We all are breathing under the covid pandemic situation, and we have a lot to worry about our health. One must stay miles away from getting sick, which the healthily working immune system promises us to allow ourselves to experience a productive version of ourselves. Together we can see the homecoming of a stronger system by working physically and letting the mind relax. It is essential for controlling diabetes and high blood pressure, maintaining bone strength and muscle tone through regular exercise is important especially after ordinary outdoor activities are curtailed during the COVID -19 pandemic.

Sedentary behavior and low levels of physical activity can have negative effects on the health, well-being, and quality of life of individuals. Self-quarantine can also cause additional stress and challenge the mental health of citizens. Physical inactivity is common among people with intellectual impairments, as are avoidable health problems such as obesity and cardiovascular disease. Increased exercise and wellness involvement can help them enhance their overall health and well-being.

Physical activity and relaxation techniques can be valuable tools to help you remain calm and continue to protect your health during this time. WHO recommends 150 minutes of moderate-intensity or 75 minutes of vigorous-intensity physical activity per week, or a combination of both. ThereFore Freak App is the Best Solution to stay mentally and physically fit during these tough times.

What it does

"FREAK" is predominantly designed to strengthen a person's immune system, which plays a vital role in the pandemic situation of Covid 19, which the world is struggling with. The app strives to improve the physical and mental health of the population to revive the immune system and wellbeing. The best thing which can happen to health is fitness. Physical activity reduces the risk of chronic disease, improves balance and coordination, helps to lose weight, and promotes strong muscles and bones. It boosts respiratory, cardiovascular health, and overall health at the same time. You may reduce body weight along with the risk of fatal diseases like diabetes, heart disease, and some cancers and even expand your sleeping habits and self-esteem.

FREAK fitness coach provides its users with specific exercise plans and guides them through training to achieve their fitness goals. It uses the front camera of your smartphone to monitor your performance and then make changes to the workout plan. It also delivers audio feedback in real-time. It offers personalized fitness and lifestyle plans. Aaptiv needs to be fed with a few details like eating habits with diet plans, fitness goals, and current fitness level. Freak AI fitness coach's main goal is to get its users active, fit, and healthy. It does this by providing customized fitness training that can be done anywhere, at any time. Freak turns your smartphone into a personal fitness trainer that tracks your workouts using computer vision. Freak, like the other well-known personal trainers, provides real-time audio feedback.

How I built it

  • Machine Learning Postnet Model by Tensorflow. It is a Predefined Model by Tensorflow that is a train to detect the body key points of a person’s body, by detecting body parts such as elbows, hips, wrists, knees, and ankles. It uses the joints of these body parts to determine body postures. Postnet Model will help to get key points on the real-time data and help to detect a person's Body.

  • Postnet Classifier to train the Custom Pose Detection. With the help of a classifier, different poses of exercises are classified which can be trained on different Dataset of exercises resulting in good accuracy.

  • Google Cloud/ Firebase. Google Cloud to create and access data and for creating chatbots and other ML Models.

  • ChatBot using Google’s DialogueFlow. Dialogflow is a natural language understanding platform used to design and integrate a conversational user interface into mobile apps bots, interactive voice response systems. The chatbot will help the user to interact and to solve their queries.

  • Immune System Checker. It will help to generate the health report of a person and to recommend activities.

  • BMI Calculator. To check Body Mass Index.

Challenges we ran into

Freak uses the neural network, and classic computer vision algorithms, with a 95% accuracy of recognition of asanas, which includes a data set of more than a thousand images. This dataset acts as training for the neural network and therefore is the most important aspect of the app. These representative datasets are hard to create, particularly when it comes to finding several images of people in a particular pose. These images should contain different angles, and because different people in their ordinary lives have performed different yoga poses, it becomes difficult to sync them with the existing systems. Along with the representative dataset, another problem faced by the app is the visibility of the body. Now, if a person is standing near a window or bright light, it might be difficult for the camera to catch certain parts of the body or it might blend the body’s outline with a large object behind. So, while using Freak, it is not recommended to keep the camera against bright light or close to a window.


The current App is presently accessible in English, but I intend to expand to include other languages in the future. The model is presently trained on a limited number of datasets; however, the dataset may be increased by including additional yoga postures done by humans in both indoor and outdoor settings to improve the model's performance.

With the aid of sensors, I plan to include additional health-related analyzers in the future, such as tracking footsteps, heart rate, and blood pressure. Also, a reminder system that notifies the user when it's time to drink, take medicine, or exercise.

Built With

Share this project: