In the context of computer vision and image processing, a is an abstract representation of data learned by a neural network, specifically within the intermediate or "hidden" layers of a deep learning model. Key Characteristics
detect simple patterns like edges, textures, or blobs. Intermediate layers combine these into more complex shapes.
: Unlike traditional "handcrafted" features (such as color histograms or shape descriptors) that are designed by humans, deep features are learned automatically by the model during training.
: Deep features are typically output as numerical vectors (a row of numbers) from the last fully connected or pooling layer before the final classification. Common Applications
: Deep learning models build these features in stages:
represent high-level concepts or objects (e.g., a "wheel" or a "face").