The Mechanism of Human Facial Expression

Globally, there is a huge unmet need for effective treatments for neurodegenerative diseases. The complexity of the molecular mechanisms underlying neuronal degeneration and the heterogeneity of the patient population present massive challenges to the development of early diagnostic tools and effective treatments for these diseases. Machine learning, a subfield of artificial intelligence, is enabling scientists, clinicians and patients to address some of these challenges. In this Review, we discuss how machine learning can aid early diagnosis and interpretation of medical images as well as the discovery and development of new therapies. A unifying theme of the different applications of machine learning is the integration of multiple high-dimensional sources of data, which all provide a different view on disease, and the automated derivation of actionable insights.

/pdf/applications-of-machine-learning-to-diagnosis-and-treatment-4ayj9iduxu.pdf

Applications of machine learning to diagnosis and treatment of neurodegenerative diseases

A major barrier to the effective conduct of clinical trials of new drug candidates against Alzheimer’s disease (AD) and to identifying patients for receiving future disease-modifying treatments is the limited capacity of the current health system to find and diagnose patients with early AD pathology. This may be related in part to the limited capacity of the current health systems to select those people likely to have AD pathology in order to confirm the diagnosis with available cerebrospinal fluid and imaging biomarkers at memory clinics. In the current narrative review, we summarize the literature on candidate blood tests for AD that could be implemented in primary care settings and used for the effective identification of individuals at increased risk of AD pathology, who could be referred for potential inclusion in clinical trials or future approved treatments following additional testing. We give an updated account of blood-based candidate biomarkers and biomarker panels for AD-related brain changes. Our analysis centres on biomarker candidates that have been replicated in more than one study and discusses the need of further studies to achieve the goal of a primary care-based screening algorithm for AD.

/pdf/blood-based-molecular-biomarkers-for-alzheimer-s-disease-3y9jrufjbz.pdf

Blood-based molecular biomarkers for Alzheimer's disease.

Facial expressions are one of the most powerful, natural and immediate means for human being to communicate their emotions and intensions. Recognition of facial expression has many applications including human-computer interaction, cognitive science, human emotion analysis, personality development etc. In this paper, we propose a new method for the recognition of facial expressions from single image frame that uses combination of appearance and geometric features with support vector machines classification. In general, appearance features for the recognition of facial expressions are computed by dividing face region into regular grid (holistic representation). But, in this paper we extracted region specific appearance features by dividing the whole face region into domain specific local regions. Geometric features are also extracted from corresponding domain specific regions. In addition, important local regions are determined by using incremental search approach which results in the reduction of feature dimension and improvement in recognition accuracy. The results of facial expressions recognition using features from domain specific regions are also compared with the results obtained using holistic representation. The performance of the proposed facial expression recognition system has been validated on publicly available extended Cohn-Kanade (CK+) facial expression data sets.

Facial expression recognition based on local region specific features and support vector machines

The complexity of Alzheimer’s disease (AD) and its long prodromal phase poses challenges for early diagnosis and yet allows for the possibility of the development of disease modifying treatments for secondary prevention. It is, therefore, of importance to develop biomarkers, in particular, in the preclinical or early phases that reflect the pathological characteristics of the disease and, moreover, could be of utility in triaging subjects for preventative therapeutic clinical trials. Much research has sought biomarkers for diagnostic purposes by comparing affected people to unaffected controls. However, given that AD pathology precedes disease onset, a pathology endophenotype design for biomarker discovery creates the opportunity for detection of much earlier markers of disease. Blood-based biomarkers potentially provide a minimally invasive option for this purpose and research in the field has adopted various “omics” approaches in order to achieve this. This review will, therefore, examine the current literature regarding blood-based proteomic biomarkers of AD and its associated pathology.

/pdf/blood-based-proteomic-biomarkers-of-alzheimer-s-disease-1cjh18z1hu.pdf

Blood-Based Proteomic Biomarkers of Alzheimer’s Disease Pathology

We present a computer vision-based system named Anubhav (a Hindi word meaning feeling) which recognizes emotional facial expressions from streaming face videos. Our system runs at a speed of 10 frames per second (fps) on a 3.2-GHz desktop and at 3 fps on an Android mobile device. Using entropy and correlation-based analysis, we show that some particular salient regions of face image carry major expression-related information compared with other face regions. We also show that spatially close features within a salient face region carry correlated information regarding expression. Therefore, only a few features from each salient face region are enough for expression representation. Extraction of only a few features considerably saves response time. Exploitation of expression information from spatial as well as temporal dimensions gives good recognition accuracy. We have done extensive experiments on two publicly available data sets and also on live video streams. The recognition accuracies on benchmark CK
 $$+$$
 data set and on live video stream by our system are at least 13 and 20 % better, respectively, compared to competing approaches.

Anubhav : recognizing emotions through facial expression

Motivation: Alzheimer’s disease (AD) is a dementia that gets worse with time resulting in loss of memory and cognitive functions. The life expectancy of AD patients following diagnosis is � 7 years. In 2006, researchers estimated that 0.40% of the world population (range 0.17–0.89%) was afflicted by AD, and that the prevalence rate would be tripled by 2050. Usually, examination of brain tissues is required for definite diagnosis of AD. So, it is crucial to diagnose AD at an early stage via some alternative methods. As the brain controls many functions via releasing signalling proteins through blood, we analyse blood plasma proteins for diagnosis of AD. Results: Here, we use a radial basis function (RBF) network for feature selection called feature selection RBF network for selection of plasma proteins that can help diagnosis of AD. We have identified a set of plasma proteins, smaller in size than previous study, with comparable prediction accuracy. We have also analysed mild cognitive impairment (MCI) samples with our selected proteins. We have used neural networks and support vector machines as classifiers. The principle component analysis, Sammmon projection and heat-map of the selected proteins have been used to demonstrate the proteins’ discriminating power for diagnosis of AD. We have also found a set of plasma signalling proteins that can distinguish incipient AD from MCI at an early stage. Literature survey strongly supports the AD diagnosis capability of the selected plasma proteins. Availability and implementation: The FSRBF code is available at https://sites.google.com/site/agar

Identification of a small set of plasma signalling proteins using neural network for prediction of Alzheimer’s disease

For synthesis of realistic facial expressions displaying emotions, we need an efficient representation of pure (eg, surprise ) as well as mixed (eg, happily surprised ) emotional expressions In this paper, we train an expression map (XM) that efficiently represents the emotional expressions We propose an algorithm that utilizes the XM to synthesize emotional expressions, tailor-made for the facial structure of the target person The proposed method can also control the proportions of different basic emotional expressions of those, when mixed together, to generate realistic emotional facial expressions Unlike many existing methods, our expression synthesis model requires only one expression-neutral face image of the target person Both qualitative and quantitative tests on four data sets show promising results On average, we have achieved 924% correct validation of the expressions synthesized by our method We also show that for both basic and mixed emotional expressions, our method generates finer expression details compared to existing state-of-the-art works

Synthesis of Realistic Facial Expressions Using Expression Map

A novel bag-of-words based approach is proposed for recognizing facial expressions corresponding to each of the six basic prototypic emotions from a video sequence. Each video sequence is represented as a specific combination of local (in spatio-temporal scale) motion patterns. These local motion patterns are captured in motion descriptors (MDs) which are unique combinations of optical flow and image gradient. These MDs can be compared to the words in the bag-of-words setting. Generally, the key-words in the wordbook as reported in the literature, are rigid, i.e., are taken as it is from the training data and cannot generalize well. We propose a novel adaptive learning technique for the key-words. The adapted key-MDs better represent the local motion patterns of the videos and generalize well to the unseen data and thus give better expression recognition accuracy. To test the efficiency of the proposed approach, we have experimented extensively on three well known datasets. We have also compared the results with existing state-of-the-art expression descriptors. Our method gives better accuracy. The proposed approach have been able to reduce the training time including the time for feature-extraction more than nine times and test time more than twice as compared to current state-of-the-art descriptor.

Facial expression recognition through adaptive learning of local motion descriptor

In real life facial expressions show mixture of emotions. This paper proposes a novel expression descriptor based expression map that can efficiently represent pure, mixture and transition of facial expressions. The expression descriptor is the integration of optic flow and image gradient values and the descriptor value is accumulated in temporal scale. The expression map is realized using self-organizing map. We develop an objective scheme to find the percentage of different prototypical pure emotions (e.g., happiness, surprise, disgust etc.) that mix up to generate a real facial expression. Experimental results show that the expression map can be used as an effective classifier for facial expressions.

Swapna Agarwal

Papers

Anubhav : recognizing emotions through facial expression

Identification of a small set of plasma signalling proteins using neural network for prediction of Alzheimer’s disease

Synthesis of Realistic Facial Expressions Using Expression Map

Facial expression recognition through adaptive learning of local motion descriptor

Decoding mixed emotions from expression map of face images