Face Emotion Based Intelligent Chaterbot
| Autor: | Sachin Radder, Nalini C. Iyer, Srinivasagouda C Patil, Satish Chikkamath |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Facial expression
Computational complexity theory Computer science business.industry Deep learning ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Machine learning computer.software_genre Facial recognition system Field (computer science) Face (geometry) Artificial intelligence Android (operating system) business Affective computing computer |
| Zdroj: | 2021 2nd International Conference for Emerging Technology (INCET). |
| DOI: | 10.1109/incet51464.2021.9456249 |
| Popis: | Recognition of emotion is the detection of human feelings from facial expressions. Emotion recognition based on facial images has over the years been regarded as a challenging subject in the field of affective computing. Although there are several methods to solve this problem, due to their computational sophistication, they cannot be implemented on the embedded devices involved. We use three light and quantized deep learning models that can be deployed on embedded devices to address this problem. To obtain real-time output of emotion recognition, lightweight and quantized deep learning models are required. We use the model ensemble technique to improve accuracy, where we take the weighted fusion of two lightweight and quantized deep learning models so that they can be deployed with reduced computational complexity and improved accuracy on android devices. We were thus able to obtain real-time recognition of emotions on Android devices. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|