BEIJING - WiMi Hologram Cloud has developed what it calls a CNN (convolutional neural network) algorithm-based image recognition system. CNN's recognition algorithm is based on an artificial neural network. It applies the CNN algorithm to image recognition technology, showing apparent advantages compared to the traditional machine learning algorithm, the company says.

In CNNs, according to the company, neurons in one layer are not connected to all neurons in the next layer. Instead, they use a 3D structure in which each group of neurons analyses a specific region or feature of the image.

CNNs filter connections by proximity (analyzing pixels only for nearby pixels), allowing for a computationally sound training process. This consists of multiple stages of convolution and sampling, then the extracted features are fed into the fully connected layer for the computation of classification results. The convolutional layer obtains the features of the image from the upper layer and the data on the unit nodes from each local area in the input layer, which need to cover the entire data set.

Image recognition technology's use in the field of artificial intelligence covers navigation, resource analysis, environmental monitoring, and medical research, the company says. In the future, WiMi will continue to expand the application scenarios of its developed CNN algorithm. WIMI Hologram Cloud began operations in 2015 as a holographic cloud technical solution provider focusing on holographic AR automotive HUD software, 3D holographic pulse LiDAR, head-mounted light field holographic equipment, holographic semiconductor, holographic cloud software, and holographic car navigation.