Wild facial expression recognition based on incremental active learning
Autor: | Phill Kyu Rhee, Md. Rezaul Bashar, Minhaz Uddin Ahmed, Kim Yeong Hyeon, Kim Jin Woo |
---|---|
Rok vydání: | 2018 |
Předmět: |
Facial expression
Computer science Active learning (machine learning) business.industry Cognitive Neuroscience Deep learning ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Process (computing) 020206 networking & telecommunications Experimental and Cognitive Psychology Pattern recognition 02 engineering and technology Facial recognition system Transformation (function) Artificial Intelligence Face (geometry) 0202 electrical engineering electronic engineering information engineering Benchmark (computing) 020201 artificial intelligence & image processing Artificial intelligence business Software |
Zdroj: | Cognitive Systems Research. 52:212-222 |
ISSN: | 1389-0417 |
Popis: | Facial expression recognition in a wild situation is a challenging problem in computer vision research due to different circumstances, such as pose dissimilarity, age, lighting conditions, occlusions, etc. Numerous methods, such as point tracking, piecewise affine transformation, compact Euclidean space, modified local directional pattern, and dictionary-based component separation have been applied to solve this problem. In this paper, we have proposed a deep learning–based automatic wild facial expression recognition system where we have implemented an incremental active learning framework using the VGG16 model developed by the Visual Geometry Group. We have gathered a large amount of unlabeled facial expression data from Intelligent Technology Lab (ITLab) members at Inha University, Republic of Korea, to train our incremental active learning framework. We have collected these data under five different lighting conditions: good lighting, average lighting, close to the camera, far from the camera, and natural lighting and with seven facial expressions: happy, disgusted, sad, angry, surprised, fear, and neutral. Our facial recognition framework has been adapted from a multi-task cascaded convolutional network detector. Repeating the entire process helps obtain better performance. Our experimental results have demonstrated that incremental active learning improves the starting baseline accuracy from 63% to average 88% on ITLab dataset on wild environment. We also present extensive results on face expression benchmark such as Extended Cohn-Kanade Dataset, as well as ITLab face dataset captured in wild environment and obtained better performance than state-of-the-art approaches. |
Databáze: | OpenAIRE |
Externí odkaz: |