Intelligent scissors (live-wire) - Intelligent scissors, also called live-wire in related interactive boundary-selection workflows, helps a user trace an image boundary by finding low-cost...
Interleaved (HWC) layout - An interleaved HWC image layout organizes data by height, width and channel, with channel values grouped for each pixel in a conventional contiguous...
Intermediate representation - An intermediate representation, or IR, is a structured form of a program or computation used between stages of translation, analysis or optimization.
Interval tree - An interval tree is a data structure for storing ranges and efficiently finding ranges that overlap a query interval or contain a query point.
Intrinsic-image decomposition - Intrinsic-image decomposition estimates separate components of an image that describe properties such as surface reflectance and shading.
Inverse depth parametrization - Inverse depth parametrization represents a visual feature using the reciprocal of its depth, together with information describing its viewing ray and...
Inverse filtering - Inverse filtering attempts to undo a known filtering operation by applying its mathematical inverse.
Inverse mapping - In image warping, inverse mapping determines which source coordinate supplies the value for each output coordinate.
Inverse problem - An inverse problem estimates unknown causes, parameters or underlying objects from observed effects.
Inverse-variance weighting - Inverse-variance weighting combines estimates by assigning larger weights to those with smaller variances.
Iris recognition - Iris recognition is a biometric technique that compares patterns in the iris, the textured region surrounding the pupil, to support identity verification or...
Isophote - An isophote in a scalar image is a curve along which intensity has a constant value. It is an image level line, analogous to an equal-height contour on a map.
Isotropic scaling - Isotropic scaling, also called uniform scaling, changes an object's size by the same factor in every spatial direction.
Joint compatibility branch and bound - Joint compatibility branch and bound, commonly abbreviated JCBB, is a data-association method that searches for a large set of mutually compatible matches...
Kernel regression - Kernel regression estimates a relationship between predictors and an outcome using locally weighted observations.
Keystoning - Keystoning is a perspective effect in which an intended rectangular image or planar subject appears trapezoidal, often because the projection or viewing...
KLT (Kanade - Lucas - Tomasi) tracker - The Kanade - Lucas - Tomasi, or KLT, tracker follows selected image features across successive frames by estimating local patch motion.
Lanczos - In the supplied image-resampling context, Lanczos refers to a family of interpolation filters built from a sinc function multiplied by a finite-support window.
Landmark detection - Landmark detection estimates the locations of predefined or otherwise task-relevant reference points in an image or scene.
Landmark point - A landmark point is a consistently identifiable location on an object or shape that can be matched with corresponding locations in other images or examples.
Laplace's equation - Laplace's equation states that the Laplacian of an unknown function is zero: ∇²u=0.
Laplacian smoothing - Laplacian smoothing reduces local variation by updating values or geometric positions according to differences from their neighbors.
Latent variable model - A latent variable model describes observed data using additional variables that are not directly observed in the dataset.
Learned operator - In computational photography, a learned operator is a function whose behavior is fitted from data to perform an image-processing or prediction task.
Lens-profile correction - Lens-profile correction uses a stored model of a lens and compatible capture conditions to compensate for predictable optical effects in an image.
Level set - A level set is the collection of points at which a function has the same specified value.
Levels - Levels is an image-editing adjustment that remaps tonal values using controls for the input black point, input white point, midtones, and output range.
Light field - A light field describes light traveling through space as a function of position and direction.
Light transport - Light transport describes how light moves through a scene and interacts with surfaces and media before reaching a sensor or observer.
Line intersection - Line intersection is the geometric relationship in which two lines share one or more points.
Linear filter - A linear filter transforms a signal or image while preserving superposition: filtering a weighted sum of inputs gives the same result as taking the...
Linear interpolation - Linear interpolation estimates a value between two known samples by following the straight line that connects them.
Linear inverse problem - A linear inverse problem estimates an unknown quantity from measurements related to it by a linear forward model.
Linear light - Linear light describes an image representation in which numerical values are proportional to the represented light quantity within a defined color and...
Linear shift-invariant (LSI) filter - A linear shift-invariant filter, or LSI filter, preserves superposition and responds the same way when an input pattern is shifted in space.
Local Laplacian filters - Local Laplacian filters are edge-aware image-processing methods that construct an output Laplacian pyramid using locally centered nonlinear intensity...
Local tone mapping - Local tone mapping adjusts an image's tonal values using information about each location's surroundings.
Locally adaptive regression kernel (LARK) - A locally adaptive regression kernel (LARK) is a description of a pixel's neighborhood whose shape adapts to local image structure.
Log encoding - Log encoding represents image signals with a logarithmic or partly logarithmic transfer function.
Log-normal distribution - A log-normal distribution describes a positive random quantity whose logarithm follows a normal distribution.
Look-up table - A look-up table, commonly called a LUT, stores output values that can be retrieved using an input value or combination of values.
Low-pass filter - A low-pass filter preserves slowly varying components of a signal while reducing more rapidly varying components.
Lucas--Kanade method - The Lucas - Kanade method is a gradient-based approach to image alignment.
Lucky imaging - Lucky imaging captures many short exposures, selects those least affected by changing image degradation, aligns them, and combines them into an improved image.
M-estimation - M-estimation is a broad approach to estimating model parameters by optimizing an aggregate criterion across observations.
Malvar - He - Cutler demosaicking - Malvar - He - Cutler demosaicking is a linear method for estimating missing red, green, and blue values in images captured with a Bayer color filter array.