Pattern recognition is a field/problem of classifying data (observations, measurements) into categories or classes based on statistical information extracted from the patterns. It’s essentially the broader term that encompasses machine learning and some aspects of signal processing and AI dealing with recognition tasks (speech recognition, OCR, image recognition). Pattern recognition approaches can be supervised (training on labeled data) or unsupervised (clustering, discovering patterns). The “patterns” could be visual (like shapes in an image), auditory (sounds), or more abstract. The term is somewhat classical, used in context of early AI for things like fingerprint recognition, face recognition, etc. Many traditional pattern recognition techniques overlapped with what we now call machine learning (like Bayes classifiers, linear discriminants, decision trees). The field emphasizes feature extraction and the statistical nature of recognition. It gave rise to subfields like image processing, speech processing, etc., each focusing on patterns in specific data types.
Data Selection & Data Viewer
Get data insights and find the perfect selection strategy
Learn MoreSelf-Supervised Pretraining
Leverage self-supervised learning to pretrain models
Learn MoreSmart Data Capturing on Device
Find only the most valuable data directly on devide
Learn More