In control system theory, and various branches of engineering, a transfer function matrix, or just transfer matrix is a generalisation of the transfer functions of single-input single-output (SISO) systems to multiple-input and multiple-output (MIMO) systems. The matrix relates the outputs of the system to its inputs. It is a particularly useful construction for linear time-invariant (LTI) systems because it can be expressed in terms of the s-plane. In some systems, especially ones consisting entirely of passive components, it can be ambiguous which variables are inputs and which are outputs. In electrical engineering, a common scheme is to gather all the voltage variables on one side and all the current variables on the other regardless of which are inputs or outputs. This results in all the elements of the transfer matrix being in units of impedance. The concept of impedance (and hence impedance matrices) has been borrowed into other energy domains by analogy, especially mechanics and acoustics. Many control systems span several different energy domains. This requires transfer matrices with elements in mixed units. This is needed both to describe transducers that make connections between domains and to describe the system as a whole. If the matrix is to properly model energy flows in the system, compatible variables must be chosen to allow this. == General == A MIMO system with m outputs and n inputs is represented by a m × n matrix. Each entry in the matrix is in the form of a transfer function relating an output to an input. For example, for a three-input, two-output system, one might write, [ y 1 y 2 ] = [ g 11 g 12 g 13 g 21 g 22 g 23 ] [ u 1 u 2 u 3 ] {\displaystyle {\begin{bmatrix}y_{1}\\y_{2}\end{bmatrix}}={\begin{bmatrix}g_{11}&g_{12}&g_{13}\\g_{21}&g_{22}&g_{23}\end{bmatrix}}{\begin{bmatrix}u_{1}\\u_{2}\\u_{3}\end{bmatrix}}} where the un are the inputs, the ym are the outputs, and the gmn are the transfer functions. This may be written more succinctly in matrix operator notation as, Y = G U {\displaystyle \mathbf {Y} =\mathbf {G} \mathbf {U} } where Y is a column vector of the outputs, G is a matrix of the transfer functions, and U is a column vector of the inputs. In many cases, the system under consideration is a linear time-invariant (LTI) system. In such cases, it is convenient to express the transfer matrix in terms of the Laplace transform (in the case of continuous time variables) or the z-transform (in the case of discrete time variables) of the variables. This may be indicated by writing, for instance, Y ( s ) = G ( s ) U ( s ) {\displaystyle \mathbf {Y} (s)=\mathbf {G} (s)\mathbf {U} (s)} which indicates that the variables and matrix are in terms of s, the complex frequency variable of the s-plane arising from Laplace transforms, rather than time. The examples in this article are all assumed to be in this form, although that is not explicitly indicated for brevity. For discrete time systems s is replaced by z from the z-transform, but this makes no difference to subsequent analysis. The matrix is particularly useful when it is a proper rational matrix, that is, all its elements are proper rational functions. In this case, the state-space representation can be applied. In systems engineering, the overall system transfer matrix G (s) is decomposed into two parts: H (s) representing the system being controlled, and C(s) representing the control system. C (s) takes as its inputs the inputs of G (s) and the outputs of H (s). The outputs of C (s) form the inputs for H (s). == Electrical systems == In electrical systems, it is often the case that the distinction between input and output variables is ambiguous. They can be either, depending on circumstance and point of view. In such cases, the concept of port (a place where energy is transferred from one system to another) can be more useful than input and output. It is customary to define two variables for each port (p): the voltage across it (Vp) and the current entering it (Ip). For instance, the transfer matrix of a two-port network can be defined as follows, [ V 1 V 2 ] = [ z 11 z 12 z 21 z 22 ] [ I 1 I 2 ] {\displaystyle {\begin{bmatrix}V_{1}\\V_{2}\end{bmatrix}}={\begin{bmatrix}z_{11}&z_{12}\\z_{21}&z_{22}\\\end{bmatrix}}{\begin{bmatrix}I_{1}\\I_{2}\end{bmatrix}}} where the zmn are called the impedance parameters, or z-parameters. They are so-called because they are in units of impedance and relate port currents to a port voltage. The z-parameters are not the only way that transfer matrices are defined for two-port networks. Six basic matrices relate voltages and currents, each with advantages for particular system network topologies. However, only two of these can be extended beyond two ports to an arbitrary number of ports. These two are the z-parameters and their inverse, the admittance parameters or y-parameters. To understand the relationship between port voltages and currents and inputs and outputs, consider the simple voltage divider circuit. If we only wish to consider the output voltage (V2) resulting from applying the input voltage (V1) then the transfer function can be expressed as, [ V 2 ] = [ R 2 R 1 + R 2 ] [ V 1 ] {\displaystyle {\begin{bmatrix}V_{2}\end{bmatrix}}={\begin{bmatrix}{\dfrac {R_{2}}{R_{1}+R_{2}}}\end{bmatrix}}{\begin{bmatrix}V_{1}\end{bmatrix}}} which can be considered the trivial case of a 1×1 transfer matrix. The expression correctly predicts the output voltage if there is no current leaving port 2, but is increasingly inaccurate as the load increases. If, however, we attempt to use the circuit in reverse, driving it with a voltage at port 2 and calculate the resulting voltage at port 1 the expression gives completely the wrong result even with no load on port 1. It predicts a greater voltage at port 1 than was applied at port 2, an impossibility with a purely resistive circuit like this one. To correctly predict the behaviour of the circuit, the currents entering or leaving the ports must also be taken into account, which is what the transfer matrix does. The impedance matrix for the voltage divider circuit is, [ V 1 V 2 ] = [ R 1 + R 2 R 2 R 2 R 2 ] [ I 1 I 2 ] {\displaystyle {\begin{bmatrix}V_{1}\\V_{2}\end{bmatrix}}={\begin{bmatrix}R_{1}+R_{2}&R_{2}\\R_{2}&R_{2}\end{bmatrix}}{\begin{bmatrix}I_{1}\\I_{2}\end{bmatrix}}} which fully describes its behaviour under all input and output conditions. At microwave frequencies, none of the transfer matrices based on port voltages and currents are convenient to use in practice. Voltage is difficult to measure directly, current next to impossible, and the open circuits and short circuits required by the measurement technique cannot be achieved with any accuracy. For waveguide implementations, circuit voltage and current are entirely meaningless. Transfer matrices using different sorts of variables are used instead. These are the powers transmitted into, and reflected from a port, which are readily measured in the transmission line technology used in distributed-element circuits in the microwave band. The most well-known and widely used of these sorts of parameters is the scattering parameters, or s-parameters. == Mechanical and other systems == The concept of impedance can be extended into the mechanical and other domains through a mechanical-electrical analogy, hence the impedance parameters and other forms of 2-port network parameters can also be extended to the mechanical domain. To do this, an effort variable and a flow variable are made analogues of voltage and current, respectively. For mechanical systems under translation these variables are force and velocity respectively. Expressing the behaviour of a mechanical component as a two-port or multi-port with a transfer matrix is a useful thing to do because, like electrical circuits, the component can often be operated in reverse and its behaviour is dependent on the loads at the inputs and outputs. For instance, a gear train is often characterised simply by its gear ratio, a SISO transfer function. However, the gearbox output shaft can be driven around to turn the input shaft, requiring a MIMO analysis. In this example, the effort and flow variables are torque T and angular velocity ω, respectively. The transfer matrix in terms of z-parameters will look like, [ T 1 T 2 ] = [ z 11 z 12 z 21 z 22 ] [ ω 1 ω 2 ] {\displaystyle {\begin{bmatrix}T_{1}\\T_{2}\end{bmatrix}}={\begin{bmatrix}z_{11}&z_{12}\\z_{21}&z_{22}\end{bmatrix}}{\begin{bmatrix}\omega _{1}\\\omega _{2}\end{bmatrix}}} However, the z-parameters are not necessarily the most convenient for characterising gear trains. A gear train is the analogue of an electrical transformer and the h-parameters (hybrid parameters) better describe transformers because they directly include the turns ratios (the analogue of gear ratios). The gearbox transfer matrix in h-parameter format is, [ T 1 ω 2 ] = [ h 11 h 12 h 21 h 22 ] [ ω 1 T 2 ] {\displaystyle {\begin{bmatrix}T_{1}\\\omega _{2}\end{bm
H (company)
H Company, also known simply as H, is a French artificial intelligence startup which develops "action-oriented" artificial intelligence agents for enterprise automation and productivity. In May 2024, H Company closed a record-setting $220 million seed round, at the time the largest AI raise in Europe. In 2026, H Company released Holo 3, the latest generation of its computer-use AI models. The update marked a major advance in agentic AI, enabling agents to navigate any user interface, interpret screens, and complete complex, multi-step tasks across enterprise systems—much like a human user. This breakthrough positioned H Company at the frontier of computer-use autonomy, accelerating the integration of AI in enterprise workflows. == History == H Company was founded in 2023 in Paris by Laurent Sifre, Charles Kantor, and three DeepMind veterans: Daan Wiestra, Karl Tuyls, Julien Perollat. In May 2024, the firm secured what was then the largest European AI seed round, totaling $220 million led by US investors including Eric Schmidt (former Google CEO), Amazon, and backed by Accel, Bpifrance, UiPath, Eurazeo, Xavier Niel, Yuri Milner, Bernard Arnault, Samsung and others. In August 2024, three cofounders (Wiestra, Tuyls, Perollat) left the company over operational disagreements. In November 2024, H launched Runner H, its first agentic-API platform, which combined a large language model (LLM) and a reduced, 2-billion parameter vision-language model (VLM). In May 2025, H Company acquired Mithril Security, and in June 2025 the company widened its offering for agentic models. In June 2025, Gautier Cloix (formerly CEO Palantir France) replaced Charles Kantor as CEO of H Company, aiming to pivot the company towards a "forward deployed engineers" model. In July 2025, H Company introduced Surfer-H-CLI, an open-source, web-native Chrome agent designed for browser-based automation—able to search, scroll, click, and type on behalf of users and controllable via any visual language model (VLM). When paired with its June 2025 open-sourced 3B-parameter Holo-1 model, Surfer-H-CLI achieved 92.2% WebVoyager benchmark accuracy. == Activity == H Company creates enterprise AI models and agents (agentic AI) to automate and optimize complex workflows. H Company specifically designs AI agents called computer use capable of autonomously interfacing with any software (local or cloud-based) to detect and automate repetitive operations. H Company is based in Paris, France, with international offices in London and New York. H Company raised $220 million since its inception. Gautier Cloix is president and CEO of the company. H Company client include the French national lottery FDJ United. In March 2026, H Company released Holo3, a family of artificial intelligence models designed to operate digital systems by interacting directly with user interfaces. Holo3 enables agents ("virtual humanoids") to understand what is displayed in front-end environments—such as web pages, desktop applications, and other graphical user interfaces—and perform actions such as clicking, typing, and navigating across them to complete multi-step tasks. On the OSWorld-Verified benchmark, Holo3 reportedly achieved about 78.9%, surpassing the scores of OpenAI’s GPT‑5.4 and Anthropic’s Claude Opus 4.6 on this specific test, at roughly one-tenth of the inference cost of these proprietary systems. The release has been presented as a significant step toward automating routine digital workflows, allowing organizations to offload repetitive on-screen work, such as data entry and reconciliation across multiple tools, to AI-based agents.
Zero-shot learning
Zero-shot learning (ZSL) is a problem setup in deep learning where, at test time, a learner observes samples from classes which were not observed during training, and needs to predict the class that they belong to. The name is a play on words based on the earlier concept of one-shot learning, in which classification can be learned from only one, or a few, examples. Zero-shot methods generally work by associating observed and non-observed classes through some form of auxiliary information, which encodes observable distinguishing properties of objects. For example, given a set of images of animals to be classified, along with auxiliary textual descriptions of what animals look like, an artificial intelligence model which has been trained to recognize horses, but has never been given a zebra, can still recognize a zebra when it also knows that zebras look like striped horses. This problem is widely studied in computer vision, natural language processing, and machine perception. == Background and history == The first paper on zero-shot learning in natural language processing appeared in a 2008 paper by Chang, Ratinov, Roth, and Srikumar, at the AAAI'08, but the name given to the learning paradigm there was dataless classification. The first paper on zero-shot learning in computer vision appeared at the same conference, under the name zero-data learning. The term zero-shot learning itself first appeared in the literature in a 2009 paper from Palatucci, Hinton, Pomerleau, and Mitchell at NIPS'09. This terminology was repeated later in another computer vision paper and the term zero-shot learning caught on, as a take-off on one-shot learning that was introduced in computer vision years earlier. In computer vision, zero-shot learning models learned parameters for seen classes along with their class representations and rely on representational similarity among class labels so that, during inference, instances can be classified into new classes. In natural language processing, the key technical direction developed builds on the ability to "understand the labels"—represent the labels in the same semantic space as that of the documents to be classified. This supports the classification of a single example without observing any annotated data, the purest form of zero-shot classification. The original paper made use of the Explicit Semantic Analysis (ESA) representation but later papers made use of other representations, including dense representations. This approach was also extended to multilingual domains, fine entity typing and other problems. Moreover, beyond relying solely on representations, the computational approach has been extended to depend on transfer from other tasks, such as textual entailment and question answering. The original paper also points out that, beyond the ability to classify a single example, when a collection of examples is given, with the assumption that they come from the same distribution, it is possible to bootstrap the performance in a semi-supervised like manner (or transductive learning). Unlike standard generalization in machine learning, where classifiers are expected to correctly classify new samples to classes they have already observed during training, in ZSL, no samples from the classes have been given during training the classifier. It can therefore be viewed as an extreme case of domain adaptation. == Prerequisite information for zero-shot classes == Naturally, some form of auxiliary information has to be given about these zero-shot classes, and this type of information can be of several types. Learning with attributes: classes are accompanied by pre-defined structured description. For example, for bird descriptions, this could include "red head", "long beak". These attributes are often organized in a structured compositional way, and taking that structure into account improves learning. While this approach was used mostly in computer vision, there are some examples for it also in natural language processing. Learning from textual description. As pointed out above, this has been the key direction pursued in natural language processing. Here class labels are taken to have a meaning and are often augmented with definitions or free-text natural-language description. This could include for example a wikipedia description of the class. Class-class similarity. Here, classes are embedded in a continuous space. A zero-shot classifier can predict that a sample corresponds to some position in that space, and the nearest embedded class is used as a predicted class, even if no such samples were observed during training. == Generalized zero-shot learning == The above ZSL setup assumes that at test time, only zero-shot samples are given, namely, samples from new unseen classes. In generalized zero-shot learning, samples from both new and known classes, may appear at test time. This poses new challenges for classifiers at test time, because it is very challenging to estimate if a given sample is new or known. Some approaches to handle this include: a gating module, which is first trained to decide if a given sample comes from a new class or from an old one, and then, at inference time, outputs either a hard decision, or a soft probabilistic decision a generative module, which is trained to generate feature representation of the unseen classes—a standard classifier can then be trained on samples from all classes, seen and unseen. == Domains of application == Zero shot learning has been applied to the following fields: image classification semantic segmentation image generation object detection natural language processing computational biology abstract reasoning
Vicuna LLM
Vicuna LLM is an omnibus large language model used in AI research. Its methodology is to enable the public at large to contrast and compare the accuracy of LLMs "in the wild" (an example of citizen science) and to vote on their output; a question-and-answer chat format is used. At the beginning of each round two LLM chatbots from a diverse pool of nine are presented randomly and anonymously, their identities only being revealed upon voting on their answers. The user has the option of either replaying ("regenerating") a round, or beginning an entirely fresh one with new LLMs. (The user also has the option of choosing which LLMs to do battle.) Based on Llama 2, it is an open source project, and it itself has become the subject of academic research in the burgeoning field. A non-commercial, public demo of the Vicuna-13b model is available to access using LMSYS.
Google Books Ngram Viewer
The Google Books Ngram Viewer is an online search engine that charts the frequencies of any set of search strings using a yearly count of n-grams found in printed sources published between 1500 and 2022 in Google's text corpora in English, Chinese (simplified), French, German, Hebrew, Italian, Russian, or Spanish. There are also some specialized English corpora, such as American English, British English, and English Fiction. The program can search for a word or a phrase. The n-grams are matched with the text within the selected corpus, and if found in 40 or more books, are then displayed as a graph. The program supports searches for parts of speech and wildcards. It is routinely used in research. == History == The Ngram Viewer was created by Google software engineers Will Brockman and Jon Orwant , who teamed up with Harvard researchers Jean-Baptiste Michel and Erez Lieberman Aiden. The service was released on December 16, 2010. Before the release, it was difficult to quantify the rate of linguistic change because of the absence of a database that was designed for this purpose, said Steven Pinker, a well-known linguist who was one of the co-authors of the Science paper published on the same day. The Google Books Ngram Viewer was developed in the hope of opening a new window to quantitative research in the humanities field, and the database contained 500 billion words from 5.2 million books publicly available from the very beginning. The intended audience was scholarly, but the Google Books Ngram Viewer made it possible for anyone with a computer to see a graph that represents the diachronic change of the use of words and phrases with ease. Lieberman said in response to The New York Times that the developers aimed to provide even children with the ability to browse cultural trends throughout history. In the Science paper, Lieberman and his collaborators called the method of high-volume data analysis in digitized texts "culturomics". == Usage == Commas delimit user-entered search terms, where each comma-separated term is searched in the database as an n-gram (for example, "nursery school" is a 2-gram or bigram). The Ngram Viewer then returns a plotted line chart. Due to limitations on the size of the Ngram database, only matches found in at least 40 books are indexed. == Limitations == The data sets of the Ngram Viewer have been criticized for their reliance upon inaccurate optical character recognition (OCR) and for including large numbers of incorrectly dated and categorized texts. Because of these errors, and because they are uncontrolled for bias (such as the increasing amount of scientific literature, which causes other terms to appear to decline in popularity), care must be taken in using the corpora to study language or test theories. Furthermore, the data sets may not reflect general linguistic or cultural change and can only hint at such an effect because they do not involve any metadata like date published, author, length, or genre, to avoid any potential copyright infringements. Systemic errors like the confusion of s and f in pre-19th century texts (due to the use of ſ, the long s, which is similar in appearance to f) can cause systemic bias. Although the Google Books team claims that the results are reliable from 1800 onwards, poor OCR and insufficient data mean that frequencies given for languages such as Chinese may only be accurate from 1970 onward, with earlier parts of the corpus showing no results at all for common terms, and data for some years containing more than 50% noise. Guidelines for doing research with data from Google Ngram have been proposed that try to address some of the issues discussed above.
Brill tagger
The Brill tagger is an inductive method for part-of-speech tagging. It was described and invented by Eric Brill in his 1993 PhD thesis. It can be summarized as an "error-driven transformation-based tagger". It is: a form of supervised learning, which aims to minimize error; and, a transformation-based process, in the sense that a tag is assigned to each word and changed using a set of predefined rules. In the transformation process, if the word is known, it first assigns the most frequent tag, or if the word is unknown, it naively assigns the tag "noun" to it. High accuracy is eventually achieved by applying these rules iteratively and changing the incorrect tags. This approach ensures that valuable information such as the morphosyntactic construction of words is employed in an automatic tagging process. == Algorithm == The algorithm starts with initialization, which is the assignment of tags based on their probability for each word (for example, "dog" is more often a noun than a verb). Then "patches" are determined via rules that correct (probable) tagging errors made in the initialization phase: Initialization: Known words (in vocabulary): assigning the most frequent tag associated to a form of the word Unknown word == Rules and processing == The input text is first tokenized, or broken into words. Typically in natural language processing, contractions such as "'s", "n't", and the like are considered separate word tokens, as are punctuation marks. A dictionary and some morphological rules then provide an initial tag for each word token. For example, a simple lookup would reveal that "dog" may be a noun or a verb (the most frequent tag is simply chosen), while an unknown word will be assigned some tag(s) based on capitalization, various prefix or suffix strings, etc. (such morphological analyses, which Brill calls Lexical Rules, may vary between implementations). After all word tokens have (provisional) tags, contextual rules apply iteratively, to correct the tags by examining small amounts of context. This is where the Brill method differs from other part of speech tagging methods such as those using Hidden Markov Models. Rules are reapplied repeatedly, until a threshold is reached, or no more rules can apply. Brill rules are of the general form: tag1 → tag2 IF Condition where the Condition tests the preceding and/or following word tokens, or their tags (the notation for such rules differs between implementations). For example, in Brill's notation: IN NN WDPREVTAG DT while would change the tag of a word from IN (preposition) to NN (common noun), if the preceding word's tag is DT (determiner) and the word itself is "while". This covers cases like "all the while" or "in a while", where "while" should be tagged as a noun rather than its more common use as a conjunction (many rules are more general). Rules should only operate if the tag being changed is also known to be permissible, for the word in question or in principle (for example, most adjectives in English can also be used as nouns). Rules of this kind can be implemented by simple Finite-state machines. See Part of speech tagging for more general information including descriptions of the Penn Treebank and other sets of tags. Typical Brill taggers use a few hundred rules, which may be developed by linguistic intuition or by machine learning on a pre-tagged corpus. == Code == Brill's code pages at Johns Hopkins University are no longer on the web. An archived version of a mirror of the Brill tagger at its latest version as it was available at Plymouth Tech can be found on Archive.org. The software uses the MIT License.
Image registration
Image registration is the process of transforming different sets of data into one coordinate system. Data may be multiple photographs, data from different sensors, times, depths, or viewpoints. It is used in computer vision, medical imaging, military automatic target recognition, and compiling and analyzing images and data from satellites. Registration is necessary in order to be able to compare or integrate the data obtained from these different measurements. == Algorithm classification == === Intensity-based vs feature-based === Image registration or image alignment algorithms can be classified into intensity-based and feature-based. One of the images is referred to as the target, fixed or sensed image and the others are referred to as the moving or source images. Image registration involves spatially transforming the source/moving image(s) to align with the target image. The reference frame in the target image is stationary, while the other datasets are transformed to match to the target. Intensity-based methods compare intensity patterns in images via correlation metrics, while feature-based methods find correspondence between image features such as points, lines, and contours. Intensity-based methods register entire images or sub-images. If sub-images are registered, centers of corresponding sub images are treated as corresponding feature points. Feature-based methods establish a correspondence between a number of especially distinct points in images. Knowing the correspondence between a number of points in images, a geometrical transformation is then determined to map the target image to the reference images, thereby establishing point-by-point correspondence between the reference and target images. Methods combining intensity-based and feature-based information have also been developed. === Transformation models === Image registration algorithms can also be classified according to the transformation models they use to relate the target image space to the reference image space. The first broad category of transformation models includes affine transformations, which include rotation, scaling, translation and shearing. Affine transformations are global in nature, thus, they cannot model local geometric differences between images. The second category of transformations allow 'elastic' or 'nonrigid' transformations. These transformations are capable of locally warping the target image to align with the reference image. Nonrigid transformations include radial basis functions (thin-plate or surface splines, multiquadrics, and compactly-supported transformations), physical continuum models (viscous fluids), and large deformation models (diffeomorphisms). Transformations are commonly described by a parametrization, where the model dictates the number of parameters. For instance, the translation of a full image can be described by a translation vector parameter. These models are called parametric models. Non-parametric models on the other hand, do not follow any parameterization, allowing each image element to be displaced arbitrarily. There are a number of programs that implement both estimation and application of a warp-field. It is a part of the SPM and AIR programs. === Transformations of coordinates via the law of function composition rather than addition === Alternatively, many advanced methods for spatial normalization are building on structure preserving transformations homeomorphisms and diffeomorphisms since they carry smooth submanifolds smoothly during transformation. Diffeomorphisms are generated in the modern field of Computational Anatomy based on flows since diffeomorphisms are not additive although they form a group, but a group under the law of function composition. For this reason, flows which generalize the ideas of additive groups allow for generating large deformations that preserve topology, providing 1-1 and onto transformations. Computational methods for generating such transformation are often called LDDMM which provide flows of diffeomorphisms as the main computational tool for connecting coordinate systems corresponding to the geodesic flows of Computational Anatomy. There are a number of programs which generate diffeomorphic transformations of coordinates via diffeomorphic mapping including MRI Studio and MRI Cloud.org === Spatial vs frequency domain methods === Spatial methods operate in the image domain, matching intensity patterns or features in images. Some of the feature matching algorithms are outgrowths of traditional techniques for performing manual image registration, in which an operator chooses corresponding control points (CP) in images. When the number of control points exceeds the minimum required to define the appropriate transformation model, iterative algorithms like RANSAC can be used to robustly estimate the parameters of a particular transformation type (e.g. affine) for registration of the images. Frequency-domain methods find the transformation parameters for registration of the images while working in the transform domain. Such methods work for simple transformations, such as translation, rotation, and scaling. Applying the phase correlation method to a pair of images produces a third image which contains a single peak. The location of this peak corresponds to the relative translation between the images. Unlike many spatial-domain algorithms, the phase correlation method is resilient to noise, occlusions, and other defects typical of medical or satellite images. Additionally, the phase correlation uses the fast Fourier transform to compute the cross-correlation between the two images, generally resulting in large performance gains. The method can be extended to determine rotation and scaling differences between two images by first converting the images to log-polar coordinates. Due to properties of the Fourier transform, the rotation and scaling parameters can be determined in a manner invariant to translation. === Single- vs multi-modality methods === Another classification can be made between single-modality and multi-modality methods. Single-modality methods tend to register images in the same modality acquired by the same scanner/sensor type, while multi-modality registration methods tended to register images acquired by different scanner/sensor types. Multi-modality registration methods are often used in medical imaging as images of a subject are frequently obtained from different scanners. Examples include registration of brain CT/MRI images or whole body PET/CT images for tumor localization, registration of contrast-enhanced CT images against non-contrast-enhanced CT images for segmentation of specific parts of the anatomy, and registration of ultrasound and CT images for prostate localization in radiotherapy. === Automatic vs interactive methods === Registration methods may be classified based on the level of automation they provide. Manual, interactive, semi-automatic, and automatic methods have been developed. Manual methods provide tools to align the images manually. Interactive methods reduce user bias by performing certain key operations automatically while still relying on the user to guide the registration. Semi-automatic methods perform more of the registration steps automatically but depend on the user to verify the correctness of a registration. Automatic methods do not allow any user interaction and perform all registration steps automatically. === Similarity measures for image registration === Image similarities are broadly used in medical imaging. An image similarity measure quantifies the degree of similarity between intensity patterns in two images. The choice of an image similarity measure depends on the modality of the images to be registered. Common examples of image similarity measures include cross-correlation, mutual information, sum of squared intensity differences, and ratio image uniformity. Mutual information and normalized mutual information are the most popular image similarity measures for registration of multimodality images. Cross-correlation, sum of squared intensity differences and ratio image uniformity are commonly used for registration of images in the same modality. Many new features have been derived for cost functions based on matching methods via large deformations have emerged in the field Computational Anatomy including Measure matching which are pointsets or landmarks without correspondence, Curve matching and Surface matching via mathematical currents and varifolds. == Uncertainty == There is a level of uncertainty associated with registering images that have any spatio-temporal differences. A confident registration with a measure of uncertainty is critical for many change detection applications such as medical diagnostics. In remote sensing applications where a digital image pixel may represent several kilometers of spatial distance (such as NASA's LANDSAT imagery), an uncertain image registration can mean that a solution could b