arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.12233cs.CVcs.HCcs.LG
收藏

基于深度学习和图像处理的高效手语识别系统及数据集创建方法

Efficient sign language recognition system and dataset creation method based on deep learning and image processing

Alvaro Leandro Cavalcante Carneiro, Lucas de Brito Silva, Denis Henrique Pinheiro Salvadeo

摘要:

每年都会创建新的深度学习架构,在图像识别方面取得最先进的成果,并使人们相信,在几年内,手语翻译等复杂任务将变得更加容易,成为听障社区的沟通工具。另一方面,这些算法仍然需要大量的数据来训练,并且数据集创建过程昂贵,耗时且缓慢。因此,这项工作的目的是研究数字图像处理和机器学习,可以用来创建一个手语数据集有效的技术。我们讨论了数据采集,如每秒的帧速率捕获或子采样的视频,背景类型,预处理和数据增强,使用卷积神经网络和目标检测来创建一个图像分类器,并比较基于统计测试的结果。研究人员创建了不同的数据集来测试假设,其中包含14个日常使用的单词,并由不同的智能手机在RGB颜色系统中记录。我们在测试集上实现了96.38%的准确率,在包含更具挑战性条件的验证集上实现了81.36%的准确率,表明30 FPS是训练分类器的最佳帧速率子样本,几何变换比强度变换更好,人工背景创建对模型泛化无效。在未来的工作中,这些权衡应被视为创建数据集和训练标志识别模型时计算成本和准确性增益之间的成本效益准则。

英文摘要:

New deep-learning architectures are created every year, achieving state-of-the-art results in image recognition and leading to the belief that, in a few years, complex tasks such as sign language translation will be considerably easier, serving as a communication tool for the hearing-impaired community. On the other hand, these algorithms still need a lot of data to be trained and the dataset creation process is expensive, time-consuming, and slow. Thereby, this work aims to investigate techniques of digital image processing and machine learning that can be used to create a sign language dataset effectively. We argue about data acquisition, such as the frames per second rate to capture or subsample the videos, the background type, preprocessing, and data augmentation, using convolutional neural networks and object detection to create an image classifier and comparing the results based on statistical tests. Different datasets were created to test the hypotheses, containing 14 words used daily and recorded by different smartphones in the RGB color system. We achieved an accuracy of 96.38% on the test set and 81.36% on the validation set containing more challenging conditions, showing that 30 FPS is the best frame rate subsample to train the classifier, geometric transformations work better than intensity transformations, and artificial background creation is not effective to model generalization. These trade-offs should be considered in future work as a cost-benefit guideline between computational cost and accuracy gain when creating a dataset and training a sign recognition model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑