Digital Image Processing

By W. Burger, M. Burge. 2016

12,987 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Energy Estimator Networks (2018, background): “3 (b) is the denoising by median + Gaussian ﬁlters, a baseline in signal processing (Gonzalez & Woods, 2012).”
Weighted Guided Image Filtering (2016, background): “̂G(p′) is the magnitude of the Sobel gradient, and ̌G(p′) is the magnitude of the Roberts gradient [24].”
SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection (2018, background): “The image pyramid [1,15], which is one of the most popular approaches to multi-scale detection, has been applied to many applications such as pedestrian detection [5,6,7,8], human pose estimation [36], and object detection [10].”
Hierarchical Image Saliency Detection on Extended CSSD (2016, neutral): “3(b) by the watershed-like method [15].”
Defining coherent vortices objectively from the vorticity (2015, background): “(22) (1)Frame-invariance cannot be defined restricted to a curvilinear surface, as Euclidean frame changes take the observer off the surface.”
A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure (2015, methodology): “Given an explicit model, the most fundamental, albeit slow, approach to detecting such objects in an image is using a generalized Hough transform [82,83].”
Using hyperspectral imaging to discriminate yellow leaf curl disease in tomato leaves (2018, methodology): “…any interference from the background by two steps: the first is to create a binary mask using the grey image at Wavelength 1 with the Otsu’s method (Gonzalez and Woods 2002), and the second is to perform the logical AND operator between the mask and both selected sensitive wavelength images and…”
PIVlab – Towards User-friendly, Affordable and Accurate Digital Particle Image Velocimetry in MATLAB (2014, background): “Inhomogeneous lighting can cause low frequency background information which can be removed by applying a high-pass filter that mostly conserves the high frequency information from the particle illumination [11].”
An Exploratory Analysis of Multi-Class Uncertainty Approximation in Bayesian Convolutional Neural Networks (2018, methodology): “In this section we follow [Gonzalez and Woods, 2017] and [Goodfellow et al.”
FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space (2025, neutral): “Traditional image processing pipelines work by directly manipulating pixel values or by applying geometric and photometric transformations under explicit user control [14, 55].”
Methods for Nuclei Detection, Segmentation, and Classification in Digital Histopathology: A Review—Current Status and Future Potential (2014, background): “…into account concavity point detection [28], [51], [57], [60], [61], [68], distance transform [11], [26], [54], marker-controlled watershed [9], [19], [24], [25], [59], adaptive ACM with shape and curvature information [63]–[65], [67], GMM and EM [55], and graphs [51], [58], [61] have…”
A New Deep Learning-Based Food Recognition System for Dietary Assessment on An Edge Computing Service Infrastructure (2018, methodology): “Inspired by this observation, we employ watershed [48] segmentation algorithm to preprocessing the image at FC.”
The Grid Method for In‐plane Displacement and Strain Measurement: A Review and Analysis (2016, background): “A broad literature on image restoration is available in the image processing community (see [174] for the general case or Ref.”
Spectral–Spatial Hyperspectral Image Classification With Edge-Preserving Filtering (2014, methodology): “For example, the statistics-based method [50] assigns the label of a pixel to the most frequent class within its neighborhood pixels.”
High-Speed Tracking with Kernelized Correlation Filters (2014, neutral): “At this point we just found an unexpected formula from classical signal processing—the solution is a regularized correlation filter [9], [21].”