Summary of Complex-valued Convolutional Neural Network Classification Of Hand Gesture From Radar Images, by Shokooh Khandan
Complex-valued convolutional neural network classification of hand gesture from radar images
by Shokooh Khandan
First submitted to arxiv on: 17 Sep 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The abstract discusses advancements in hand gesture recognition systems, which have numerous applications in fields like safety, security, and automotive industries. The paper reviews various deep neural network architectures, such as multi-layer perceptron (MLP), convolutional neural network (CNN), recurrent neural network (RNN), and cascade architectures. However, existing algorithms are designed for real-valued (RV) inputs and struggle with complex-valued (CV) radar images. Researchers have converted CV optimization problems into RV ones by splitting complex numbers, but this method doubles the network dimensions. The paper proposes a fully complex-valued convolutional neural network (FCV-CNN), including building blocks, forward and backward operations, and derivatives in the complex domain. The proposed model is compared with an equivalent real-valued model on two sets of CV hand gesture radar images. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Hand gesture recognition systems have made significant progress in recent years and are now being used in various applications. The paper talks about different deep learning models that can be used for this task, including MLP, CNN, RNN, and more. However, most current algorithms only work with real numbers, which makes it hard to use them on complex-valued data like radar images. The researchers have tried to fix this by converting the complex numbers into real ones, but this makes the models bigger and less efficient. To solve this problem, the paper proposes a new type of neural network that can handle complex numbers from start to finish. |
Keywords
» Artificial intelligence » Cnn » Deep learning » Gesture recognition » Neural network » Optimization » Rnn
