This invention relates to a Facial Stress Detection for people using Deep learning and it’s related with Computer Science domain.
Background of the Invention
Stress is the most frequently used term in day-to-day life for everyone. People from almost every age group face the consequences of stress in their life. Stress may occur from an event, thought, or feeling that makes humans angry, nervous, or frustrated Stress is a response of the human body to a challenge or request. “Stress is a non-specific response of a human body to any demand for the change” [Selye H 1978]. Stress can affect the human body, behavior, feelings, and thoughts as well. Stress can be positive (eustress)and negative(distress). Positive Stress helps an individual to avoid danger or meet a deadline. But when the Stress stays for a longer period it is referred to as Negative Stress, it may harm human health as well (Cleveland Clinic, 2015, May 2).
In India, one in-four citizen is suffering from stress in his/her day to day life (World Health Organization. 2010, December 8) that's why we need a system that can recognize the Stress at an early stage and can protect the people from its later severe impacts. Automatic detection of Stress minimizes the risk of health issues and improves the welfare of society. This paves the way for the necessity of a scienti?c tool, which uses behavioral signals thereby automating the detection of Stress levels in individuals.
Through this invention we propose a stress recognition system which will recognize the stress in human being at an early stage. The automatic recognition of stress keeps down the risk of health issues and improves the well-being of society. This paves the way for the essentials of a research-based tool, which uses behavioral and pulse rate signals of an individual for automatic detection of the Stress.
Deep learning is a subset of machine learning that is essentially a three-layer neural network. These neural networks aim to imitate the activity of the human brain by allowing it to "learn" from enormous amounts of data, albeit they fall far short of its capabilities. While a single-layer neural network may produce approximate predictions, additional hidden layers can help to optimize and improve accuracy.
Much artificial intelligence (AI) apps and services rely on deep learning to improve automation by executing analytical and physical activities without the need for human participation. Everyday products and services (such as digital assistants, voice-enabled TV remotes, and credit card fraud detection), as well as upcoming innovations, use deep learning technology (such as self-driving cars).
None of the prior art indicate above either alone or in combination with one another disclose what the present invention has disclosed. This invention uses the concepts of Artificial Intelligence and Deep Learning to develop an app for automatically detecting stress at an early stage.
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
The primary objective of the present invention is to develop a Stress recognition System using Artificial Intelligence and Deep Learning for automatically recognizing the stress level of an individual as low, medium and high.
Discloses herein an Artificial Intelligence and Deep Learning Based Facial Recognition System for Stress Detection comprises a Raw Images (201), Features Extractions (202), Data Extraction (203), Data Cleaning (204), Data Scaling (205), Features selection (206), and Deep Learning Algorithms (207), and OUTPUT (208).
The facial images are classified into seven facial expression categories namely Disgust, Anger, Fear, Sad, Happy, 'Neutral, and Surprise.
The parameters from the captured facial image like eyebrows both left and right Lip movement, Head positioning, Eye blinking, Gaze movement.
A secondary dataset is used to train and test the classifier; and the face portion is detected and the required features are extracted from input raw images by applying Vola-Jone or other Image processing algorithms for dual-feature fusion.
The facial landmark point on the face image which are captured through an app or digital camera and then the important local regions are located using Open CV. ANN, SVM, CNN, and Deep Learning algorithms is used for analyzing the data; and the transfer learning algorithm may also be used for better results.
In the pre-processing stage, resized each image to a suitable size for each CNN model and converts the grey images to the RGB images.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
Figure 1: Raw images are normalized and then trained with the help of the CNN model and the output will be produced is CNN Weights.
Figure 2- Testing Phase
Figure 3- The Architecture of Facial Stress Recognition System (A)
Figure 4- The Architecture of Facial Stress Recognition System (B)
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.

DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Stress is a severe problem that is affecting the life of an individual. Once the individual affects by severe side-effects of Stress it becomes difficult to get rid of it. A famous quote says prevention is better than cure. Hence, a stress recognition system for early stress identification has been invented, it will help individuals to keep themselves safe from severe side effects of the stress. This invention relates to a Deep Learning based system for Facial Stress Recognition. The technology allows an accurate and secure way to detect the stress of an individual. More particularly this present invention relates to implementing a Deep Learning-based system of real-time Facial Stress Recognition. Furthermore, it is an accurate system for detecting Facial stress and its levels in an individual.
The invention may be used by the organizations to recognize the stress level of the employees and will guide them to take the corrective measures as well. This may be helpful to increase the productivity of the employees as well.
People are working hard for a better lifestyle; they get stressed due to several reasons which put a severe side-effect on their health, wealth and personal /professional relations. Human race is facing a lot many severe effects of stress from a couple of decades. Stress is one of the most severe issues in the current era. It shows the need for a system that can be used by the individuals to recognize the stress at an early stage. We need a system to identify this hazard at the initial level. This invention serves as a model for the society for Stress Recognition by capturing their facial images at the early stage. To address these issues, Deep Learning has emerged as a potential solution due to its capabilities such as Accuracy, reliability, Huge Amount of Resource, Large Number of Layers and Model Optimizing Hyper-parameters.
This invention uses Deep Learning applications in Stress Detection. The methodology to achieve the goal is as follows:
As per the literature the facial images are classified into seven facial expression categories namely Disgust, Anger, Fear, Sad, Happy, 'Neutral, and Surprise. The inventors studied the following parameters from the captured facial image like eyebrows both left and right Lip movement, Head positioning, Eye blinking, Gaze movement. A secondary dataset is used to train and test the classifier. Initially, the face portion is detected and the required features are extracted from input raw images by applying Vola-Jone or other Image processing algorithms for dual-feature fusion, we detect the facial landmark point on the face image which are captured through an app or digital camera and then the important local regions are located using Open CV. ANN, SVM, CNN, and Deep Learning algorithms is used for analyzing the data. The transfer learning algorithm may also be used for better results.
In, the pre-processing stage, we resized each image to a suitable size for each CNN model and converts the grey images to the RGB images.

Novel Features:
1. Facial Stress Recognition System is related to using Artificial Intelligence and Deep Learning applications for designing the app.
2. Facial Stress Recognition System analyses the role of Deep Learning in Psychology.
3. Facial Stress Recognition System identifies the stress of an individual at an early stage in real time environment.

We Claim:

1. An Artificial Intelligence and Deep Learning Based Facial Recognition System for Stress Detection comprises a Raw Images (201), Features Extractions (202), Data Extraction (203), Data Cleaning (204), Data Scaling (205), Features selection (206), and Deep Learning Algorithms (207), and OUTPUT (208).
2. The system as claimed in claim 1, wherein facial images are classified into seven facial expression categories namely Disgust, Anger, Fear, Sad, Happy, 'Neutral, and Surprise.
3. The system as claimed in claim 1, wherein parameters from the captured facial image like eyebrows both left and right Lip movement, Head positioning, Eye blinking, Gaze movement.
4. The system as claimed in claim 1, wherein a secondary dataset is used to train and test the classifier; and the face portion is detected and the required features are extracted from input raw images by applying Vola-Jone or other Image processing algorithms for dual-feature fusion.
5. The system as claimed in claim 1, wherein the facial landmark point on the face image which are captured through an app or digital camera and then the important local regions are located using Open CV. ANN, SVM, CNN, and Deep Learning algorithms is used for analyzing the data; and the transfer learning algorithm is used for better results.
6. The system as claimed in claim 1, wherein in the pre-processing stage, resized each image to a suitable size for each CNN model and converts the grey images to the RGB images.