Digital image processing

By P. Hawkes. 1980

How researchers see this paper

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

In Speech & Audio

Citations in the corpus

Making Convolutional Networks Shift-Invariant Again (2019, methodology): “When downsampling a signal, such an image, the textbook solution is to anti-alias by low-pass ﬁltering the signal (Op-penheim et al., 1999; Gonzalez & Woods, 1992).”
Propagation kernels: efficient graph kernels from propagated information (2014, methodology): “We perform a leave-one-out ( ) cross validation on the 41 objects in db, where the kernel parameter t is learned on each training set again via .”
Generic object recognition with boosting (2006, methodology): “For illumination normalization, we use homomorphic filtering (see e.g., [14], chapter 4.5).”
Leaf segmentation in plant phenotyping: a collation study (2015, methodology): “We adopt two metrics, based respectively on the Modified Hausdorff Distance (MHD) [19] and Pratt’s Figure of Merit (FoM) [45], to compare point sets A and B denoting leaf object boundaries.”
Image-Guided Robotic Flexible Needle Steering (2007, background): “It is quite robust to noise and can be normalized to allow pattern matching independently of scale and offset in the images [18].”
Fire detection using statistical color model in video sequences (2007, methodology): “There are lots of color-transformation algorithms that transform RGB color space to other color spaces [9], which can be used to separate the luminance from the chrominance.”
The FFT on a GPU (2003, unknown): “ 0 u ∈ {0, M 2 }, v ∈ {0, N 2 } −A[u][N−v] u ∈ {0, M 2 }, 0 < v < N 2 A[u][v] u ∈ {0, M 2 }, N 2 < v < N −A[M−u][v] 0 < u < M 2 , v ∈ {0, N 2 } −A[M−u][N−v] 0 < u < M 2 , 0 < v < N 2 −A[M−u][N−v] 0 < u < M 2 , N 2 < v < N A[u][v] M 2 < u < M (10)”
A guided tour into subcellular colocalization analysis in light microscopy (2006, background): “The cross-correlation function calculation allows an estimation of the dimensions of the particles, as the width of the bell-shaped curve at half maximum reflects the approximate particle size convolved by the PSF of the optical system.”
A neural network classifier capable of recognizing the patterns of all major subcellular structures in fluorescence microscope images of HeLa cells (2001, methodology): “The Matlab imfeature function was used to calculate the Euler number, the number of objects in the image minus the number of holes (Gonzalez and Woods, 1992, p. 505).”
Dynamic Bayesian Networks for Audio-Visual Speech Recognition (2002, methodology): “The contour of the lips (Figure 4c) is obtained through the binary chain encoding method [20] followed by a smoothing operation.”
MRI-Based Attenuation Correction for PET/MRI: A Novel Approach Combining Pattern Recognition and Atlas Registration (2008, background): “Satisfying results can indeed be achieved with standard segmentation techniques from digital image processing (6,7).”
A fusion-based enhancing method for weakly illuminated images (2016, methodology): “Some conventional histogram-based methods, such as histogram equalization (HE) [5] and contrast-limited adaptive histogram equalization (CLAHE) [6], are widely used because of their simplicity and effectiveness in enhancing low contrast images, but can lead to contrast over-enhancement and noise amp”
Sourcebook of parallel computing (2003, background): “There are also numerous excellent books focused on image processing [389, 508, 776], and multidimensional signal processing [296, 614].”
Hierarchical Saliency Detection (2013, methodology): “3 (b) by the watershedlike method [9] .”