123

Deep learning allows computational models to learn and represent data with multiple levels of abstraction mimicking how the brain perceives and understands information.

Deep learning is a rich family of methods, encompassing neural networks and a unsupervised and supervised learning methods.

Convolutional Neural Networks (CNNs) were inspired by the visual system’s structure. A CNN comprises three main types of neural layers, namely, (i) convolutional layers, (ii) pooling layers, and (iii) fully connected layers.

Deep Belief Networks (DBNs) are probabilistic generative models which provide a joint probability distribution over observable data and labels. they can capture many layers of complex representations of input data and they are appropriate for unsupervised learning since they can be trained on unlabeled data.

Applications in Computer Vision

Object detection is the process of detecting instances of semantic objects of a certain class (such as humans, airplanes, or birds) in digital images and video. A common approach for object detection is CNN.

Face recognition is technology capable of matching a human face from a digital image and it is one of the hottest computer vision applications with great commercial interest as well.

human pose estimation is to determine the position of human joints from images. Human pose estimation is a very challenging and difficult task/ standart apporch is cnn and dbn.

in Conclusions

The surge of deep learning extent due to the achievements in computer vision. CNNs DBNs have been showed sota rates in visual tasks, such as object detection, face recognition, action and activity recognition, human pose estimation, image retrieval, and semantic segmentation.