Machine Learning for sEMG Facial Feature Characterization

2019 ◽  
Author(s):  
Amleset Kelati ◽  
Juha Plosila ◽  
Hannu Tenhunen
Keyword(s):  
Machine Learning ◽  
Facial Feature ◽  
Feature Characterization

scholarly journals Polarization imaging feature characterization of different endometrium phases by machine learning

OSA Continuum ◽  
2021 ◽  
Author(s):  
Yue Yao ◽  
Min Zuo ◽  
Yang Dong ◽  
Liyun Shi ◽  
Yuanhuan Zhu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Imaging Feature ◽  
Polarization Imaging ◽  
Feature Characterization

scholarly journals Privacy Protection With Facial Deidentification Machine Learning Methods: Can Current Methods Be Applied to Dermatology?

Iproceedings ◽  
10.2196/35431 ◽  
2021 ◽  
Vol 6 (1) ◽  
pp. e35431
Author(s):  
Hyeon Ki Jeong ◽  
Christine Park ◽  
Ricardo Henao ◽  
Meenal Kheterpal
Keyword(s):  
Machine Learning ◽  
Image Analysis ◽  
Skin Color ◽  
Image Data ◽  
Facial Feature ◽  
Human Detection ◽  
Use Cases ◽  
Facial Image ◽  
High Quality ◽  
Data Utility

Background In the era of increasing tools for automatic image analysis in dermatology, new machine learning models require high-quality image data sets. Facial image data are needed for developing models to evaluate attributes such as redness (acne and rosacea models), texture (wrinkles and aging models), pigmentation (melasma, seborrheic keratoses, aging, and postinflammatory hyperpigmentation), and skin lesions. Deidentifying facial images is critical for protecting patient anonymity. Traditionally, journals have required facial feature concealment typically covering the eyes, but these guidelines are largely insufficient to meet ethical and legal guidelines of the Health Insurance Portability and Accountability Act for patient privacy. Currently, facial feature deidentification is a challenging task given lack of expert consensus and lack of testing infrastructure for adequate automatic and manual facial image detection. Objective This study aimed to review the current literature on automatic facial deidentification algorithms and to assess their utility in dermatology use cases, defined by preservation of skin attributes (redness, texture, pigmentation, and lesions) and data utility. Methods We conducted a systematic search using a combination of headings and keywords to encompass the concepts of facial deidentification and privacy preservation. The MEDLINE (via PubMed), Embase (via Elsevier), and Web of Science (via Clarivate) databases were queried from inception to May 1, 2021. Studies with the incorrect design and outcomes were excluded during the screening and review process. Results A total of 18 studies, largely focusing on general adversarial network (GANs), were included in the final review reporting various methodologies of facial deidentification algorithms for still and video images. GAN-based studies were included owing to the algorithm’s capacity to generate high-quality, realistic images. Study methods were rated individually for their utility for use cases in dermatology, pertaining to skin color or pigmentation and texture preservation, data utility, and human detection, by 3 human reviewers. We found that most studies notable in the literature address facial feature and expression preservation while sacrificing skin color, texture, pigmentation, which are critical features in dermatology-related data utility. Conclusions Overall, facial deidentification algorithms have made notable advances such as disentanglement and face swapping techniques, while producing realistic faces for protecting privacy. However, they are sparse and currently not suitable for complete preservation of skin texture, color, and pigmentation quality in facial photographs. Using the current advances in artificial intelligence for facial deidentification summarized herein, a novel approach is needed to ensure greater patient anonymity, while increasing data access for automated image analysis in dermatology. Conflicts of Interest None declared.

scholarly journals A Hybrid Enhanced Real-Time Face Recognition Model using Machine Learning Method with Dimension Reduction

2021 ◽  
Vol 1 (3) ◽  
pp. 12-16
Author(s):  
Jaya Kumari ◽  
◽  
Kailash Patidar ◽  
Mr. Gourav Saxena ◽  
Mr. Rishi Kushwaha ◽  
...  
Keyword(s):  
Machine Learning ◽  
Principal Component Analysis ◽  
Face Recognition ◽  
Technology Implementation ◽  
Principal Component ◽  
Facial Feature ◽  
Component Analysis ◽  
Experimental Result ◽  
Scale Invariant ◽  
Recognition Model

Face recognition techniques play a crucial role in numerous disciplines of data security, verification, and authentication. The face recognition algorithm selects a face attribute from an image datasets. Recognize identification is an authentication device for verification as well as validation having both data analysis and feasible significance. The facerecognizing centered authentication framework can further be considered an AI technology implementation for instantly identifying a particular image. In this research, we are presenting a hybrid face recognition model (HFRM) using machine learning methods with “Speed Up Robust Features” (SURF), “scale-invariant feature transform” (SIFT), Locality Preserving Projections (LPP) &Principal component analysis (PCA) method. In the proposed HFRM model SURF method mainly detects the local feature efficiently. SIFT method mainly utilizes to detect the local features and recognize them. LPP retains the local framework of facial feature area which is generally quite meaningful than on the sequence kept by a 'principal component analysis (PCA) as well as “linear discriminate analysis” (LDA). The proposed HFRM method is compared with the existing (H. Zaaraoui et al., 2020) method and the experimental result clearly shows the outstanding performance in terms of detection rate and accuracy % over existing methods.

scholarly journals EKSTRAKSI FITUR BERBASIS AVERAGE FACE UNTUK PENGENALAN EKSPRESI WAJAH

2017 ◽  
Vol 2 (2) ◽  
pp. 130-134
Author(s):  
Jarot Dwi Prasetyo ◽  
Zaehol Fatah ◽  
Taufik Saleh
Keyword(s):  
Machine Learning ◽  
Facial Expression ◽  
Facial Expressions ◽  
Facial Expression Recognition ◽  
Facial Feature ◽  
Expression Recognition ◽  
Facial Feature Extraction ◽  
Sample Data ◽  
Machine Interface ◽  
The Difference

In recent years it appears interest in the interaction between humans and computers. Facial expressions play a fundamental role in social interaction with other humans. In two human communications is only 7% of communication due to language linguistic message, 38% due to paralanguage, while 55% through facial expressions. Therefore, to facilitate human machine interface more friendly on multimedia products, the facial expression recognition on interface very helpful in interacting comfort. One of the steps that affect the facial expression recognition is the accuracy in facial feature extraction. Several approaches to facial expression recognition in its extraction does not consider the dimensions of the data as input features of machine learning Through this research proposes a wavelet algorithm used to reduce the dimension of data features. Data features are then classified using SVM-multiclass machine learning to determine the difference of six facial expressions are anger, hatred, fear of happy, sad, and surprised Jaffe found in the database. Generating classification obtained 81.42% of the 208 sample data.

scholarly journals A Review on Facial Emotion Recognition Using Machine and Deep Learning Algorithm

2020 ◽  
pp. 09-13
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Deep Learning ◽  
Emotion Recognition ◽  
Facial Expressions ◽  
Learning Algorithm ◽  
Facial Feature ◽  
Facial Emotion Recognition ◽  
Facial Emotion ◽  
Expression Recognition

Facial emotions are the changes in facial expressions about a person’s inner excited tempers, objectives, or social exchanges which are scrutinized with the aid of computer structures that attempt to subsequently inspect and identify the facial feature and movement variations from visual data. Facial emotion recognition (FER) is a noteworthy area in the arena of computer vision and artificial intelligence due to its significant commercial and academic potential. FER has become a widespread concept of deep learning and offers more fields for application in our day-to-day life. Facial expression recognition (FER) has gathered widespread consideration recently as facial expressions are thought of as the fastest medium for communicating any of any sort of information. Recognizing facial expressions provides an improved understanding of a person’s thoughts or views. With the latest improvement in computer vision and machine learning, it is plausible to identify emotions from images. Analyzing them with the presently emerging deep learning methods enhance the accuracy rate tremendously as compared to the traditional contemporary systems. This paper emphases the review of a few of the machine learning, deep learning, and transfer learning techniques used by several researchers that flagged the means to advance the classification accurateness of the FEM.

scholarly journals Privacy Protection With Facial Deidentification Machine Learning Methods: Can Current Methods Be Applied to Dermatology? (Preprint)

2021 ◽  
Author(s):  
Hyeon Ki Jeong ◽  
Christine Park ◽  
Ricardo Henao ◽  
Meenal Kheterpal
Keyword(s):  
Machine Learning ◽  
Image Analysis ◽  
Skin Color ◽  
Image Data ◽  
Facial Feature ◽  
Human Detection ◽  
Use Cases ◽  
Facial Image ◽  
High Quality ◽  
Data Utility

BACKGROUND In the era of increasing tools for automatic image analysis in dermatology, new machine learning models require high-quality image data sets. Facial image data are needed for developing models to evaluate attributes such as redness (acne and rosacea models), texture (wrinkles and aging models), pigmentation (melasma, seborrheic keratoses, aging, and postinflammatory hyperpigmentation), and skin lesions. Deidentifying facial images is critical for protecting patient anonymity. Traditionally, journals have required facial feature concealment typically covering the eyes, but these guidelines are largely insufficient to meet ethical and legal guidelines of the Health Insurance Portability and Accountability Act for patient privacy. Currently, facial feature deidentification is a challenging task given lack of expert consensus and lack of testing infrastructure for adequate automatic and manual facial image detection. OBJECTIVE This study aimed to review the current literature on automatic facial deidentification algorithms and to assess their utility in dermatology use cases, defined by preservation of skin attributes (redness, texture, pigmentation, and lesions) and data utility. METHODS We conducted a systematic search using a combination of headings and keywords to encompass the concepts of facial deidentification and privacy preservation. The MEDLINE (via PubMed), Embase (via Elsevier), and Web of Science (via Clarivate) databases were queried from inception to May 1, 2021. Studies with the incorrect design and outcomes were excluded during the screening and review process. RESULTS A total of 18 studies, largely focusing on general adversarial network (GANs), were included in the final review reporting various methodologies of facial deidentification algorithms for still and video images. GAN-based studies were included owing to the algorithm’s capacity to generate high-quality, realistic images. Study methods were rated individually for their utility for use cases in dermatology, pertaining to skin color or pigmentation and texture preservation, data utility, and human detection, by 3 human reviewers. We found that most studies notable in the literature address facial feature and expression preservation while sacrificing skin color, texture, pigmentation, which are critical features in dermatology-related data utility. CONCLUSIONS Overall, facial deidentification algorithms have made notable advances such as disentanglement and face swapping techniques, while producing realistic faces for protecting privacy. However, they are sparse and currently not suitable for complete preservation of skin texture, color, and pigmentation quality in facial photographs. Using the current advances in artificial intelligence for facial deidentification summarized herein, a novel approach is needed to ensure greater patient anonymity, while increasing data access for automated image analysis in dermatology.

Sign in / Sign up

Export Citation Format

Share Document