Inspiration
Throughout my high school years, I volunteered in the field of art therapy for individuals with autism. These experiences allowed me to discover the need for emotional cognition support for children with autism.
What it does
We've developed a facial recognition system within a web and mobile application that automatically identifies and tags users in photos. This eliminates the need for manual tagging in each photo, saving time and effort. Leveraging facial recognition technology, we've also engineered a system capable of accurately analyzing the emotions of individuals in photos or videos. This system can detect subtle changes in facial expressions, aiding users in better understanding the emotional states of others thereby enhancing empathetic communication and social interactions.
How we built it
We initiated the project by installing Node.js on our computers. Then, we used Vue CLI to scaffold our project. Afterward, we focused on generating static pages and integrating corresponding APIs. The business logic was implemented per our requirements, followed by rigorous deployment testing. Facial features such as eyes, nose, mouth, and the contour of the face are authenticated through computer algorithms and pattern recognition techniques. This technology is applicable in numerous fields and is adept at understanding someone’s emotional and potential psychological state. Computer vision and machine learning techniques are employed to parse patterns of micro-expressions and body language on the face, inferring emotions like happiness, sadness, anger, and surprise. This technology aids in the development of emotional intelligence and social intelligent interactions.
Challenges we ran into
The performance of our facial recognition system could be affected by ethnicity, gender, age, and skin color. This is due to potentially unvaried samples in our training datasets or imbalances in sample distribution. Facial recognition technology involves personal privacy and data security. Properly handling and protecting facial recognition data, while complying with pertinent laws and regulations, is imperative.
Accomplishments that we're proud of
Our facial recognition algorithm has made significant strides in accuracy, now surpassing the recognition capabilities of the human eye. This has turned facial recognition into a reliable and effective solution for identity authentication and recognition. Our facial recognition system can now rapidly detect and identify faces in real-time video streams.
What we learned
The hands-on experience with Node.js, Vue CLI, and the integration of APIs bolstered our technical skill set. We became proficient in creating responsive static pages and implementing complex business logic into our application. Furthermore, working with facial recognition technology deepened our understanding of machine learning algorithms and computer vision. We learned how to train models to recognize and interpret facial features and expressions accurately.
What's next for EmotionLearner
Personalization and User Experience: The future of facial recognition technology in EmotionLearner is geared towards enhanced personalization and user experience. By recognizing individuals’ emotions and affective states, we aim to provide smarter, more personalized services and interactive experiences for users. We plan to refine our algorithms for greater sensitivity to a range of emotional nuances, enabling more accurate user profiles that can adapt to the unique emotional journeys of each individual. This could open up new avenues for tailored content delivery, adaptive learning systems, and even support for mental health initiatives by identifying potential stress or anxiety indicators.
Log in or sign up for Devpost to join the conversation.