Diatom autofocusing in brightfield microscopy: a comparative study

By J. L. Pech-Pacheco, Gabriel Cristóbal, J. Chamorro-Martínez, J. Fernández-Valdivia. Proceedings 15th International Conference on Pattern Recognition. ICPR-2000, 2000

499 citations recorded by the source corpus.

Subfields: Clinical Biochemistry, Media Technology, Ophthalmology

View Paper: https://www.semanticscholar.org/paper/e8abff35432e6e963d9b2ae78a5c177dcd256e04

How researchers see this paper

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

In Media Technology

Citations in the corpus

Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation Dataset (2019, methodology): “Following the same pipeline in [56], we apply the Laplacian edge extraction, calculate the variance among all the output pixels and use a threshold 500 to determine whether this image can be selected.”
Nerfies: Deformable Neural Radiance Fields (2020, methodology): “Blurry Frame Filtering: For video captures, we filter blurry frames using the variance of the Laplacian [42].”
Presentation Attack Detection for Face Recognition Using Light Field Camera (2015, methodology): “In particular, the use of Tenengrad variance [30] focus measure operator has shown the best performance on all three kinds of face artefact samples.”
Whole-Body Human Pose Estimation in the Wild (2020, methodology): “We choose a variation of the Laplacian method [43] to measure it.”
Revisiting Over-Smoothness in Text to Speech (2022, methodology): “To measure the degree of over-smoothness of mel-spectrograms objectively, we calculate the variation of the Laplacian (Pech-Pacheco et al., 2000) (VarL) on the generated mel-spectrograms and compare with that on the ground-truth mel-spectrograms.”
Large-Scale Visual Speech Recognition (2018, methodology): “To construct the validation and test sets we removed blurry videos by thresholding the variance of the Laplacian of each frame (Pech-Pacheco et al., 2000); we kept them in the training set as a form of data augmentation.”
Compressing GANs using Knowledge Distillation (2019, background): “The variance of laplacian of an image gives a measure of the sharpness of the image (Pech-Pacheco et al., 2000).”
Incorporating Side Information by Adaptive Convolution (2017, background): “The features includes the variance of the Laplacian (Pech-Pacheco et al. 2000), saturation (Liu et al. 2008) and 3 features calculated from the radially averaged power spectrum (Liu et al. 2008; Shi et al. 2014).”