3,135 articles
Image registration
Image registration, also known as coregistration or image matching, geometrically aligns two or more images of the same scene taken at different times, viewpoints, or sensors.
Image scaling
Image scaling, also known as image resampling or resizing, changes the number of pixels in a digital image, with the interpolation method determining quality and speed.
Image segmentation
Image segmentation, also called digital image segmentation, is the task of partitioning an image into labeled regions so objects and structures are separated from the background.
Image stitching
Image stitching, also called photo mosaicking, is a computer vision technique that combines overlapping images into one panorama or high-resolution mosaic, widely used in smartphones and satellite mapping.
Image subtraction
Image subtraction is a digital image processing operation that computes pixel-wise differences between two images, making changed or moving regions stand out for motion detection.
Image warping
Image warping is a spatial transformation of a digital image that maps every pixel position to a new location, used in registration, panorama stitching, and texture mapping.
Image watermarking
Image watermarking is a digital image processing technique that embeds hidden information, such as an ownership identifier or authentication data, into an image's pixels for later detection or extraction.
Image-to-image translation
Image-to-image translation is a computer vision problem of learning to convert images between domains while preserving content, with Pix2Pix as the paired and CycleGAN as the unpaired reference method.
ImageJ
ImageJ is public domain Java software for processing and analyzing scientific images, created by Wayne Rasband at NIH in 1997 and widely used in biological image analysis.
IMDb
IMDb, the Internet Movie Database, is an online database of films, television series, and video games, founded by Col Needham in 1990 and owned by Amazon.
IMDb country and regional sub-sites
IMDb country and regional sub-sites do not exist as separate national sites; IMDb localizes its single global website through country preferences, alternate titles, per-country release dates, and, since 2023, machine-translated languages.
Imitation learning
Imitation learning trains an agent from expert demonstrations by learning a mapping between observations and actions, without a hand-specified reward function, and is widely used in robotics and games.
Immuta
Immuta is a Boston-based data security and data provisioning company founded in 2015 by Matthew Carroll, Steve Touw, and Mike Schiller; its platform enforces centralized, attribute-based access policies across Snowflake, Databricks, and other cloud data platforms, with $259.5M raised.
Implicit bias of gradient descent
Implicit bias of gradient descent is the tendency of gradient descent to select particular loss-minimizing solutions, such as low-norm or max-margin ones, without explicit regularization.
Imply (company)
Imply Data, Inc. is a Burlingame, California software company founded in 2015 by the original creators of Apache Druid (Fangjin Yang, Gian Merlino, Vadim Ogievetsky), selling Polaris, Enterprise, and Lumi; it raised $100M Series D in 2022 at a $1.1B valuation and remains private. Not the Brazilian Imply technology firm founded 2003.
IMS Health
IMS Health was an American healthcare analytics company founded in 1954 that collected prescription and sales data for drugmakers, merging into Quintiles in 2016 to form IQVIA.
In-memory database
An in-memory database (IMDB), also called a RAM database, is a database management system that keeps its primary data in main memory rather than on disk.
In-memory processing
In-memory processing keeps a workload's data resident in RAM rather than on disk to speed up analytics, transactions, and machine learning, studied since the 1980s in systems like SAP HANA and Spark.
In-place algorithm
An in-place algorithm is an algorithm that uses only constant extra space beyond its input, so algorithms like heapsort and quicksort sort without an auxiliary array.
Inception network
The Inception network is a family of convolutional neural network architectures for image classification, introduced in 2014; its GoogLeNet version won ILSVRC 2014 by running filters of several sizes in parallel.
Inception score
The Inception score (IS) is a metric for evaluating generative image models, measuring the confidence and diversity of a pretrained Inception classifier's predictions on generated images.
Incremental computation
Incremental computation is a computing method that updates a program's output when its input changes, doing work proportional to the change rather than the dataset.
Incremental learning (machine learning)
Incremental learning trains a machine learning model by updating it continuously as new data arrives instead of retraining from a fixed dataset, with catastrophic forgetting as its central difficulty.
Incremental processing
Incremental processing: data engineering pattern where pipelines process only new, updated, or deleted records since the last run, using watermarks, timestamps, or change data capture instead of full refresh.
Incremental view maintenance
Incremental view maintenance (IVM) computes and applies only deltas to materialized views when base tables change, instead of full recomputation. Key ideas: delta queries, counting algorithm, immediate vs deferred maintenance, DBSP/F-IVM engines.
Independent component analysis
Independent component analysis (ICA) is a statistical method for separating mixed signals into independent sources, formulated by Pierre Comon in 1994 and used for blind source separation.
Individual fairness
Individual fairness is a definition of algorithmic fairness, introduced by Cynthia Dwork and colleagues in the 2011 paper Fairness Through Awareness, which requires that similar individuals be treated similarly by a machine-learning model.
Inertial odometry
Inertial odometry is a dead-reckoning method that estimates a vehicle's or person's position, velocity, and orientation by integrating accelerometer and gyroscope measurements alone, without satellite signals, maps, or cameras.
Inference attack
An inference attack is an attack on a machine learning system that tries to extract sensitive information from a deployed model, such as whether a record was used in training.
Infinite impulse response
An infinite impulse response (IIR) filter is a digital filter whose response to a single impulse never reaches exactly zero because feedback recirculates energy through the system.