Noise Immunity and Robustness Study of Image Recognition Using a Convolutional Neural Network

Ziyadinov, Vadim; Терешонок, М. В.

doi:10.3390/s22031241

Cited by 14 publications

(8 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is possible that the feature vector is not mapped correctly to the expected position of the landmark. The relatively low inference accuracy of a deep neural network (trained with noisy data) on a noiseless or less noisy testing dataset has also been reported in other studies ( 40 – 42 ). More experiments are needed to analyze BoneNet's performance on noiseless data and data with different noise levels in both training and testing dataset.…”

Section: Experiments and Resultssupporting

confidence: 69%

See 1 more Smart Citation

Automatic landmark detection and mapping for 2D/3D registration with BoneNet

Nguyen

Pereira²,

Liang³

et al. 2022

Front. Vet. Sci.

View full text Add to dashboard Cite

The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) or an expensive computation (tomographic reconstruction-based), the manual annotation method depends on the experience of operators. In this paper, we tackle these challenges by a strategic approach that consists of two building blocks: an automated 3D landmark extraction technique and a deep neural network for 2D landmarks detection. For 3D landmark extraction, we propose a technique based on the shortest voxel coordinate variance to extract the 3D landmarks from the 3D tomographic reconstruction of an object. For 2D landmark detection, we propose a customized ResNet18-based neural network, BoneNet, to automatically detect geometrical landmarks on X-ray fluoroscopy images. With a deeper network architecture in comparison to the original ResNet18 model, BoneNet can extract and propagate feature vectors for accurate 2D landmark inference. The 3D poses of the animal are then reconstructed by aligning the extracted 2D landmarks from X-ray radiographs and the corresponding 3D landmarks in a 3D object reference model. Our proposed method is validated on X-ray images, simulated from a real piglet hindlimb 3D computed tomography scan and does not require manual annotation of landmark positions. The simulation results show that BoneNet is able to accurately detect the 2D landmarks in simulated, noisy 2D X-ray images, resulting in promising rigid and articulated parameter estimations.

show abstract

Section: Experiments and Resultssupporting

confidence: 69%

“…noisy testing dataset has also been reported in other studies (40)(41)(42). More experiments are needed to analyze BoneNet's performance on noiseless data and data with different noise levels in both training and testing dataset.…”

Section: D Landmarks Detectionsupporting

confidence: 57%

Automatic landmark detection and mapping for 2D/3D registration with BoneNet

Nguyen

Pereira²,

Liang³

et al. 2022

Front. Vet. Sci.

View full text Add to dashboard Cite

show abstract

“…is clustering requires the collection of similar features, and the Gaussian distribution coefficients gathered into a class of clustering form a fuzzy clustering. e fuzzy clustering should be calculated by combining the hierarchical and K-means algorithm as the clustering method, and the parameter setting is adjustable; it is convenient to control the number of iterative calculations [19]. In the algorithm, K-means clustering method calculates the training samples as K clusters and then assigns other samples to similar clusters.…”

Section: Fuzzy Cluster Analysis Of Digital Display Of Folk Arts Andmentioning

confidence: 99%

Research on Folk Handicraft Image Recognition Based on Neural Networks and Visual Saliency

Dai

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

How to identify quickly the images of folk arts and crafts works has become a difficult problem of cultural heritage value mining. Therefore, combined with the image recognition technology can improve the accuracy of the identification of folk arts and crafts works. This paper improves the ITTI significant model based on the method of linear addition of significant maps with the same proportion. Firstly, Bayesian model and Gaussian model are used to extract the probability distribution of image feature vector; secondly, the k-means algorithm is used to identify image accuracy extraction work, and finally ALOI database is used to test judgment image recognition accuracy; experimental results found that the improved technology does help to improve the folk arts and handicraft image recognition accuracy.

show abstract

“…Convolutional neural networks (CNNs) have been widely used in the computer vision field due to their advantages in conventional kernel and nonlinear fitting. CNNs can be used for classification [14], segmentation [15], and image recognition [16] by stacking the conventional layer, pooling layer, and activation function in different structures. CNNs offer advantages in dealing with 2D image data, which is similar to the computational process of DIC, and CNNs are known to be the most suitable networks to realize DIC algorithms.…”

Section: Introductionmentioning

confidence: 99%

Experimental and simulation investigation of stereo-DIC via a deep learning algorithm based on initial speckle positioning technology

Dai,

Wei,

Gao

et al. 2024

Appl. Opt.

View full text Add to dashboard Cite

For the deep-learning-based stereo-digital image correlation technique, the initial speckle position is crucial as it influences the accuracy of the generated dataset and deformation fields. To ensure measurement accuracy, an optimized extrinsic parameter estimation algorithm is proposed in this study to determine the rotation and translation matrix of the plane in which the speckle is located between the world coordinate system and the left camera coordinate system. First, the accuracy of different extrinsic parameter estimation algorithms was studied by simulations. Subsequently, the dataset of stereo speckle images was generated using the optimized extrinsic parameters. Finally, the improved dual-branch CNN deconvolution architecture was proposed to output displacements and strains simultaneously. Simulation results indicate that DAS-Net exhibits enhanced expressive capabilities, as evidenced by a reduction in displacement errors compared to previous research. The experimental results reveal that the mean absolute percentage error between the stereo-DIC results and the generated dataset is less than 2%, suggesting that the initial speckle positioning technology effectively minimizes the discrepancy between the images in the dataset and those obtained experimentally. Furthermore, the DAS-Net algorithm accurately measures the displacement and strain fields as well as their morphological characteristics.

show abstract

Noise Immunity and Robustness Study of Image Recognition Using a Convolutional Neural Network

Cited by 14 publications

References 29 publications

Automatic landmark detection and mapping for 2D/3D registration with BoneNet

Automatic landmark detection and mapping for 2D/3D registration with BoneNet

Research on Folk Handicraft Image Recognition Based on Neural Networks and Visual Saliency

Experimental and simulation investigation of stereo-DIC via a deep learning algorithm based on initial speckle positioning technology

Contact Info

Product

Resources

About