Fact-checked by Grok 2 weeks ago

Image subtraction

Image subtraction is a core technique in that computes the pixel-by-pixel difference between two registered images to generate a resultant image that emphasizes variations or changes while suppressing common background elements. Mathematically, for two input images f(x, y) and h(x, y), the subtracted image is given by g(x, y) = f(x, y) - h(x, y), where the result highlights discrepancies in intensity values across corresponding pixels. This operation assumes the images are aligned and, if necessary, normalized or convolved to account for differences in acquisition conditions such as illumination or . The method is particularly valuable for applications requiring the isolation of dynamic or evolving features. In , image subtraction enables mask-mode radiography by differencing pre-contrast and post-contrast X-rays to reveal structures and propagation without overlying anatomical noise. In and , it supports by subtracting consecutive video frames to identify moving objects against a static background. in and also relies on this technique to quantify alterations in landscapes or urban areas over time. In astronomy, image subtraction is essential for discovering transient celestial events, such as supernovae or variable stars, by aligning reference and new images, applying a space-varying convolution kernel to match point spread functions, and then differencing to detect faint changes amid galactic noise. Additional uses include industrial quality control, like bare printed circuit board inspection, where subtraction identifies defects by comparing a reference design against a captured image. Despite its simplicity, effective implementation often involves preprocessing steps like registration and noise reduction to minimize artifacts in the difference image.

Fundamentals

Definition

Image subtraction is a fundamental operation in that involves performing a pixel-wise subtraction between two or more registered images to generate a difference image, effectively removing common elements and isolating variations between them. In this process, the intensity value of each pixel in the second image is subtracted from the corresponding pixel in the first image, assuming the images are spatially aligned to ensure pixel-to-pixel correspondence. This technique highlights disparities that might otherwise be obscured in individual images, making it a core tool for comparative analysis. The concept traces its origins to early 20th-century , particularly in astronomy, where the blink comparator—developed by German physicist Carl Pulfrich for in 1904—enabled rapid alternation between two photographic plates to visually detect differences, such as moving celestial objects. This manual method laid the groundwork for subtraction techniques by emphasizing change detection through comparison. The transition to digital image subtraction occurred in the 1960s, driven by NASA's efforts, including the missions, which necessitated computerized processing of digitized photographs for operations like subtraction to enhance lunar surface details. Primarily, image subtraction serves to enhance subtle differences, suppress unchanging backgrounds, and detect motion or alterations while preserving unchanged regions intact. For instance, subtracting a pre-event from a post-event one can isolate modifications, such as structural changes in or environmental shifts in , thereby facilitating targeted analysis.

Mathematical Formulation

Image subtraction is fundamentally a pixel-wise arithmetic operation that computes the difference between corresponding intensity values in two or more digital images. For two input images I_1(x, y) and I_2(x, y), where (x, y) represents the spatial coordinates of a , the resulting difference D(x, y) is defined as D(x, y) = I_2(x, y) - I_1(x, y). This formulation assumes perfect between the images and directly yields regions of change or contrast where D(x, y) \neq 0, while unchanged areas approach zero. The operation is linear and commutative in the sense that I_1 - I_2 = -(I_2 - I_1), allowing flexibility in designating and images. Extensions to multi-image subtraction generalize this to a , particularly useful for suppressing static backgrounds or averaging multiple frames to enhance . The difference can be expressed as a weighted : D(x, y) = \sum_{i=1}^n w_i I_i(x, y), where n is the number of input images, and the weights w_i satisfy \sum_{i=1}^n w_i = 1 for normalized averaging (e.g., equal weights w_i = 1/n reduce random by a factor of \sqrt{n}). Negative weights can emphasize differences from a reference frame, as in background subtraction techniques. To mitigate effects from global shifts or varying illumination, the raw difference is often . A standard approach is z-score , which standardizes the : D'(x, y) = \frac{D(x, y) - \mu_D}{\sigma_D}, where \mu_D and \sigma_D denote the mean and standard deviation of D across all pixels, respectively. This yields a zero-mean, unit-variance , enabling consistent thresholding (e.g., |D'(x, y)| > k for , with k typically 2–3). Such is crucial in applications requiring statistical analysis of differences. In implementations, images are quantized to finite bit depths, such as 8-bit (values 0–255) or 16-bit , necessitating handling of and underflow during . The result is typically clipped: D(x, y) = \max(0, \min(L-1, I_2(x, y) - I_1(x, y))), where L is the number of gray levels (e.g., 256 for 8-bit). For preserving negative differences, signed formats or floating-point representations are used, with post-clipping to the display range. This ensures computational stability in software like or .

Methods

Basic Subtraction Techniques

Basic image subtraction techniques involve straightforward arithmetic operations on values to highlight differences between s, assuming the input s are already aligned spatially. Direct subtraction computes the difference D by subtracting the intensities of a reference I_2 from a target I_1, such that D(x, y) = I_1(x, y) - I_2(x, y) for each position (x, y). This process begins with selecting or acquiring the two s, ensuring they share the same dimensions and —typically through manual cropping or simple translation if minor shifts exist, without advanced registration. The resulting difference reveals changes, such as added or removed features, where positive values indicate brighter regions in I_1 and negative values indicate darker ones; to handle negatives in unsigned formats like 8-bit , implementations often clip to zero or use absolute differences |I_1(x, y) - I_2(x, y)|. This method is computationally efficient, requiring only per-pixel operations, and serves as a foundational tool for in controlled environments. In static scenes, background subtraction employs a reference frame representing the unchanging to isolate foreground elements, particularly moving objects. A single reference background image B is captured when no motion is present, and subsequent frames I_t are subtracted from it: D_t(x, y) = |I_t(x, y) - B(x, y)|. The mitigates sign issues and emphasizes deviations caused by motion or changes. This technique assumes a camera and minimal environmental variations, making it suitable for simple setups where the background remains consistent over time. Pixels in D_t with low values correspond to static background, while higher values delineate foreground objects. Temporal subtraction extends this idea to dynamic sequences by differencing consecutive frames in video to detect motion, without needing a predefined static reference. For a video sequence, the difference is computed as D_t(x, y) = |I_t(x, y) - I_{t-1}(x, y)|, where I_t is the frame and I_{t-1} the previous one; this captures inter-frame changes attributable to object movement. The method is simple and capable but sensitive to camera shake or rapid lighting shifts, as it relies solely on temporal adjacency. A basic implementation in might proceed as follows:
for each frame I_t in video sequence:
    if t > 1:
        compute D_t = abs(I_t - I_{t-1})  // element-wise absolute difference
        apply optional normalization to D_t (e.g., scale to [0, 255])
    output D_t as motion map
This approach highlights moving edges effectively in uniform motion scenarios. Following subtraction, thresholding binarizes the difference image to segment changes into a clear foreground mask, enhancing interpretability. A simple binary threshold T is applied such that the output mask M(x, y) = 1 if D(x, y) > T, and 0 otherwise, where T is chosen empirically (e.g., based on noise level, often 20-50 for 8-bit images). This step suppresses minor noise-induced differences while preserving significant changes, facilitating subsequent tasks like object counting. For instance, in motion detection, regions where M = 1 represent detected alterations. The choice of T critically affects sensitivity, with lower values capturing subtle motions but risking false positives.

Advanced Subtraction Methods

Advanced subtraction methods extend basic pixel-wise by incorporating transformations, statistical averaging, or computational models to address issues such as variations, amplification, and periodic artifacts in real-world scenarios. These techniques enhance the robustness of images, particularly in domains requiring high like medical diagnostics and scientific analysis. Logarithmic subtraction applies a logarithmic transformation to both the target and reference images prior to subtraction, which normalizes exponential intensity variations due to differing exposures or attenuations, commonly employed in imaging such as (). This approach converts multiplicative differences into additive ones, yielding subtraction images that isolate enhancements while minimizing background inconsistencies. For instance, in , the logarithm of the intensities is subtracted to produce a linear representation of iodine concentration changes. Multi-frame averaging improves suppression in by computing the of multiple reference images as the , reducing random variations in the reference and thus in the resulting image. The is calculated as D(x, y) = I(x, y) - \frac{1}{n} \sum_{i=1}^n I_i(x, y), where I(x, y) is the target image at (x, y), and I_i(x, y) are the reference frames. This method is particularly effective for low-signal environments, as averaging n frames can reduce variance by a factor of $1/\sqrt{n}. Frequency-domain subtraction performs the operation after transforming images into the Fourier domain using the (FFT), allowing targeted suppression of periodic noise or low-frequency trends that persist in spatial subtraction. In this approach, the FFTs of the target and reference are subtracted, optionally with filtering to emphasize high-frequency changes, before inverse transformation back to the spatial domain. Machine learning-assisted subtraction leverages neural networks, such as autoencoders, to predict and refine difference images by learning non-linear mappings from paired or sequential inputs, emerging prominently in the for handling complex variations like motion or illumination changes. Autoencoders, for example, encode input images into a and decode to reconstruct references or directly estimate differences, outperforming traditional methods in tasks by adapting to scene-specific patterns. These methods have been applied in for temporal analysis, where convolutional autoencoders facilitate robust subtraction under varying conditions.

Applications

Medical Imaging

In medical imaging, () plays a pivotal role in visualizing blood vessels by subtracting a pre-contrast "" image from subsequent post-contrast images, effectively removing overlying bone and to isolate vascular structures. This technique enhances contrast and detail for diagnosing vascular diseases such as stenoses, aneurysms, and occlusions. Introduced by in the late 1970s, with clinical establishment in the early 1980s, as the first computer-assisted two-dimensional method, revolutionized by enabling real-time fluoroscopic guidance during procedures like catheterizations. Temporal subtraction in chest radiography facilitates the detection of interval changes in lung pathology by subtracting a prior radiograph from a current one, thereby suppressing stationary anatomical structures like ribs and the heart to highlight new or evolving abnormalities such as nodules, infiltrates, or effusions. This reduces visual clutter and aids radiologists in identifying subtle lung alterations that might otherwise be obscured. Studies have demonstrated significant improvements in diagnostic performance; for instance, one investigation reported ROC area (Az) improving from 0.89 to 0.98 with temporal subtraction images. Another study on peripheral lung nodules showed enhanced accuracy, with the figure-of-merit increasing from 0.920 to 0.980 in observer performance tests for certified radiologists. Image subtraction techniques in and computed (CT) are employed to accentuate tumors and lesions by mitigating from dense tissues or prior scans. In , temporal subtraction between sequential exams highlights developing masses or microcalcifications, while contrast-enhanced digital subtracts low-energy from high-energy images to reveal enhancing lesions indicative of . Research from the 2000s indicated detection improvements of 20-30%, with one study noting a 21.2% increase in radiologist sensitivity for cancers using subtraction-aided systems. In CT, temporal subtraction isolates pathological changes, such as small tumors; studies using non-rigid registration for temporal subtraction have shown improved detection of lung nodules and metastases. These methods are particularly valuable in follow-up imaging for monitoring treatment response or progression. Hybrid methods combining segmentation techniques such as region growing, thresholding, and clustering have advanced automated anomaly detection in magnetic resonance imaging (MRI) sequences, particularly for brain tumors and other neurological changes. These approaches enable precise isolation and classification of lesions like gliomas or metastases. Seminal works in hybrid segmentation, such as those combining region growing with thresholding for MRI tumor boundaries, achieve high Dice similarity coefficients (around 0.90) for anomaly outlining, supporting early diagnostic interventions. This fusion reduces false positives from motion artifacts and enhances workflow in clinical settings.

Astronomy and Remote Sensing

In astronomy, image subtraction has been instrumental in detecting transient celestial events since the early , with the blink serving as a foundational manual tool. Invented around 1904, this device allowed astronomers to rapidly alternate between two photographic plates of the same sky region, highlighting differences such as moving objects or variable stars. Its most famous application occurred in 1930 when used a blink at to discover by identifying its motion against background stars in plates taken 23 days apart. Modern digital equivalents automate this process through software pipelines that perform pixel-wise subtraction after alignment, enabling efficient detection of variables like novae or asteroids in large datasets. A seminal advancement in subtraction for astronomy is the Alard-Lupton algorithm, introduced in 1998, which optimizes the of images with differing seeing conditions by convolving one image with a space-varying to match the point spread function of the other. This method has become widely adopted for difference imaging analysis (DIA), particularly in monitoring variable stars, where it preserves photometric precision even in crowded fields by minimizing artifacts from imperfect alignment. For instance, in observations, the algorithm has enabled the detection of faint variables with signal-to-noise ratios improved by factors of 2-3 compared to traditional aperture photometry. In large-scale astronomical surveys, difference imaging subtracts reference template images from new exposures to isolate transients like supernovae against static backgrounds. The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST), which began operations in 2025 with first light on June 23, 2025, and full survey later that year, relies on such techniques in its to detect millions of supernovae annually, achieving detection efficiencies above 90% for events brighter than 24th in early visits. This approach is crucial for , as it handles the survey's vast data volume—expected to exceed 30 terabytes nightly—while flagging cosmic events for follow-up. In , image subtraction facilitates by differencing multispectral satellite images over time, revealing alterations like . Using Landsat series data, post-2010 studies have applied NDVI-based image differencing to monitor loss, achieving user's accuracies of 80-90% in identifying disturbed areas when validated against . For example, in the , this method has quantified annual rates with spatial resolutions of 30 meters, supporting global carbon accounting efforts. Additionally, atmospheric correction in multispectral often employs dark-object subtraction to remove or path radiance effects, where the minimum digital number in a band—assumed to represent atmospheric —is subtracted from all pixels, improving retrieval by 5-10% in cloudy scenes.

Industrial and Security Uses

In industrial manufacturing, image subtraction serves as a foundational technique for defect detection by comparing a image of a flawless product against images captured on lines, highlighting anomalies such as scratches, dents, or misalignments through pixel-wise differences. This method has been integral to in the automotive sector since the 1990s, when systems became widespread for inspecting body panels and components, enabling automated identification of surface flaws to reduce manual errors and downtime. For instance, in automotive , subtracting aligned frames from real-time captures allows for rapid flagging of defects like inconsistencies or errors, supporting high-volume rates while maintaining . In security applications, image subtraction underpins background subtraction algorithms in video surveillance systems, isolating moving objects from static scenes to detect intruders or unusual activities in CCTV footage. A prominent example is the ViBe (Visual Background Extractor) algorithm, introduced in 2011, which models pixel backgrounds using sample-based comparisons and random updates to achieve robust foreground segmentation even under varying lighting or camera jitter. ViBe enables real-time processing at over 200 frames per second on standard hardware, making it suitable for intruder detection in perimeter surveillance, where it distinguishes human motion from environmental noise like swaying trees or shadows. This approach has been widely adopted in commercial CCTV setups for its low computational overhead and effectiveness in dynamic environments. Non-destructive testing (NDT) in leverages image subtraction on ultrasonic or images to reveal subsurface cracks without damaging components, enhancing structural integrity assessments for parts. In ultrasonic infrared thermography, for example, a pre-excitation is subtracted from post-excitation frames to isolate heat patterns generated by crack-induced , allowing detection of microcracks in blades or composite materials. This technique significantly improves efficiency over traditional methods by enabling faster, non-contact scans that cover larger areas, reducing downtime in by streamlining defect localization. In the 2020s, image subtraction has integrated with (IoT) ecosystems in smart factories, where devices perform on-site processing to minimize latency in quality monitoring. These systems connect cameras and sensors via IoT networks to subtract reference models from live feeds at the edge, enabling defect alerts without relying on transmission, which supports scalable operations in distributed manufacturing environments. Such implementations handle thousands of images per minute, fostering and adaptive production lines in Industry 4.0 settings.

Challenges and Considerations

Noise and Artifact Management

In image subtraction, primary sources of noise include Poisson noise prevalent in photon-limited imaging modalities such as systems used in (), where the noise variance equals the mean number of detected photons, resulting in signal-dependent fluctuations that degrade image quality at low radiation doses. , arising from thermal and electronic sources in digital sensors like CCDs and arrays, is additive and signal-independent, characterized by a zero-mean with variance \sigma^2. Post-subtraction, the (SNR) is quantified as the ratio of the signal difference to the noise standard deviation in the resulting difference image, often reduced due to the propagation of uncorrelated noise from input images, which adds in quadrature and can halve the effective SNR compared to individual frames. The basic subtraction process is particularly susceptible to these noise effects, amplifying random variations in the difference image and potentially obscuring subtle features. Artifacts in subtraction results commonly manifest as ghosting, caused by imperfect alignment or between reference and target images, leading to residual structures that mimic true changes. In applications, for instance, patient or cardiac motion can produce ghosting of vessels, resulting in misregistration where anatomical features appear duplicated or displaced in the image. To mitigate and artifacts in images, Gaussian filtering applies a operation defined as D_{\text{filtered}} = D * G, where D is the difference image and G is a Gaussian with deviation \sigma tuned to random fluctuations while preserving edges, effectively reducing high-frequency components. further enhances contrast in the filtered image by redistributing pixel intensities to achieve a uniform histogram, improving visibility of low-contrast differences without introducing additional . Techniques like Gaussian filtering and histogram equalization can improve metrics such as mean squared error (MSE) in low-dose X-ray imaging. Quantitative evaluation of noise and artifact management in subtraction relies on metrics such as (MSE), computed as the average of squared differences between an expected ideal difference image and the observed result, providing a measure of overall distortion. Recent advances include deep learning-based denoising methods, such as convolutional neural networks, which outperform traditional filters in low-dose by learning noise patterns from data.

Alignment and Registration Issues

Misalignment in image subtraction occurs when corresponding features in the input images do not occupy the same spatial positions, leading to artifacts that obscure meaningful differences. In , such as , patient motion during acquisition introduces translational and rotational shifts between mask and images, resulting in misregistration artifacts that degrade diagnostic quality. In astronomical applications, atmospheric turbulence causes distortions, blurring and displacing stellar features across sequential exposures and complicating the subtraction of background noise. Similarly, in industrial inspection, camera shake from vibrations or handheld operation produces unintended translations and rotations, misaligning images captured before and after a process change. To mitigate these issues, image registration techniques align the images prior to subtraction by estimating a spatial that maps one image onto the other. Rigid registration assumes global similarity and corrects for and using feature matching methods, such as detecting keypoints like SIFT descriptors to establish correspondences and compute the parameters. For scenarios involving uniform scaling or shearing, affine registration extends rigid methods by incorporating a 6-degree-of-freedom , applied as I_2'(x, y) = I_2(T(x, y)), where T represents the affine mapping and I_2' is the transformed second image. These techniques are computationally efficient and sufficient for rigid structures, but they fail when local deformations occur, as in soft tissues or distorted fields. Non-rigid registration addresses deformable misalignments using models like thin-plate splines (), which interpolate a smooth warping based on sparse landmark correspondences while minimizing bending energy to preserve anatomical plausibility. , originally developed for in the 1970s and adapted for landmark-based in the late 1980s, excels in medical subtraction tasks involving organ motion, such as aligning pre- and post-contrast scans of deformable tissues. In astronomy, similar deformable approaches correct for non-uniform atmospheric effects across the field of view. The effectiveness of registration is evaluated using landmark-based metrics, particularly the target registration error (TRE), which quantifies the between corresponding anatomical points after , ideally approaching zero for accurate . Modern systems in the 2020s target sub-pixel precision to ensure subtraction highlights subtle changes without introducing false positives from residual misalignment. methods, including networks and transformer-based models, have emerged as powerful tools for non-rigid registration, achieving high accuracy in multi-modal as of 2024.

References

  1. [1]
    [PDF] Digital Image Processing 15CS753 - csenotes
    Oct 28, 2020 · Image Subtraction: • An application of image subtraction is in the enhancement of differences between images. • Consider the following figures.
  2. [2]
    [PDF] Lecture 5: Point Processing of Images
    Sep 20, 2005 · Image subtraction can be used to suppress background information and ... Applications: Medical imaging, motion detection, change detection.
  3. [3]
    [PDF] Digital Image Processing-3
    2. Image subtraction: This operation is carried out on co-registered scenes of the same area acquired at different times or dates, for change detection. This ...<|control11|><|separator|>
  4. [4]
    Image subtraction using a space-varying kernel
    Abstract. Image subtraction is a method by which one image is matched against another by using a convolution kernel, so that they can be differenced to detect ...
  5. [5]
    [PDF] A New Based Image Subtraction Algorithm for Bare PCB Defect ...
    In this research article, the main focus is to develop a bare PCB inspection technique through an image subtraction algorithm using a new image subtraction.
  6. [6]
    Image Subtraction - an overview | ScienceDirect Topics
    Subtraction images are defined as digital images obtained by subtracting one image from another, which removes identical information and highlights differences, ...
  7. [7]
    Image Arithmetic - Pixel Subtraction
    The pixel subtraction operator takes two images as input and produces as output a third image whose pixel values are simply those of the first image minus the ...Missing: definition | Show results with:definition
  8. [8]
    Image Arithmetic in DSP: Image Averaging and Image Subtraction
    Mar 3, 2020 · Moreover, we'll see that image subtraction allows us to compare images and detect changes. This makes image subtraction a fundamental operation ...
  9. [9]
    The 'blink comparator', as Shakespeare liked it | New Scientist
    Aug 3, 2005 · In 1904 the German instrument-maker Carl Pulfrich invented the “blink comparator”, which flickered images fast enough for astronomers to spot ...Missing: history | Show results with:history
  10. [10]
    Digital Image Processing - Medical Applications - Space Foundation
    Nov 3, 2017 · Digital imaging was developed in the mid-1960s to explore the surface of the Earth's moon. Conventional camera equipment mounted in the ...Missing: history | Show results with:history
  11. [11]
    History of the digital camera and digital imaging
    Tools included addition, subtraction, and ratioing of digital images. Further, the MIT group was developing computer digital image processing routines by 1972 ...
  12. [12]
    Image subtraction – Knowledge and References - Taylor & Francis
    Image subtraction refers to the process of subtracting one image from another on a pixel-by-pixel basis. This technique is commonly used in surveillance ...Missing: definition | Show results with:definition
  13. [13]
    [PDF] Problem Solutions–Student Set Rafael C. Gonzalez Richard E. Woods
    Change detection via subtraction is based on computing the simple difference d(x; y) = g(x; y) ¡ f(x; y). The resulting image d(x; y) can be used in two ...
  14. [14]
    On the optimal z-score threshold for SISCOM analysis to localize the ...
    Apr 17, 2018 · The difference image was smoothed using a 3D-Gaussian smoothing kernel (full width at half maximum = 15 mm) and transformed into a z-score ...
  15. [15]
    [PDF] Non-parametric Model for Background Subtraction
    The non-parametric model estimates pixel intensity probability based on samples, handles non-static backgrounds, and adapts quickly to scene changes.
  16. [16]
    [PDF] An Improved Motion Detection Method for Real-Time Surveillance
    Feb 19, 2008 · Temporal differencing is based on frame difference which attempts to detect moving regions by making use of the difference of consecutive frames ...
  17. [17]
    [PDF] Motion Detection Based on Frame Difference Method
    The frame difference method captures a static frame, then consecutive frames. It calculates the absolute difference between frames, converts to gray and binary ...
  18. [18]
    Digital Subtraction Angiography - Radiologica
    Jun 28, 2020 · As attenuation is exponential, subtracting the logarithms of the images results in a subtraction image containing only the contrast information.
  19. [19]
    [PDF] aapm report no. 15
    Generally, DSA imaging systems use logarithmic processing of the video signal to insure that a vessel of uniform diameter and uniform iodine concentration ...
  20. [20]
    Signal averaging improves signal-to-noise in OCT images
    The high acquisition speeds of modern OCT systems enable the improvement of the signal-to-noise ratio by averaging multiple signals, for instance by fusing OCT ...<|separator|>
  21. [21]
    Efficient Image Processing Technique for Detecting Spatio-Temporal ...
    The registered images are then processed through frequency-domain subtraction to visualise and quantify erosion depth. Our technique tracks changes across ...
  22. [22]
    Application of frequency domain processing to X-ray radiographic ...
    Typically implemented via frequency-domain subtraction, high-pass filtering removes lowfrequency components obtained from low-pass filtering while ...
  23. [23]
    Neural Network Autoencoder for Change Detection in Satellite ...
    This paper introduces a new algorithm for satellite image time series change detection. This algorithm is based on image subtraction analysis and does not ...
  24. [24]
    Effective image differencing with convolutional neural networks for ...
    We present here a deep-learning approach to transient detection that encapsulates all the steps of a traditional image-subtraction pipeline.
  25. [25]
    The history of digitalization in medical technology
    Sep 1, 2022 · The first computer-assisted two-dimensional X-ray technique was known as digital subtraction angiography (DSA) and became increasingly ...
  26. [26]
    Digital subtraction angiography | Radiology Reference Article
    Jul 29, 2018 · Digital subtraction angiography (DSA) is a fluoroscopic technique used extensively in interventional radiology for visualization of blood vessels.
  27. [27]
    Improved Detection of Lung Nodules by Using a Temporal ...
    CONCLUSION: The temporal subtraction technique is useful for improving detection accuracy for peripheral lung nodules on digital chest radiographs. © RSNA, 2002 ...
  28. [28]
    effect of temporal subtraction images on detection accuracy - PubMed
    Conclusion: The temporal subtraction technique can significantly improve sensitivity and specificity for detection of interval change in chest radiographs.Missing: studies | Show results with:studies
  29. [29]
    Improvement in Sensitivity of Screening Mammography with ...
    Use of the computer-aided detection system significantly improved the detection of breast cancer by increasing radiologist sensitivity by 21.2%.
  30. [30]
    Improved Detection of Small Lung Cancers with Dual-Energy ...
    Although the detection rate of missed cancers in our series was significantly improved from 40% to 59% by use of dual-energy subtraction images in the observer ...<|separator|>
  31. [31]
    Digital subtraction of temporally sequential mammograms for ... - PMC
    Sep 14, 2021 · Temporal subtraction is more effective in the microcalcifications detection and classification and may play a role in automated diagnosis systems.
  32. [32]
    Review on Hybrid Segmentation Methods for Identification of Brain ...
    Jul 11, 2022 · Tumor segmentation is possible with different soft clustering techniques and also with traditional image processing techniques.Missing: subtraction | Show results with:subtraction
  33. [33]
    [PDF] A HYBRID APPROACH BASED SEGMENTATION TECHNIQUE ...
    The, proposed system mainly focused on medical imaging to extract tumor and especially in MRI images. It has high-resolution and accurate positioning of soft ...
  34. [34]
    Finding Pluto With the Blink Comparator
    May 14, 2015 · Tombaugh operated the instrument, built by the Zeiss company and popularly called a “blink comparator,” by rotating a small dial that flipped a ...Missing: Dodge | Show results with:Dodge
  35. [35]
    The Blink Comparator - The Discovery of Pluto
    The Blink Comparator. It is possible that, without such an instrument as the blink comparator, Pluto would not have been discovered until many years later.
  36. [36]
    A Method for Optimal Image Subtraction - IOPscience
    A Method for Optimal Image Subtraction. C. Alard and Robert H. Lupton. © 1998 ... We also present some light curves of variable stars and show that ...
  37. [37]
    [PDF] Image-Subtraction Photometry of Variable Stars in the Globular ...
    We have applied Alard's image subtraction method (ISIS v2.1) to the observations of the globular clusters NGC 6388 and NGC 6441 previously analyzed using ...
  38. [38]
    Testing the LSST Difference Image Analysis Pipeline Using ...
    May 13, 2024 · We evaluate the performance of the Legacy Survey of Space and Time Science Pipelines Difference Image Analysis (DIA) on simulated images.Abstract · Introduction · Difference Image Algorithms · DIA Pipeline Analysis
  39. [39]
    SNIa-Cosmology Analysis Results from Simulated LSST Images
    Nov 12, 2021 · This paper analyzes simulated LSST images of Type Ia Supernovae (SNIa) to test the LSST pipeline and recover cosmology parameters.
  40. [40]
    Accuracy Assessments of Local and Global Forest Change Data to ...
    As a result, we found that the producer's and user's accuracies of disturbances in the Global Forest Change map were 30.1–76.8% and 50.5–90.2%, respectively, ...2. Materials And Methods · 2.4. Landsat, Sentinel-2... · 3. Results<|control11|><|separator|>
  41. [41]
    Landsat TM imagery and NDVI differencing to detect vegetation ...
    Dec 18, 2013 · In the present study, we propose a vegetation change detection analysis based on the NDVI differencing technique to assess forest cover changes ...
  42. [42]
    An improved dark-object subtraction technique for atmospheric ...
    An improved dark-object subtraction technique is demonstrated that allows the user to select a relative atmospheric scattering model to predict the haze values.
  43. [43]
    Research on detection and classification of automotive body surface ...
    This paper proposes a highly robust method for classifying body surface defects. Firstly, an edge detection method that integrates the wavelet transform and the ...Missing: assembly | Show results with:assembly
  44. [44]
    The Evolution and Impact of Machine Vision in Factory Automation
    By the 1990s, vision systems started to become commonplace, with many manufacturers adopting them in their operations. Modern machine vision systems are well- ...
  45. [45]
    80 years of machine vision history explained: Key milestones from ...
    Apr 9, 2025 · Machine vision began post-WWII, with early AI foundations, the 1980s as a discrete field, and 1990s growth, and deep learning in the 2010s.
  46. [46]
    A Universal Background Subtraction Algorithm for Video Sequences
    Aug 9, 2025 · This paper presents a technique for motion detection that incorporates several innovative mechanisms.
  47. [47]
    Ultrasonic infrared thermal wave nondestructive evaluation for crack ...
    Jan 8, 2008 · The ultrasonic infrared thermal wave nondestructive detection is fast, sensitive for cracks, especially cracks that vertical with structure's ...Missing: subtraction destructive
  48. [48]
    Advances in Automated NDT: Viable Inspection Solutions for ...
    Mar 2, 2025 · Automated Ultrasonic Testing (UT) systems play a key role in improving efficiency, reducing inspection time, and enhancing imaging and defect detection ...The Need For Advanced Tools... · Inspection Planning Tools · Ndt Analysis Tools
  49. [49]
    Edge Computing Examples in Manufacturing | OTAVA
    In manufacturing, the shift toward edge computing is driven by rising pressure for agility, safety, and uptime. Facilities are handling more data than ever ...Missing: 2020s | Show results with:2020s
  50. [50]
    Manufacturing the Future of AI with Edge Computing
    Sep 15, 2021 · Edge computing allows sensor-enabled devices to collect and process data locally to deliver insights on the factory floor without having to communicate with ...Missing: subtraction | Show results with:subtraction<|separator|>
  51. [51]
  52. [52]
  53. [53]
    [PDF] arXiv:1202.2902v1 [astro-ph.IM] 14 Feb 2012
    Feb 14, 2012 · In image subtraction we assume that we have two im- ages of ... This bias will enable such a fit with vastly reduced mean–squared error.
  54. [54]
    Image registration for applications in Digital Subtraction Angiography
    A serious problem encountered in this technique is misregistration of images due to patient motion. The resulting artifacts which arise from the misalignment ...
  55. [55]
    Difference image analysis: extension to a spatially varying ...
    Astronomical images are formed on a discrete detector array, after the sky scene suffers attenuation, geometrical distortion and blurring by the atmosphere and ...
  56. [56]
    Image alignment and registration with OpenCV - PyImageSearch
    Aug 31, 2020 · We'll learn how OpenCV can help us align and register our images using keypoint detectors, local invariant descriptors, and keypoint matching.
  57. [57]
    Comparison and evaluation of rigid, affine, and nonrigid registration ...
    There was no significant difference between rigid and affine registration methods. Conclusion: Nonrigid registration significantly reduces the effects of ...
  58. [58]
    Nonrigid Image Registration in Digital Subtraction Angiography ...
    Jun 29, 2013 · In their method, nonrigid motions are iteratively modeled using thin-plate spline (TPS) which is calculated from a set of corresponding interest ...
  59. [59]
    Estimation and Reduction of Target Registration Error - PMC - NIH
    Similarly, TRE is defined as the Euclidean distance between the target position in image space and the position of the target transformed from image space ...
  60. [60]
    [2405.12927] On Image Registration and Subpixel Estimation - arXiv
    May 21, 2024 · Image registration is a classical problem in machine vision which seeks methods to align discrete images of the same scene to subpixel accuracy in general ...