Valid Data Augmentation by Patch Alpha Matting

Liu, Hongyun; Rao, Jianghao; Zhou, Lei; Zhang, Jianlin

doi:10.1109/siprocess.2019.8868572

Cited by 3 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some more advanced augmentation techniques are based on the segmentation of objects of interest as foreground and the replacement of their background with specific image content. Examples of this are presented in [9,11,17,19].…”

Section: Mask-based Object Insertionmentioning

confidence: 99%

Deep-learning-based instrument detection for intra-operative robotic assistance

et al. 2022

View full text Add to dashboard Cite

Purpose: Robotic scrub nurses have the potential to become an attractive solution for the operating room. Surgical instrument detection is a fundamental task for these systems, which is the focus of this work. We address the detection of the complete surgery set for wisdom teeth extraction, and propose a data augmentation technique tailored for this task. Methods: Using a robotic scrub nurse system, we create a dataset of 369 unique multi-instrument images with manual annotations. We then propose the Mask-Based Object Insertion method, capable of automatically generating a large amount of synthetic images. By using both real and artificial data, different Mask R-CNN models are trained and evaluated. Results: Our experiments reveal that models trained on the synthetic data created with our method achieve comparable performance to that of models trained on real images. Moreover, we demonstrate that the combination of real and our artificial data can lead to a superior level of generalization. Conclusion: The proposed data augmentation technique is capable of dramatically reducing the labelling work required for training a deep-learning-based detection algorithm. A dataset for the complete instrument set for wisdom teeth extraction is made available for the scientific community, as well as the raw information required for the generation of the synthetic data (https://github.com/Jorebs/Deep-learning-based-instrument-detection-for-intra operative-robotic-assistance).

show abstract

Section: Mask-based Object Insertionmentioning

confidence: 99%

Deep-learning-based instrument detection for intra-operative robotic assistance

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Some scholars tried to enhance and expand data by means of image processing algorithms [14][15][16]. The core idea is to regularize the target images in the original training set to generate new target images, without changing their labels.…”

Section: Introductionmentioning

confidence: 99%

Detection of Dense Small Rigid Targets Based on Convolutional Neural Network and Synthetic Images

Zhang¹,

Chen²

2021

View full text Add to dashboard Cite

Facing the image detection of dense small rigid targets, the main bottleneck of convolutional neural network (CNN)-based algorithms is the lack of massive correctly labeled training images. To make up for the lack, this paper proposes an automatic end-to-end synthesis algorithm to generate a huge amount of labeled training samples. The synthetic image set was adopted to train the network progressively and iteratively, realizing the detection of dense small rigid targets based on the CNN and synthetic images. Specifically, the standard images of the target classes and the typical background mages were imported, and the color, brightness, position, orientation, and perspective of real images were simulated by image processing algorithm, creating a sufficiently large initial training set with correctly labeled images. Then, the network was preliminarily trained on this set. After that, a few real images were compiled into the test set. Taking the missed and incorrectly detected target images as inputs, the initial training set was progressively expanded, and then used to iteratively train the network. The results show that our method can automatically generate a training set that fully substitutes manually labeled dataset for network training, eliminating the dependence on massive manually labeled images. The research opens a new way to implement the tasks similar to the detection of dense small rigid targets, and provides a good reference for solving similar problems through deep learning (DL).

show abstract

“…Enough amount of data used for learning and testing increases the accuracy of the training stage [4][5][6]. Hence, learning-based algorithms may be capable of detecting small details and differences [7][8][9]. Moreover, the qualities and content of the datasets differ according to the aim of the studies.…”

Section: Introductionmentioning

confidence: 99%