Augmentor: An Image Augmentation Library for Machine Learning

Bloice, Marcus Daniel; Stocker, Christof; Holzinger, Andreas

doi:10.21105/joss.00432

Cited by 208 publications

(84 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It can be done either one time as an oversampling of the dataset or each time during the training process. Effective data augmentation can improve the accuracy of the network (Bloice et al, 2017;DeVries and Taylor, 2017). We used different techniques for augmentation (Figure 4), which were available in OpenCV and NumPy: image rotation (orientations of core and lamination), brightness (as different photography settings) color manipulation (different composition of the rock) and random cropping (core plug extracted).…”

Section: Image Augmentationmentioning

confidence: 99%

Deep convolutions for in-depth automated rock typing

Baraboshkin

Ismailova

Orlov

et al. 2020

Computers & Geosciences

View full text Add to dashboard Cite

The description of rocks is one of the most time-consuming tasks in the everyday work of a geologist, especially when very accurate description is required. We here present a method that reduces the time needed for accurate description of rocks, enabling the geologist to work more efficiently. We describe the application of methods based on color distribution analysis and feature extraction. Then we focus on a new approach, used by us, which is based on convolutional neural networks. We used several well-known neural network architectures (AlexNet, VGG, GoogLeNet, ResNet) and made a comparison of their performance. The precision of the algorithms is up to 95% on the validation set with GoogLeNet architecture. The best of the proposed algorithms can describe 50 m of full-size core in one minute.

show abstract

Section: Image Augmentationmentioning

confidence: 99%

Deep convolutions for in-depth automated rock typing

Baraboshkin

Ismailova

Orlov

et al. 2020

Computers & Geosciences

View full text Add to dashboard Cite

show abstract

“…For training of muscle segmentation U-net, the same optimizer and parameters were set as above. A data augmentation for the segmentation network included horizontal flip, random rotation, shear transform, perspective skewing and random erasing [11] using a publicly available augmentation software Augmenter [12]. The U-net output often contains small island-like noise regions, thus, as a post-processing, we detected connected components and removed the components with a volume less than 5% of the total segmented volume.…”

Section: Training Of U-netmentioning

confidence: 99%

Bayesian Segmentation of Hip and Thigh Muscles in Metal Artifact-Contaminated CT Using Convolutional Neural Network-Enhanced Normalized Metal Artifact Reduction

Sakamoto

Hiasa

Otake

et al. 2020

J Sign Process Syst

View full text Add to dashboard Cite

In total hip arthroplasty, analysis of postoperative medical images is important to evaluate surgical outcome. Since Computed Tomography (CT) is most prevalent modality in orthopedic surgery, we aimed at the analysis of CT image. In this work, we focus on the metal artifact in postoperative CT caused by the metallic implant, which reduces the accuracy of segmentation especially in the vicinity of the implant. Our goal was to develop an automated segmentation method of the bones and muscles in the postoperative CT images. We propose a method that combines Normalized Metal Artifact Reduction (NMAR), which is one of the state-of-the-art metal artifact reduction methods, and a Convolutional Neural Network-based segmentation using two U-net architectures. The first U-net refines the result of NMAR and the muscle segmentation is performed by the second U-net. We conducted experiments using simulated images of 20 patients and real images of three patients to evaluate the segmentation accuracy of 19 muscles. In simulation study, the proposed method showed statistically significant improvement (p<0.05) in the average symmetric surface distance (ASD) metric for 14 muscles out of 19 muscles and the average ASD of all muscles from 1.17 ± 0.543 mm (mean ± std over all patients) to 1.10 ± 0.509 mm over our previous method. The real image study using the manual trace of gluteus maximus and medius muscles showed ASD of 1.32 ± 0.25 mm. Our future work includes training of a network in an end-to-end manner for both the metal artifact reduction and muscle segmentation.

show abstract

“…During training data generation, patch size is fixed to 9x9, and ψ value is randomly selected from interval [4,11]. Reference patch with positive and negative pairs are augmented [5] in spatial and spectral domains which includes random cropping, flipping, transformation, and contrast variation. This dataset along with the data generation framework is available for public use 2 and further details of the dataset are given in supplementary material.…”

Section: Synthetic People Stereo Patch Datasetmentioning

confidence: 99%

“…Methods have tried to address this problem in the literature for different applications such as semantic segmentation [31], stereo reconstruction and optical flow estimation [20] and scene understanding [30]. These methods increase the variation in dataset by augmentation of training data with random spatial operations [5] or by creating realistic data. We have exploited these ideas by using realistic textures and applying augmentation to generated patches (Section 3.2).…”

Section: Introductionmentioning

confidence: 99%

Learning Dense Wide Baseline Stereo Matching for People

Caliskan

Mustafa

Imre

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

Existing methods for stereo work on narrow baseline image pairs giving limited performance between wide baseline views. This paper proposes a framework to learn and estimate dense stereo for people from wide baseline image pairs. A synthetic people stereo patch dataset (S2P2) is introduced to learn wide baseline dense stereo matching for people. The proposed framework not only learns human specific features from synthetic data but also exploits pooling layer and data augmentation to adapt to real data. The network learns from the human specific stereo patches from the proposed dataset for wide-baseline stereo estimation. In addition to patch match learning, a stereo constraint is introduced in the framework to solve wide baseline stereo reconstruction of humans. Quantitative and qualitative performance evaluation against state-of-the-art methods of proposed method demonstrates improved wide baseline stereo reconstruction on challenging datasets. We show that it is possible to learn stereo matching from synthetic people dataset and improve performance on real datasets for stereo reconstruction of people from narrow and wide baseline stereo data.

show abstract

Augmentor: An Image Augmentation Library for Machine Learning

Cited by 208 publications

References 6 publications

Deep convolutions for in-depth automated rock typing

Deep convolutions for in-depth automated rock typing

Bayesian Segmentation of Hip and Thigh Muscles in Metal Artifact-Contaminated CT Using Convolutional Neural Network-Enhanced Normalized Metal Artifact Reduction

Learning Dense Wide Baseline Stereo Matching for People

Contact Info

Product

Resources

About