Results 21 to 30 of about 733,862 (315)
The use of on-line co-training to reduce the training set size in pattern recognition methods: application to left ventricle segmentation in ultrasound [PDF]
, 2012 The use of statistical pattern recognition models to segment the left ventricle of the heart in ultrasound images has gained substantial attention over the last few years.
Nascimento, J. +3 more
core +1 more source
Sparse self-attention aggregation networks for neural sequence slice interpolation
BioData Mining, 2021 Background Microscopic imaging is a crucial technology for visualizing neural and tissue structures. Large-area defects inevitably occur during the imaging process of electron microscope (EM) serial slices, which lead to reduced registration and semantic
Zejin Wang +4 more
doaj +1 more source
Incremental and Adaptive Learning for Interactive Machine Translation [PDF]
, 2011 [EN] High-quality translation between any pair of languages can be achieved by human post-editing of the outputs of a MT system or by following the Interactive Machine Translation (IMT) approach. In the interactive pattern recognition framework, IMT can
Toselli, Alejandro Héctor +4 more
core +1 more source
Scientific Reports, 2021 In many research areas, scientific progress is accelerated by multidisciplinary access to image data and their interdisciplinary annotation. However, keeping track of these annotations to ensure a high-quality multi-purpose data set is a challenging and ...
Christian Marzahl +9 more
doaj +1 more source
AUCReshaping: improved sensitivity at high-specificity
Scientific Reports, 2023 The evaluation of deep-learning (DL) systems typically relies on the Area under the Receiver-Operating-Curve (AU-ROC) as a performance metric. However, AU-ROC, in its holistic form, does not sufficiently consider performance within specific ranges of ...
Sheethal Bhat +9 more
doaj +1 more source
Aggregating the temporal coherent descriptors in videos using multiple learning kernel for action recognition [PDF]
, 2018 Action recognition methods enable several intelligent machines to recognize human action in their daily life videos. Indeed, many action recognition methods give a noticeable misclassification rate due to the big variations within the videos of the same ...
Abdel-Nasser, Mohamed +7 more
core +1 more source
Scientific Reports, 2021 Biometric identification techniques such as photo-identification require an array of unique natural markings to identify individuals. From 1975 to present, Bigg’s killer whales have been photo-identified along the west coast of North America, resulting ...
Christian Bergler +7 more
doaj +1 more source
Pattern recognition for high performance imaging [PDF]
, 2018 High performance imaging technology generates images with high spectral and spatial resolution, high dynamic range, and/or at high speed. Hyperspectral images contain tens or hundreds of contiguous wavelength indexed bands that are related to material ...
Jun Zhou +5 more
core +1 more source
Keypoint induced distance profiles for visual recognition [PDF]
, 2009 We show that histograms of keypoint descriptor distances can make useful features for visual recognition. Descriptor distances are often exhaustively computed between sets of keypoints, but besides finding the k-smallest distances the structure of the ...
Tat-Jun Chin +5 more
core +1 more source
SSN2V: unsupervised OCT denoising using speckle split
Scientific Reports, 2023 Denoising in optical coherence tomography (OCT) is important to compensate the low signal-to-noise ratio originating from laser speckle. In recent years learning algorithms have been established as the most powerful denoising approach.
Julia Schottenhamml +6 more
doaj +1 more source