Publications by authors named "Parham Aarabi"

11 Publications

  • Page 1 of 1

Comparing the self-perceived effects of a facial anti-aging product to those automatically detected from selfie images of Chinese women of different ages and cities.

Skin Res Technol 2021 Sep 6;27(5):880-890. Epub 2021 Apr 6.

ModiFace, A L'Oréal Group Company, Toronto, ON, Canada.

Objective: To assess the agreement, after 1-month application of a popular and efficient anti-aging product, between self-perceived facial signs of aging and those detected and graded by an automatic A.I-based system, using smartphones' selfie images.

Material And Methods: Of 1065 Chinese women, aged 18-60 years, from eight different Chinese cities were recruited. They were asked to apply daily, for 1 month, a referential anti-aging product onto their whole face. Selfie images were taken by all subjects at D and D and sent to our facilities for being analyzed through 10 different facial signs. At D , all subjects were asked to fill a questionnaire on the status of their faces, through six general statements.

Results: A global agreement between both approaches is reached, particularly among women older than 40 years where the severity of facial signs is already more pronounced or among younger women who present at least facial signs scored above one grading units. This limit becomes, therefore, a prerequisite in the recruitment of Chinese subjects in the case of anti-aging applied studies and possible automatically based on automatic grading system. When respecting such conditions, the positive effects of the product on most facial signs can be demonstrated after 28 days of successive applications.

Conclusion: Such methodological approach paves the road in fulfilling the need of consumers of a better transparency in the claims of an anti-aging product.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1111/srt.13037DOI Listing
September 2021

The Impact of Electrode Density and Precision on Brain-Computer Interfaces.

Annu Int Conf IEEE Eng Med Biol Soc 2020 07;2020:430-433

In this paper, we review several advances in different fields that provide new potential for brain-computer interfaces enabled by directly interfacing biological neural networks with electrodes, including recent successes with liquid injected conductive channels and mesh electronics supported by 3D scaffolds. Based on this review, it is clear that the success of biological neural connectivity is dependent on the precision and density of the inserted electrodes. In order to better understand the dynamics of this relationship, we propose a simple impedance-based electrode connectivity model, based on which we perform a simulation of the impact of both electrode density and electrode precision on the amount of information lost as part of the connection. Although the examples illustrated are more informative rather than conclusive, the fundamental takeaway from this work is that electrode density is a substantially important parameter while electrode precision is necessarily helpful.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/EMBC44109.2020.9176553DOI Listing
July 2020

The continuous development of a complete and objective automatic grading system of facial signs from selfie pictures: Asian validation study and application to women of three ethnic origins, differently aged.

Skin Res Technol 2021 Mar 20;27(2):183-190. Epub 2020 Jul 20.

ModiFace - A L'Oréal Group Company, Toronto, ON, Canada.

Objective: To evaluate the capacity of the automatic detection system to accurately grade, from smartphones' selfie pictures, the severity of seven new facial signs added to the nine previously integrated.

Methods: A two-step approach was conducted: first, to check on 112 Korean women, how the AI-based automatic grading system may correlate with dermatological assessments, taken as reference; second, to confirm on 1140 women of three ancestries (African, Asian, and Caucasian) the relevance of the newly input facial signs.

Results: The sixteen specific Asian facial signs, detected automatically, were found significantly (P < .0001) highly correlated with the clinical evaluations made by two Korean dermatologists (wrinkles: r = .90; sagging: r = .75-.95; vascular: r = .85; pores: r = .60; pigmentation: r = .50-.80). When applied at a larger scale on women of different ethnicities, new signs were found of good accuracy and reproducibility, albeit depending on ethnicity. Due to contrast with the innate skin complexion, the facial signs dealing with skin pigmentation were found of a much higher relevance among Asian women than African or Caucasian women. The automatic gradings were even found of a slightly higher accuracy than the clinical gradings.

Conclusion: The previously used automatic grading system is now completed by adding new facial signs apt at being detected. The continuous development is now integrating some limitations with regard to the constitutive skin complexion of the self-pictured subjects. Presenting reproducible assessments, highly correlated with medical grading, this system could change tremendously clinical researches, like in epidemiological studies, where it offers an easy, fast, affordable, and confidential approach in the objective quantification of facial signs.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1111/srt.12922DOI Listing
March 2021

A new procedure, free from human assessment that automatically grades some facial skin structural signs. Comparison with assessments by experts, using referential atlases of skin ageing.

Int J Cosmet Sci 2019 Feb;41(1):67-78

ModiFace - A L'Oréal Group Company, Toronto, Canada.

Objective: To develop an automatic system that grades the severity of facial signs through 'selfies' pictures taken by women of different ages and ethnics.

Methods: 1140 women from three ethnics (African-American, Asian, Caucasian), of different ages (18-80 years old), took 'selfies' by high resolution smartphones cameras under different conditions of lighting or facial expressions. A dedicated software, was developed, based on a Convolutional Neural Network (CNN) that integrates training data from referential Skin Aging Atlases. The latter allows to an immediate quantification of the severity of nine facial signs according to the ethnicity declared by the subject. These automatic grading were confronted to those assessed by 12 trained experts and dermatologists either on 'selfies' pictures or in live conditions on a smaller cohort of women.

Results: The system appears weakly influenced by lighting conditions or facial expressions (coefficients of variations ranging 10-13% for most signs) and leads to global agreements with experts' assessments, even showing a better reproducibility on some facial signs.

Conclusion: This automatic scoring system, still in development, seems offering a new quantitative approach in the quantified description of facial signs, independent from human vision, in many applications, being individual, cosmetic oriented or dermatological with regard to the follow-up of medical anti-ageing corrective strategies.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1111/ics.12512DOI Listing
February 2019

Hair Segmentation Using Heuristically-Trained Neural Networks.

IEEE Trans Neural Netw Learn Syst 2018 01 18;29(1):25-36. Epub 2016 Oct 18.

We present a method for binary classification using neural networks (NNs) that performs training and classification on the same data using the help of a pretraining heuristic classifier. The heuristic classifier is initially used to segment data into three clusters of high-confidence positives, high-confidence negatives, and low-confidence sets. The high-confidence sets are used to train an NN, which is then used to classify the low-confidence set. Applying this method to the binary classification of hair versus nonhair patches, we obtain a 2.2% performance increase using the heuristically trained NN over the current state-of-the-art hair segmentation method.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TNNLS.2016.2614653DOI Listing
January 2018

A quantitative evaluation of alcohol withdrawal tremors.

Annu Int Conf IEEE Eng Med Biol Soc 2015 ;2015:6215-8

This paper evaluates the relation between Alcohol Withdrawal Syndrome tremors in the left and right hands of patients. By analyzing 122 recordings from 61 patients in emergency departments, we found a weak relationship between the left and right hand tremor frequencies (correlation coefficient of 0.63). We found a much stronger relationship between the expert physician tremor ratings (on CIWA-Ar 0-7 scale) of the two hands, with a correlation coefficient of 0.923. Next, using a smartphone to collect the tremor data and using a previously developed model for obtaining estimated tremor ratings, we also found a strong correlation (correlation coefficient of 0.852) between the estimates of each hand. Finally, we evaluated different methods of combining the data from the two hands for obtaining a single tremor rating estimate, and found that simply averaging the tremor ratings of the two hands results in the lowest tremor estimate error (an RMSE of 0.977). Looking at the frequency dependence of this error, we found that higher frequency tremors had a much lower estimation error (an RMSE of 1.102 for tremors with frequencies in the 3-6Hz range as compared to 0.625 for tremors with frequencies in the 7-10Hz range).
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/EMBC.2015.7319812DOI Listing
September 2016

Tiny videos: a large data set for nonparametric video retrieval and frame classification.

IEEE Trans Pattern Anal Mach Intell 2011 Mar;33(3):618-30

Department of Electrical and Computer Engineering, University of Toronto, ON, Canada.

In this paper, we present a large database of over 50,000 user-labeled videos collected from YouTube. We develop a compact representation called "tiny videos" that achieves high video compression rates while retaining the overall visual appearance of the video as it varies over time. We show that frame sampling using affinity propagation-an exemplar-based clustering algorithm-achieves the best trade-off between compression and video recall. We use this large collection of user-labeled videos in conjunction with simple data mining techniques to perform related video retrieval, as well as classification of images and video frames. The classification results achieved by tiny videos are compared with the tiny images framework [24] for a variety of recognition tasks. The tiny images data set consists of 80 million images collected from the Internet. These are the largest labeled research data sets of videos and images available to date. We show that tiny videos are better suited for classifying scenery and sports activities, while tiny images perform better at recognizing objects. Furthermore, we demonstrate that combining the tiny images and tiny videos data sets improves classification precision in a wider range of categories.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2010.118DOI Listing
March 2011

Real-time face detection and lip feature extraction using field-programmable gate arrays.

IEEE Trans Syst Man Cybern B Cybern 2006 Aug;36(4):902-12

Department of Electrical and Computer Engineering, University of Toronto, ON, Canada.

This paper proposes a new technique for face detection and lip feature extraction. A real-time field-programmable gate array (FPGA) implementation of the two proposed techniques is also presented. Face detection is based on a naive Bayes classifier that classifies an edge-extracted representation of an image. Using edge representation significantly reduces the model's size to only 5184 B, which is 2417 times smaller than a comparable statistical modeling technique, while achieving an 86.6% correct detection rate under various lighting conditions. Lip feature extraction uses the contrast around the lip contour to extract the height and width of the mouth, metrics that are useful for speech filtering. The proposed FPGA system occupies only 15050 logic cells, or about six times less than a current comparable FPGA face detection system.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/tsmcb.2005.862728DOI Listing
August 2006

Enhanced sound localization.

IEEE Trans Syst Man Cybern B Cybern 2004 Jun;34(3):1526-40

Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, M5S 364 Canada.

A new approach to sound localization, known as enhanced sound localization, is introduced, offering two major benefits over state-of-the-art algorithms. First, higher localization accuracy can be achieved compared to existing methods. Second, an estimate of the source orientation is obtained jointly, as a consequence of the proposed sound localization technique. The orientation estimates and improved localizations are a result of explicitly modeling the various factors that affect a microphone's level of access to different spatial positions and orientations in an acoustic environment. Three primary factors are accounted for, namely the source directivity, microphone directivity, and source-microphone distances. Using this model of the acoustic environment, several different enhanced sound localization algorithms are derived. Experiments are carried out in a real environment whose reverberation time is 0.1 seconds, with the average microphone SNR ranging between 10-20 dB. Using a 24-element microphone array, a weighted version of the SRP-PHAT algorithm is found to give an average localization error of 13.7 cm with 3.7% anomalies, compared to 14.7 cm and 7.8% anomalies with the standard SRP-PHAT technique.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/tsmcb.2004.826398DOI Listing
June 2004

Phase-based dual-microphone robust speech enhancement.

IEEE Trans Syst Man Cybern B Cybern 2004 Aug;34(4):1763-73

Edward S. Rogers, Sr, Department of Electrical and Computer Engineering, University of Toronto, Toronto, M5S364 ON, Canada.

A dual-microphone speech-signal enhancement algorithm, utilizing phase-error based filters that depend only on the phase of the signals, is proposed. This algorithm involves obtaining time-varying, or alternatively, time-frequency (TF), phase-error filters based on prior knowledge regarding the time difference of arrival (TDOA) of the speech source of interest and the phases of the signals recorded by the microphones. It is shown that by masking the TF representation of the speech signals, the noise components are distorted beyond recognition while the speech source of interest maintains its perceptual quality. This is supported by digit recognition experiments which show a substantial recognition accuracy rate improvement over prior multimicrophone speech enhancement algorithms. For example, for a case with two speakers with a 0.1 s reverberation time, the phase-error based technique results in a 28.9% recognition rate gain over the single channel noisy signal, a gain of 22.0% over superdirective beamforming, and a gain of 8.5% over postfiltering.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/tsmcb.2004.830345DOI Listing
August 2004

Localization-based sensor validation using the Kullback-Leibler divergence.

Authors:
Parham Aarabi

IEEE Trans Syst Man Cybern B Cybern 2004 Apr;34(2):1007-16

Artificial Perception Laboratory, University of Toronto, Toronto, ON, Canada M5S 3G4.

A sensor validation criteria based on the sensor's object localization accuracy is proposed. Assuming that the true probability distribution of an object or event in space f(x) is known and a spatial likelihood function (SLF) psi(x) for the same object or event in space is obtained from a sensor, then the expected value of the SLF E[psi(x)] is proposed as a suitable validity metric for the sensor, where the expectation is performed over the distribution f(x). It is shown that for the class of increasing linear log likelihood SLFs, the proposed validity metric is equivalent to the Kullback-Leibler distance between f(x) and the unknown sensor-based distribution g(x) where the SLF psi(x) is an observable increasing function of the unobservable g(x). The proposed technique is illustrated through several simulated and experimental examples.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/tsmcb.2003.818555DOI Listing
April 2004
-->