Fundamentals of Digital Image Processing

By Anil K. Jain. Control of Color Imaging Systems, 2018

3,176 citations recorded by the source corpus.

Introduction. 1. Two Dimensional Systems and Mathematical Preliminaries. 2. Image Perception. 3. Image Sampling and Quantization. 4. Image Transforms. 5. Image Representation by Stochastic Models. 6. Image Enhancement. 7. Image Filtering and Restoration. 8. Image Analysis and Computer Vision. 9. Image Reconstruction From Projections. 10. Image Data Compression.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1061dea79f8c5e55bf11f7873b9de109c51cbc67

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

A comprehensive survey of recent trends in deep learning for digital images augmentation (2021, background): “Flipping (Vyas et al. 2018) reflects an image around its vertical axis or horizontal axis or both vertical and horizontal axis.”
A Machine Learning Approach to Diagnosing Lung and Colon Cancer Using a Deep Learning-Based Classification Framework (2021, background): “The one that is most commonly used is called the discrete Laplacian operator, which is defined as [40]:”
A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement (2017, methodology): “As another way to avoid saturation, histogram equalization (HE) [33] can improve the contrast effectively and became a widely-used technique.”
PSNR vs SSIM: imperceptibility quality assessment for image steganography (2020, background): “A histogram is a pixel distribution plot that is presented with a graph with a range of pixel values and the frequency of existing pixel values [42].”
What makes for good views for contrastive learning (2020, background): “4), was designed to mimic the way humans perceive color [28].”
Graph Signal Processing: Overview, Challenges, and Applications (2017, methodology): “ype II) is associated with many of the lossy image/video compression standards [181], [182] from JPEG, to MPEG-1 [183] to H.264/AVC [184], [185] and HEVC. Based on [186], see also item 6, page 153 in [187], the energy compaction offered by the DCT was justiﬁed because the DCT asymptotically approxim”
Brief review of image denoising techniques (2019, methodology): “Spatial-frequency domain filtering methods use low pass filtering by designing a frequency domain filter that passes all frequencies lower than and attenuates all frequencies higher than a cut-off frequency [14, 16].”
The Singular Values of Convolutional Layers (2018, methodology): “Lemma 3 (Jain (1989) Section 5.5) Q is unitary.”
Structure-Preserving Color Normalization and Sparse Stain Separation for Histological Images (2016, methodology): “Otherwise, the distribution of various materials and their associated true colors can be quite different between the scenes.”
Watch Your Up-Convolution: CNN Based Generative Deep Neural Networks Are Failing to Reproduce Spectral Distributions (2020, background): “However, it is well known that up-scaling operations notoriously alter the spectral properties of a signal [28], causing high frequency distortions in the output.”
A Comprehensive Review of Image Enhancement Techniques (2010, background): “<= R and 0 <= c <= C (2) It can be seen that every pixel value from the original image is subtracted from the 255. The resultant image becomes negative of the original image. Negative images [3] are useful for enhancing white or grey detail embedded in dark regions of an image. s = 1.0 - r ”
Graph Learning From Data Under Laplacian and Structural Constraints (2016, background): “video signals can be modeled using weighted graphs whose weights capture the correlation or similarity between neighboring pixel values (such as in nearest-neighbor models) [5]–[10].”