from video is an exemplar case where both humans and computers underperform. In recent emotion recognition competitions, top approaches were using either geometric relationships that best captured facial dynamics or an accurate registration technique to develop appearance features. These two methods capture two different types of facial information similarly to how the human visual system divides information when perceiving faces. In this paper, we propose a biologically-inspired fusion approach that emulates this process. The efficacy of the approach is tested with the Audio/Visual Emotion Challenge 2011 data set, a non-trivial data set where state-of-the-art approaches perform under chance. The proposed approach increases classification rates by 18.5% on publicly available data.
Clinical Ophthalmology, 2013
To compare the visual acuity and quality of vision achieved with three widely-used intraocular le... more To compare the visual acuity and quality of vision achieved with three widely-used intraocular lenses (IOLs) in subjects with bilateral cataracts. This three-arm, parallel, prospective, partially masked, single-surgeon study randomized 78 subjects to receive bilateral Crystalens® Advanced Optics (AO) accommodating IOLs, AcrySof® IQ ReSTOR® +3.0 multifocal IOLs, or TECNIS® Multifocal IOLs. Examinations were assessed through days 120 to 180. The Crystalens AO group had statistically significantly better monocular and binocular, high-contrast (HC) and low-contrast (LC) uncorrected intermediate visual acuity, HC and LC distance-corrected intermediate visual acuity, and significantly fewer monocular and binocular halos and starbursts than did the ReSTOR and TECNIS groups. Monocular and binocular, HC and LC uncorrected near visual acuity exhibited no significant differences among the three lenses. For monocular and binocular HC distance-corrected near visual acuity, the Crystalens AO performed significantly better than the TECNIS and was not significantly different from the ReSTOR. For monocular and binocular LC distance-corrected near visual acuity, the Crystalens AO performed significantly better than both the ReSTOR and the TECNIS. Contrast sensitivity was clinically similar between groups. The Crystalens AO produced statistically fewer halos and starbursts. All three IOLs had excellent uncorrected acuity results at all distances and had good safety, confirming the established safety and effectiveness of these IOLs. Distance and near vision were similar between all three IOLs, and the Crystalens AO provided statistically significantly better intermediate vision.
IEEE Transactions on Affective Computing, 2014
Daimon, Apr 26, 2013
Psyche's notion in Aristotle offers an interpretative frame capable of gather up and nourish a gr... more Psyche's notion in Aristotle offers an interpretative frame capable of gather up and nourish a group of contemporary approaches that study the mind-body problem. The fact that Aristotle's notion of psyche, or soul, took into account vital functions that are not mental, as digestion or reproduction, makes easier an approach to the naturalistic, and at the same time non reductionist, theory of Aristotle about relations between mind and body. Nowadays, neuroscience studies have reopened this debate and have made necessary a new synthesis where different disciplines meet.
ROP1, a Rho family GTPase enzyme, activates the downstream target RIC4. RIC4 is an accurate repor... more ROP1, a Rho family GTPase enzyme, activates the downstream target RIC4. RIC4 is an accurate reporter of ROP1 activity, which is periodically localized at the apex of the plasma membrane in pollen tubes. It allows the positive feedback relationship between pollen tube growth and ROP1 activity to be established based on its observed behavior. It regulates the growth of filamentous
Themata Revista De Filosofia, 2012
Teaching,mathematical,reasoning,is a challenge,for most,result-oriented,teachers.,In general, man... more Teaching,mathematical,reasoning,is a challenge,for most,result-oriented,teachers.,In general, many strategies can be employed, including problem-based learning, technology-based learning, game-based learning, community-based learning, work- based learning, inquiry-based learning, project-based learning, team-based learning, web-based learning and participatory learning. However, none of these strategies may,address,the central,problem,of mistakes,made,with,inappropriate,application,of intuition,in mathematical,problem,solving. This paper,emphasizes,an agile method,of teaching,rapid,reconciliation,of intuition,and,controlled,mathematical,reasoning,to engineering,students,in order to overcome,inappropriate,use,of the intuitive,mode,of cognitive function. This emphasis
Lecture Notes in Computer Science, 2011
Communication between humans is complex and is not limited to verbal signals; emotions are convey... more Communication between humans is complex and is not limited to verbal signals; emotions are conveyed with gesture, pose and facial expression. Facial Emotion Recognition and Analysis (FERA), the techniques by which non-verbal communication is quantified, is an ...
Revista Del Congres Internacional De Docencia Universitaria I Innovacio, Mar 16, 2015
Page 1. Walden University COLLEGE OF MANAGEMENT AND TECHNOLOGY This is to certify that the doctor... more Page 1. Walden University COLLEGE OF MANAGEMENT AND TECHNOLOGY This is to certify that the doctoral dissertation by Albert P. Cruz has been found to be complete and satisfactory in all respects, and that any and all ...
2012 19th IEEE International Conference on Image Processing, 2012
Facial emotion recognition from video is an exemplar case where both humans and computers underpe... more Facial emotion recognition from video is an exemplar case where both humans and computers underperform. In recent emotion recognition competitions, top approaches were using either geometric relationships that best captured facial dynamics or an accurate registration technique to develop appearance features. These two methods capture two different types of facial information similarly to how the human visual system divides information when perceiving faces. In this paper, we propose a biologically-inspired fusion approach that emulates this process. The efficacy of the approach is tested with the Audio/Visual Emotion Challenge 2011 data set, a non-trivial data set where state-of-the-art approaches perform under chance. The proposed approach increases classification rates by 18.5% on publicly available data.