Over the centuries, humans have developed and acquired a number of ways to communicate. But hardly any of them can be as natural and instinctive as facial expressions. On the other hand, neural networks have taken the world by storm. And no surprises, that the area of Computer Vision and the problem of facial expressions recognitions hasn't remained untouched. Although a wide range of techniques have been applied, achieving extremely high accuracies and preparing highly robust FER systems still remains a challenge due to heterogeneous details in human faces. In this paper, we will be deep diving into implementing a system for recognition of facial expressions (FER) by leveraging neural networks, and more specifically, Convolutional Neural Networks (CNNs). We adopt the fundamental concepts of deep learning and computer vision with various architectures, fine-tune it's hyperparameters and experiment with various optimization methods and demonstrate a state-of-the-art single-network-accuracy of 70.10% on the FER2013 dataset without using any additional training data.
翻译:几个世纪以来,人类已经开发并获得了一系列交流方式。 但其中几乎没有人能像面部表情那样自然和本能。 另一方面,神经网络把世界推向暴风雨。 毫不奇怪, 计算机视野领域和面部表情识别问题并没有丝毫不受影响。 尽管应用了多种技术,但是由于人类面孔的复杂细节,实现极高的美化和准备高度强大的FER系统仍然是一个挑战。 在本文中,我们将深入潜入一个通过利用神经网络,更具体地说,即进化神经网络(CNNs)来识别面部表情的系统。 我们采用了各种结构的深层次学习和计算机视觉的基本概念,微调它超光量计和实验各种优化方法,并在FER2013数据集上展示了70.10%的最新单网络精确度,而没有使用任何额外的培训数据。