Deep Learning Super Sampling (DLSS) is a suite of real-time deep learning image enhancement and upscaling technologies developed by Nvidia that are available in a number of video games. The goal of these technologies is to allow the majority of the graphics pipeline to run at a lower resolution for increased performance, and then infer a higher resolution image from this that approximates the same level of detail as if the image had been rendered at this higher resolution. This allows for higher graphical settings or frame rates for a given output resolution, depending on user preference. All generations of DLSS are available on all RTX-branded cards from Nvidia in supported titles. However, the Frame Generation feature is only supported on RTX 40 series GPUs or newer and Multi Frame Generation is only available on 50 series GPUs. == History == Nvidia advertised DLSS as a key feature of GeForce RTX 20 series GPUs when they launched in September 2018. At that time, the results were limited to a few video games, namely Battlefield V, or Metro Exodus, because the algorithm had to be trained specifically on each game on which it was applied and the results were usually not as good as simple resolution upscaling. In 2019, Control shipped with ray tracing and an image processing algorithm that approximated DLSS, which did not use the Tensor Cores. In April 2020, Nvidia advertised and shipped an improved version of DLSS named DLSS 2 with driver version 445.75. DLSS 2.0 was available for a few existing games including Control and Wolfenstein: Youngblood, and would later be added to many newly released games and game engines such as Unreal Engine and Unity. This time Nvidia said that it used the Tensor Cores again, and that the AI did not need to be trained specifically on each game. Despite sharing the DLSS branding, the two iterations of DLSS differ significantly and are not backwards-compatible. In January 2025, Nvidia stated that there are over 540 games and apps supporting DLSS, and that over 80% of Nvidia RTX users activate DLSS. In March 2025, there were more than 100 games that support DLSS 4, according to Nvidia. By May 2025, over 125 games supported DLSS 4. The first video game console to use DLSS, the Nintendo Switch 2, was released on June 5, 2025. Nvidia announced DLSS 4.5 at CES 2026. In January 2026, Nvidia stated that over 250 games and applications support Multi Frame Generation. On March 16, 2026, at GTC 2026, Nvidia CEO Jensen Huang presented DLSS 5, a real-time AI model based on neural rendering that realistically enhances lighting and material surfaces at up to 4K resolution while retaining the developer's intended art style. It is planned to release in fall of 2026. In a blog post on its website, Nvidia has announced that DLSS 5 will be available in such games as Assassin's Creed Shadows, Delta Force, Hogwarts Legacy, Naraka: Bladepoint, Phantom Blade Zero, Resident Evil Requiem, Starfield, The Elder Scrolls IV: Oblivion Remastered, and more. On May 31, 2026, Nvidia announced an updated version of Ray Reconstruction for DLSS 4.5 in a blog post, scheduled for release on all RTX GPUs in August of the same year. They said it is designed to better embed spatial awareness into scenes and analyze engine data on movements and lighting conditions, resulting in a sharper, more stable, and less noisy image. === Release timeline === == Technology == === DLSS 1 === The first iteration of DLSS is a predominantly spatial image upscaler with two stages, both relying on convolutional auto-encoder neural networks. The first step is an image enhancement network which uses the current frame and motion vectors to perform edge enhancement, and spatial anti-aliasing. The second stage is an image upscaling step which uses the single raw, low-resolution frame to upscale the image to the desired output resolution. Using just a single frame for upscaling means the neural network itself must generate a large amount of new information to produce the high-resolution output, which can result in slight hallucinations such as leaves that differ in style to the source content. The neural networks are trained on a per-game basis by generating a "perfect frame" using traditional supersampling to 64 samples per pixel, as well as the motion vectors for each frame. The data collected must be as comprehensive as possible, including as many levels, times of day, graphical settings, resolutions, etc. as possible. This data is also augmented using common augmentations such as rotations, colour changes, and random noise to help generalize the test data. Training is performed on Nvidia's Saturn V supercomputer. This first iteration received a mixed response, with many criticizing the often soft appearance and artifacts along with glitches in certain situations; likely a side effect of the limited data from only using a single frame input to the neural networks which could not be trained to perform optimally in all scenarios and edge-cases. Nvidia also demonstrated the ability for the auto-encoder networks to learn the ability to recreate depth-of-field and motion blur, although this functionality has never been included in a publicly released product. === DLSS 2 === DLSS 2 is a temporal anti-aliasing upsampling (TAAU) implementation, using data from previous frames extensively through sub-pixel jittering to resolve fine detail and reduce aliasing. The data DLSS 2 collects includes: the raw low-resolution input, motion vectors, depth buffers, and exposure / brightness information. It can also be used as a simpler TAA implementation where the image is rendered at 100% resolution, rather than being upsampled by DLSS, Nvidia brands this as DLAA (Deep Learning Anti-Aliasing). TAA(U) is used in many modern video games and game engines; however, all previous implementations have used some form of manually written heuristics to prevent temporal artifacts such as ghosting and flickering. One example of this is neighborhood clamping which forcefully prevents samples collected in previous frames from deviating too much compared to nearby pixels in newer frames. This helps to identify and fix many temporal artifacts, but deliberately removing fine details in this way is analogous to applying a blur filter, and thus the final image can appear blurry when using this method. DLSS 2 uses a convolutional auto-encoder neural network trained to identify and fix temporal artifacts, instead of manually programmed heuristics as mentioned above. Because of this, DLSS 2 can generally resolve detail better than other TAA and TAAU implementations, while also removing most temporal artifacts. This is why DLSS 2 can sometimes produce a sharper image than rendering at higher, or even native resolutions using traditional TAA. However, no temporal solution is perfect, and artifacts (ghosting in particular) are still visible in some scenarios when using DLSS 2. Because temporal artifacts occur in most art styles and environments in broadly the same way, the neural network that powers DLSS 2 does not need to be retrained when being used in different games. Despite this, Nvidia does frequently ship new minor revisions of DLSS 2 with new titles, so this could suggest some minor training optimizations may be performed as games are released, although Nvidia does not provide changelogs for these minor revisions to confirm this. The main advancements compared to DLSS 1 include: Significantly improved detail retention, a generalized neural network that does not need to be re-trained per-game, and ~2x less overhead (~1–2 ms vs ~2–4 ms). It should also be noted that forms of TAAU such as DLSS 2 are not upscalers in the same sense as techniques such as ESRGAN or DLSS 1, which attempt to create new information from a low-resolution source; instead, TAAU works to recover data from previous frames, rather than creating new data. In practice, this means low resolution textures in games will still appear low-resolution when using current TAAU techniques. This is why Nvidia recommends game developers use higher resolution textures than they would normally for a given rendering resolution by applying a mip-map bias when DLSS 2 is enabled. === DLSS 3 === Augments DLSS 2 with improved image quality and the introduction of a new motion interpolation feature, called Frame Generation. The DLSS Frame Generation algorithm takes two rendered frames from the rendering pipeline and generates a new frame that smoothly transitions between them. For every frame rendered, one additional frame is generated. DLSS 3.0 makes use of a new generation Optical Flow Accelerator (OFA) included in the Ada Lovelace architecture of GeForce RTX 40 series GPUs and with that is exclusive to them. The new OFA is said to be faster and more accurate than the one already available in previous Turing and Ampere RTX GPUs. === DLSS 3.5 === DLSS 3.5 adds Ray Reconstruction, replacing multiple denoising algorithms with a single AI model trained o
Morphing
Morphing is a special effect in motion pictures and animations that changes (or morphs) one image or shape into another through a seamless transition. Traditionally such a depiction would be achieved through dissolving techniques on film. Since the early 1990s, this has been replaced by computer software to create more realistic transitions. A similar method is applied to audio recordings, for example, by changing voices or vocal lines. == Early transformation techniques == Long before digital morphing, several techniques were used for similar image transformations. Some of those techniques are closer to a matched dissolve – a gradual change between two pictures without warping the shapes in the images – while others did change the shapes in between the start and end phases of the transformation. === Tabula scalata === Known since at least the end of the 16th century, Tabula scalata is a type of painting with two images divided over a corrugated surface. Each image is only correctly visible from a certain angle. If the pictures are matched properly, a primitive type of morphing effect occurs when changing from one viewing angle to the other. === Mechanical transformations === Around 1790 French shadow play showman François Dominique Séraphin used a metal shadow figure with jointed parts to have the face of a young woman changing into that of a witch. Some 19th century mechanical magic lantern slides produced changes to the appearance of figures. For instance a nose could grow to enormous size, simply by slowly sliding away a piece of glass with black paint that masked part of another glass plate with the picture. === Matched dissolves === In the first half of the 19th century "dissolving views" were a popular type of magic lantern show, mostly showing landscapes gradually dissolving from a day to night version or from summer to winter. Other uses are known, for instance Henry Langdon Childe showed groves transforming into cathedrals. The 1910 short film Narren-grappen shows a dissolve transformation of the clothing of a female character. Maurice Tourneur's 1915 film Alias Jimmy Valentine featured a subtle dissolve transformation of the main character from respected citizen Lee Randall into his criminal alter ego Jimmy Valentine. The Peter Tchaikovsky Story in a 1959 TV-series episode of Disneyland features a swan automaton transforming into a real ballet dancer. In 1985, Godley & Creme created a "morph" effect using analogue cross-fades on parts of different faces in the video for "Cry". === Animation === In animation, the morphing effect was created long before the introduction of cinema. A phenakistiscope designed by its inventor Joseph Plateau was printed around 1835 and shows the head of a woman changing into a witch and then into a monster. Émile Cohl's 1908 animated film Fantasmagorie featured much morphing of characters and objects drawn in simple outlines. == Digital morphing == In the early 1990s, computer techniques capable of more convincing results saw increasing use. These involved distorting one image at the same time that it faded into another through marking corresponding points and vectors on the "before" and "after" images used in the morph. For example, one would morph one face into another by marking key points on the first face, such as the contour of the nose or location of an eye, and mark where these same points existed on the second face. The computer would then distort the first face to have the shape of the second face at the same time that it faded the two faces. To compute the transformation of image coordinates required for the distortion, the algorithm of Beier and Neely can be used. === Concerns === In 1993 concerns were raised about the authenticity of digitally altered images arising from morphing. Images of fake "tween" people found half way between two morphed people created a skeptical media long before AI. === Early examples === In or before 1986, computer graphics company Omnibus created a digital animation for a Tide commercial with a Tide detergent bottle smoothly morphing into the shape of the United States. The effect was programmed by Bob Hoffman. Omnibus re-used the technique in the movie Flight of the Navigator (1986). It featured scenes with a computer generated spaceship that appeared to change shape. The plaster cast of a model of the spaceship was scanned and digitally modified with techniques that included a reflection mapping technique that was also developed by programmer Bob Hoffman. The 1986 movie The Golden Child implemented early digital morphing effects from animal to human and back. Willow (1988) featured a more detailed digital morphing sequence with a person changing into different animals. A similar process was used a year later in Indiana Jones and the Last Crusade to create Walter Donovan's gruesome demise. Both effects were created by Industrial Light & Magic, using software developed by Tom Brigham and Doug Smythe (AMPAS). In 1991, morphing appeared notably in the Michael Jackson music video "Black or White" and in the movies Terminator 2: Judgment Day and Star Trek VI: The Undiscovered Country. The first application for personal computers to offer morphing was Gryphon Software Morph on the Macintosh. Other early morphing systems included ImageMaster, MorphPlus and CineMorph, all of which premiered for the Amiga in 1992. Other programs became widely available within a year, and for a time the effect became common to the point of cliché. For high-end use, Elastic Reality (based on MorphPlus) saw its first feature film use in In The Line of Fire (1993) and was used in Quantum Leap (work performed by the Post Group). At VisionArt Ted Fay used Elastic Reality to morph Odo for Star Trek: Deep Space Nine. The Snoop Dogg music video "Who Am I? (What's My Name?)", where Snoop Dogg and the others morph into dogs. Elastic Reality was later purchased by Avid, having already become the de facto system of choice, used in many hundreds of films. The technology behind Elastic Reality earned two Academy Awards in 1996 for Scientific and Technical Achievement going to Garth Dickie and Perry Kivolowitz. The effect is technically called a "spatially warped cross-dissolve". The first social network designed for user-generated morph examples to be posted online was Galleries by Morpheus. In late 1991 Yeti Productions employed a young Stephen Regelous to run it's 486 computer graphics system in Wellington New Zealand. After producer Barry Thomas showed him Michael Jackson's "Black or White", Regelous wrote 10,000 lines of C++ code of triangle-based digital morphing software. Together they created morphing based TV commercials for The NZ Cancer Society, Fit food, Salvation Army and others. The Fit food commercial employed morphing with 35mm, pin registered, digitally controlled motion control designed and made by Russell Collins with software by Stephen Regelous. In Taiwan, Aderans, a hair loss solutions provider, did a TV commercial featuring a morphing sequence in which people with lush, thick hair morph into one another, reminiscent of the end sequence of the "Black or White" video. === Present use === Morphing algorithms continue to advance and programs can automatically morph images that correspond closely enough with relatively little instruction from the user. This has led to the use of morphing techniques to create convincing slow-motion effects where none existed in the original film or video footage by morphing between each individual frame using optical flow technology. Morphing has also appeared as a transition technique between one scene and another in television shows, even if the contents of the two images are entirely unrelated. The algorithm in this case attempts to find corresponding points between the images and distort one into the other as they crossfade. While perhaps less obvious than in the past, morphing is used heavily today. Whereas the effect was initially a novelty, today, morphing effects are most often designed to be seamless and invisible to the eye. A particular use for morphing effects is modern digital font design. Using morphing technology, called interpolation or multiple master tech, a designer can create an intermediate between two styles, for example generating a semibold font by compromising between a bold and regular style, or extend a trend to create an ultra-light or ultra-bold. The technique is commonly used by font design studios. == Software == After Effects Animate Elastic Reality FantaMorph Gryphon Software Morph Morph Age Morpheus Nuke SilhouetteFX
Color histogram
In image processing and photography, a color histogram is a representation of the distribution of colors in an image. For digital images, a color histogram represents the number of pixels that have colors in each of a fixed list of color ranges that span the image's color space (the set of all possible colors). A color histogram can be built for any kind of color space, although the term is more often used for three-dimensional spaces such as RGB or HSV. For monochromatic images, the term intensity histogram may be used instead. For multi-spectral images, where each pixel is represented by an arbitrary number of measurements (for example, beyond the three measurements in RGB), a color histogram is N-dimensional, with N being the number of measurements taken. Each measurement has its own wavelength range of the light spectrum, some of which may be outside the visible spectrum. If the set of possible color values is sufficiently small, each of those colors may be placed on a range by itself; then the histogram is merely the count of pixels that have each possible color. Most often, the space is divided into an appropriate number of ranges, often arranged as a regular grid, each containing many similar color values. A color histogram may also be represented and displayed as a smooth function defined over the color space that approximates the pixel counts. Like other kinds of histograms, a color histogram is a statistic that can be viewed as an approximation of an underlying continuous distribution of color values. == Overview == Color histograms are flexible constructs that can be built from images in various color spaces, whether RGB, rg chromaticity or any other color space of any dimension. A histogram of an image is produced first by discretization of the colors in the image into a number of bins, and counting the number of image pixels in each bin. For example, a red–blue chromaticity histogram can be formed by first normalizing color pixel values by dividing RGB values by R+G+B, then quantizing the normalized R and B coordinates into N bins each. A two-dimensional histogram of red–blue chromaticity divided into four bins (N=4) may yield a histogram similar to this table: A histogram can be N-dimensional. Although harder to display, a three-dimensional color histogram for the above example could be thought of as four separate red–blue histograms, where each of the four histograms contains the red–blue values for a bin of green (0–63, 64–127, 128–191, and 192–255). The histogram provides a compact summarization of the distribution of data in an image. A color histogram of an image is relatively invariant with translation and rotation about the viewing axis, and varies only slowly with the angle of view. By comparing histogram signatures of two images and matching the color content of one image with the other, a color histogram is particularly well suited for the problem of recognizing an object of unknown position and rotation within a scene. Importantly, translation of an RGB image into the illumination invariant rg-chromaticity space allows the histogram to operate well in varying light levels. 1. What is a histogram? A histogram is a graphical representation of the number of pixels in an image. In a more simple way to explain, a histogram is a bar graph, whose X-axis represents the tonal scale (black at the left and white at the right), and Y-axis represents the number of pixels in an image in a certain area of the tonal scale. For example, the graph of a luminance histogram shows the number of pixels for each brightness level (from black to white), and when there are more pixels, the peak at the certain luminance level is higher. 2. What is a color histogram? A color histogram of an image represents the distribution of the composition of colors in the image. It shows different types of colors appeared and the number of pixels in each type of the colors appeared. The relation between a color histogram and a luminance histogram is that a color histogram can be also expressed as “three luminance histograms”, each of which shows the brightness distribution of each individual red/green/blue color channel. == Characteristics of a color histogram == A color histogram focuses only on the proportion of the number of different types of colors, regardless of the spatial location of the colors. The values of a color histogram are from statistics. They show the statistical distribution of colors and the essential tone of an image. In general, as the color distributions of the foreground and background in an image are different, there might be a bimodal distribution in the histogram. For the luminance histogram alone, there is no perfect histogram and in general, the histogram can tell whether it is over-exposure or not, but there are times when you might think the image is over exposed by viewing the histogram; however, in reality it is not. == Principles of the formation of a color histogram == The formation of a color histogram is rather simple. From the definition above, we can simply count the number of pixels for each 256 scales in each of the 3 RGB channel, and plot them on 3 individual bar graphs. In general, a color histogram is based on a certain color space, such as RGB or HSV. When we compute the pixels of different colors in an image, if the color space is large, then we can first divide the color space into certain numbers of small intervals. Each of the intervals is called a bin. This process is called color quantization. Then, by counting the number of pixels in each of the bins, we get a color histogram of the image. The concrete steps of the principles can be viewed in Example 1. == Examples == === Example 1 === Given the following image of a cat (an original version and a version that has been reduced to 256 colors for easy histogram purposes), the following data represents a color histogram in the RGB color space, using four bins. Bin 0 corresponds to intensities 0–63 Bin 1 is 64–127 Bin 2 is 128–191 and Bin 3 is 192–255. === Example 2 === Application in camera: Nowadays, some cameras have the ability to show the 3 color histograms when we take photos. We can examine clips (spikes on either the black or white side of the scale) in each of the 3 RGB color histograms. If we find one or more clipping on a channel of the 3 RGB channels, then this would result in a loss of detail for that color. To illustrate this, consider this example: We know that each of the three R, G, B channels has a range of values from 0 to 255 (8 bit). So consider a photo that has a luminance range of 0–255. Assume the photo we take is made of 4 blocks that are adjacent to each other and we set the luminance scale for each of the 4 blocks of original photo to be 10, 100, 205, 245. Thus, the image looks like the topmost figure on the right. Then, we overexpose the photo a little, say, the luminance scale of each block is increased by 10. Thus, the luminance scale for each of the 4 blocks of new photo is 20, 110, 215, 255. Then, the image looks like the second figure on the right. There is not much difference between both figures, all we can see is that the whole image becomes brighter (the contrast for each of the blocks remain the same). Now, we overexpose the original photo again, this time the luminance scale of each block is increased by 50. Thus, the luminance scale for each of the 4 blocks of the new photo is 60, 150, 255, 255. The new image now looks like the third figure on the right. Note that the scale for the last block is 255 instead of 295, for 255 is the top scale and thus the last block has clipped. When this happens, we lose the contrast of the last 2 blocks, and thus we cannot recover the image no matter how we adjust it. To conclude, when taking photos with a camera that displays histograms, always keep the brightest tone in the image below the largest scale 255 on the histogram in order to avoid losing details. == Drawbacks and other approaches == The main drawback of histograms for classification is that the representation is dependent on the color of the object being studied, ignoring its shape and texture. Color histograms can potentially be identical for two images with different object content which happens to share color information. Conversely, without spatial or shape information, similar objects of different color may be indistinguishable based solely on color histogram comparisons. There is no way to distinguish a red and white cup from a red and white plate. Put it another way: histogram-based algorithms have no concept of a generic 'cup', and a model of a red and white cup is no use when given an otherwise identical blue and white cup. Another problem is that color histograms have high sensitivity to noisy interference such as lighting intensity changes and quantization errors. High dimensionality (bins) color histograms are also another issue. Some color histogram feature spaces often occupy more than one hundred di
Geometric hashing
In computer science, geometric hashing is a method for efficiently finding two-dimensional objects represented by discrete points that have undergone an affine transformation, though extensions exist to other object representations and transformations. In an off-line step, the objects are encoded by treating each pair of points as a geometric basis. The remaining points can be represented in an invariant fashion with respect to this basis using two parameters. For each point, its quantized transformed coordinates are stored in the hash table as a key, and indices of the basis points as a value. Then a new pair of basis points is selected, and the process is repeated. In the on-line (recognition) step, randomly selected pairs of data points are considered as candidate bases. For each candidate basis, the remaining data points are encoded according to the basis and possible correspondences from the object are found in the previously constructed table. The candidate basis is accepted if a sufficiently large number of the data points index a consistent object basis. Geometric hashing was originally suggested in computer vision for object recognition in 2D and 3D, but later was applied to different problems such as structural alignment of proteins. == Geometric hashing in computer vision == Geometric hashing is a method used for object recognition. Let’s say that we want to check if a model image can be seen in an input image. This can be accomplished with geometric hashing. The method could be used to recognize one of the multiple objects in a base, in this case the hash table should store not only the pose information but also the index of object model in the base. === Example === For simplicity, this example will not use too many point features and assume that their descriptors are given by their coordinates only (in practice local descriptors such as SIFT could be used for indexing). ==== Training Phase ==== Find the model's feature points. Assume that 5 feature points are found in the model image with the coordinates ( 12 , 17 ) ; {\displaystyle (12,17);} ( 45 , 13 ) ; {\displaystyle (45,13);} ( 40 , 46 ) ; {\displaystyle (40,46);} ( 20 , 35 ) ; {\displaystyle (20,35);} ( 35 , 25 ) {\displaystyle (35,25)} , see the picture. Introduce a basis to describe the locations of the feature points. For 2D space and similarity transformation the basis is defined by a pair of points. The point of origin is placed in the middle of the segment connecting the two points (P2, P4 in our example), the x ′ {\displaystyle x'} axis is directed towards one of them, the y ′ {\displaystyle y'} is orthogonal and goes through the origin. The scale is selected such that absolute value of x ′ {\displaystyle x'} for both basis points is 1. Describe feature locations with respect to that basis, i.e. compute the projections to the new coordinate axes. The coordinates should be discretised to make recognition robust to noise, we take the bin size 0.25. We thus get the coordinates ( − 0.75 , − 1.25 ) ; {\displaystyle (-0.75,-1.25);} ( 1.00 , 0.00 ) ; {\displaystyle (1.00,0.00);} ( − 0.50 , 1.25 ) ; {\displaystyle (-0.50,1.25);} ( − 1.00 , 0.00 ) ; {\displaystyle (-1.00,0.00);} ( 0.00 , 0.25 ) {\displaystyle (0.00,0.25)} Store the basis in a hash table indexed by the features (only transformed coordinates in this case). If there were more objects to match with, we should also store the object number along with the basis pair. Repeat the process for a different basis pair (Step 2). It is needed to handle occlusions. Ideally, all the non-colinear pairs should be enumerated. We provide the hash table after two iterations, the pair (P1, P3) is selected for the second one. Hash Table: Most hash tables cannot have identical keys mapped to different values. So in real life one won’t encode basis keys (1.0, 0.0) and (-1.0, 0.0) in a hash table. ==== Recognition Phase ==== Find interesting feature points in the input image. Choose an arbitrary basis. If there isn't a suitable arbitrary basis, then it is likely that the input image does not contain the target object. Describe coordinates of the feature points in the new basis. Quantize obtained coordinates as it was done before. Compare all the transformed point features in the input image with the hash table. If the point features are identical or similar, then increase the count for the corresponding basis (and the type of object, if any). For each basis such that the count exceeds a certain threshold, verify the hypothesis that it corresponds to an image basis chosen in Step 2. Transfer the image coordinate system to the model one (for the supposed object) and try to match them. If successful, the object is found. Otherwise, go back to Step 2. === Finding mirrored pattern === It seems that this method is only capable of handling scaling, translation, and rotation. However, the input image may contain the object in mirror transform. Therefore, geometric hashing should be able to find the object, too. There are two ways to detect mirrored objects. For the vector graph, make the left side positive, and the right side negative. Multiplying the x position by -1 will give the same result. Use 3 points for the basis. This allows detecting mirror images (or objects). Actually, using 3 points for the basis is another approach for geometric hashing. === Geometric hashing in higher-dimensions === Similar to the example above, hashing applies to higher-dimensional data. For three-dimensional data points, three points are also needed for the basis. The first two points define the x-axis, and the third point defines the y-axis (with the first point). The z-axis is perpendicular to the created axis using the right-hand rule. Notice that the order of the points affects the resulting basis
Natural language processing
Natural language processing (NLP) is the processing of natural language information by a computer. NLP is a subfield of computer science and is closely associated with artificial intelligence. NLP is also related to information retrieval, knowledge representation, computational linguistics, and linguistics more broadly. Major processing tasks in an NLP system include: speech recognition, text classification, natural language understanding, and natural language generation. == History == Natural language processing has its roots in the 1950s. Already in 1950, Alan Turing published an article titled "Computing Machinery and Intelligence," which proposed what is now called the Turing test as a criterion of intelligence, though at the time that was not articulated as a problem separate from artificial intelligence. The proposed test includes a task that involves the automated interpretation and generation of natural language. === Symbolic NLP (1950s – early 1990s) === The premise of symbolic NLP is often illustrated using John Searle's Chinese room thought experiment: Given a collection of rules (e.g., a Chinese phrasebook, with questions and matching answers), the computer emulates natural language understanding (or other NLP tasks) by applying those rules to the data it confronts. 1950s: The Georgetown experiment in 1954 involved fully automatic translation of more than sixty Russian sentences into English. The authors claimed that within three or five years, machine translation would be a solved problem. However, real progress was much slower, and after the ALPAC report in 1966, which found that ten years of research had failed to fulfill the expectations, funding for machine translation was dramatically reduced. Little further research in machine translation was conducted in America (though some research continued elsewhere, such as Japan and Europe) until the late 1980s when the first statistical machine translation systems were developed. 1960s: Some notably successful natural language processing systems developed in the 1960s were SHRDLU, a natural language system working in restricted "blocks worlds" with restricted vocabularies, and ELIZA, a simulation of Rogerian psychotherapy, written by Joseph Weizenbaum between 1964 and 1966. Despite using minimal information about human thought or emotion, ELIZA was able to produce interactions that appeared human-like. When the "patient" exceeded the very small knowledge base, ELIZA might provide a generic response, for example, responding to "My head hurts" with "Why do you say your head hurts?". Ross Quillian's successful work on natural language was demonstrated with a vocabulary of only twenty words, because that was all that would fit in a computer memory at the time. 1970s: During the 1970s, many programmers began to write "conceptual ontologies", which structured real-world information into computer-understandable data. Examples are MARGIE (Schank, 1975), SAM (Cullingford, 1978), PAM (Wilensky, 1978), TaleSpin (Meehan, 1976), QUALM (Lehnert, 1977), Politics (Carbonell, 1979), and Plot Units (Lehnert 1981). During this time, the first chatterbots were written (e.g., PARRY). 1980s: The 1980s and early 1990s mark the heyday of symbolic methods in NLP. Focus areas of the time included research on rule-based parsing (e.g., the development of HPSG as a computational operationalization of generative grammar), morphology (e.g., two-level morphology), semantics (e.g., Lesk algorithm), reference (e.g., within Centering Theory) and other areas of natural language understanding (e.g., in the Rhetorical Structure Theory). Other lines of research were continued, e.g., the development of chatterbots with Racter and Jabberwacky. An important development (that eventually led to the statistical turn in the 1990s) was the rising importance of quantitative evaluation in this period. === Statistical NLP (1990s–present) === Up until the 1980s, most natural language processing systems were based on complex sets of hand-written rules. Starting in the late 1980s, however, there was a revolution in natural language processing with the introduction of machine learning algorithms for language processing. This shift was influenced by increasing computational power (see Moore's law) and a decline in the dominance of Chomskyan linguistic theories (e.g. transformational grammar), whose theoretical underpinnings discouraged the sort of corpus linguistics that underlies the machine-learning approach to language processing. 1990s: Many of the notable early successes in statistical methods in NLP occurred in the field of machine translation, due especially to work at IBM Research, such as IBM alignment models. These systems were able to take advantage of existing multilingual textual corpora that had been produced by the Parliament of Canada and the European Union as a result of laws calling for the translation of all governmental proceedings into all official languages of the corresponding systems of government. However, many systems relied on corpora that were specifically developed for the tasks they were designed to perform. This reliance has been a major limitation to their broader effectiveness and continues to affect similar systems. Consequently, significant research has focused on methods for learning effectively from limited amounts of data. 2000s: With the growth of the web, increasing amounts of raw (unannotated) language data have become available since the mid-1990s. Research has thus increasingly focused on unsupervised and semi-supervised learning algorithms. Such algorithms can learn from data that has not been hand-annotated with the desired answers or using a combination of annotated and non-annotated data. Generally, this task is much more difficult than supervised learning, and typically produces less accurate results for a given amount of input data. However, large quantities of non-annotated data are available (including, among other things, the entire content of the World Wide Web), which can often make up for the worse efficiency if the algorithm used has a low enough time complexity to be practical. 2003: word n-gram model, at the time the best statistical algorithm, is outperformed by a multi-layer perceptron (with a single hidden layer and context length of several words, trained on up to 14 million words, by Bengio et al.) 2010: Tomáš Mikolov (then a PhD student at Brno University of Technology) with co-authors applied a simple recurrent neural network with a single hidden layer to language modeling, and in the following years he went on to develop Word2vec. In the 2010s, representation learning and deep neural network-style (featuring many hidden layers) machine learning methods became widespread in natural language processing. This shift gained momentum due to results showing that such techniques can achieve state-of-the-art results in many natural language tasks, e.g., in language modeling and parsing. This is increasingly important in medicine and healthcare, where NLP helps analyze notes and text in electronic health records that would otherwise be inaccessible for study when seeking to improve care or protect patient privacy. == Approaches: Symbolic, statistical, neural networks == Symbolic approach, i.e., the hand-coding of a set of rules for manipulating symbols, coupled with a dictionary lookup, was historically the first approach used both by AI in general and by NLP in particular: such as by writing grammars or devising heuristic rules for stemming. Machine learning approaches, which include both statistical and neural networks, on the other hand, have many advantages over the symbolic approach: both statistical and neural network methods tend to focus more on the most common cases extracted from a corpus of texts, whereas the rule-based approach needs to provide rules for both rare and common cases equally. language models, produced by either statistical or neural networks methods, are more robust to both unfamiliar (e.g. containing words or structures that have not been seen before) and erroneous input (e.g. with misspelled words or words accidentally omitted) in comparison to the rule-based systems, which are also more costly to produce. the larger such a (probabilistic) language model is, the more accurate it becomes, in contrast to rule-based systems that can gain accuracy only by increasing the amount and complexity of the rules leading to intractability problems. Rule-based systems are commonly used: when the amount of training data is insufficient to successfully apply machine learning methods, e.g., for the machine translation of low-resource languages such as provided by the Apertium system, for preprocessing in NLP pipelines, e.g., tokenization, or for post-processing and transforming the output of NLP pipelines, e.g., for knowledge extraction from syntactic parses. === Statistical approach === In the late 1980s and mid-1990s, the statistical approach ended a peri
Clue (mobile app)
Clue is a menstrual health app developed by the Berlin-based technology company BioWink GmbH. The app has over 15 million users from 180 countries. The startup has raised over $17 million from backers that include Union Square Ventures and Mosaic Ventures. == History == Clue was co-founded by Ida Tin, Hans Raffauf, Mike LaVigne and Moritz von Buttlar in 2012. BioWink GmbH launched the app in 2013. Ida Tin's stated goal was to take female reproductive health “out of taboo land” and to start “a reproductive health revolution.” Tin previously led motorbike tours around the world and wrote a book about her experience. By July 2017, the Clue app had more than 8 million active users on both Android and iOS. Users were representative of more than 180 countries. In 2015, BioWink GmbH closed a $7 million Series A funding round led by Union Square Ventures and Mosaic Ventures, bringing the company's total funding to $10 million. The company was listed as one of Europe's Hottest Startups in 2015 by Wired UK, with Clue being named one of the best apps in 2015 by both Apple and Google. In March 2018, the company launched an editorial site to serve as a resource for accessible and scientific menstrual health information. == Mobile app == The Clue mobile application calculates and predicts a user's period, fertile window, and premenstrual syndrome. It also informs users the most or least likely time for becoming pregnant and allows them to track more than 30 health categories, including sex, sleep, pain, exercise, hair, skin, digestion, emotions and energy. The app can also explain how pill dosages impact fertility and includes an alarm system to allow for reminders for taking pills. In 2015, the company closed a Series A funding round and announced plans to use the proceeds to expand features of the mobile app and hire more staff. Clue also partnered with universities such as Stanford University, Columbia University, University of Washington, and University of Oxford to advance female health research. Clue integrated with Apple Inc.'s HealthKit for iOS 9 in September 2015, allowing data such as body temperature, cervical mucus quality, menstruation, ovulation test results, sexual activity, and spotting directly to the app. In 2016, Clue was available in 15 languages on both iOS and Android. That same year, Clue introduced a cycle-sharing feature and in 2017 a pill-tracking option. In February 2018, Clue made its app available on the Fitbit Ionic smartwatch. In 2026, Clue partnered with UK-based digital healthcare platform Evaro, an NHS-licensed provider, to offer embedded prescription services within the app.
Cognition Network Technology
Cognition Network Technology (CNT), also known as Definiens Cognition Network Technology, is an object-based image analysis method developed by Nobel laureate Gerd Binnig together with a team of researchers at Definiens AG in Munich, Germany. It serves for extracting information from images using a hierarchy of image objects (groups of pixels), as opposed to traditional pixel processing methods. To emulate the human mind's cognitive powers, Definiens used patented image segmentation and classification processes, and developed a method to render knowledge in a semantic network. CNT examines pixels not in isolation, but in context. It builds up a picture iteratively, recognizing groups of pixels as objects. It uses the color, shape, texture and size of objects as well as their context and relationships to draw conclusions and inferences, similar to human analysis. == History == In 1994 Professor Gerd Binnig founded Definiens. CNT was first available with the launch of the eCognition software in May 2000. In June 2010, Trimble Navigation Ltd (NASDAQ: TRMB) acquired Definiens business asset in earth sciences markets, including eCognition software, and also licensed Definiens' patented CNT. In 2014, Definiens was acquired by MedImmune, the global biologics research and development arm of AstraZeneca, for an initial consideration of $150 million. == Software == Definiens Tissue Studio Definiens Tissue Studio is a digital pathology image analysis software application based on CNT. The intended use of Definiens Tissue Studio is for biomarker translational research in formalin-fixed, paraffin-embedded tissue samples which have been treated with immunohistochemical staining assays, or hematoxylin and eosin (H&E). The central concept behind Definiens Tissue Studio is a user interface that facilitates machine learning from example digital histopathology images to derive an image analysis solution suitable for the measurement of biomarkers and/or histological features within pre-defined regions of interest on a cell-by-cell basis, and within sub-cellular compartments. The derived image analysis solution is then automatically applied to subsequent digital images to objectively measure defined sets of multiparametric image features. These data sets are used for further understanding the underlying biological processes that drive cancer and other diseases. Image processing and data analysis are performed either on a local desktop computer workstation, or on a server grid. eCognition The eCognition suite offers three components that can be used stand-alone or in combination to solve image analysis tasks. eCognition Developer is a development environment for object-based image analysis. It is used in earth sciences to develop rule sets (or applications) for the analysis of remote sensing data. eCognition Architect enables non-technical users to configure, calibrate and execute image analysis workflows created in eCognition Developer. eCognition Server software provides a processing environment for batch execution of image analysis jobs. eCognition software is utilized in numerous remote sensing and geospatial application scenarios and environments, using a variety of data types: Generic: Rapid Mapping, Change Detection, Object Recognition By environment: Diverse Landcover Mapping, Urban Analysis (i.e. impervious surface area analysis for taxation, property assessment for insurance, inventory of green infrastructure), Forestry (i.e. biomass measurement, species identification, firescar measurement), Agriculture (i.e. regional planning, precision farming, crisis response), Marine and Riparian (i.e. ecosystem evaluation, disaster management, harbor monitoring). Other: Defense, security, atmosphere and climate The online eCognition community was launched in July 2009 and had 2813 members as of July 9, 2010. Membership is distributed globally and user conferences are held regularly, the last having taken place in November 2009 in Munich, Germany. The bi-annual GEOBIA (Geographic Object-Based Image Analysis) conference is heavily attended by eCognition users, with the majority of presentations based on eCognition software.