Image classification base on PCA of multi-view deep representation

Sun, Yaoqi; Li, Liang; Zheng, Liang; Hu, Jiang; Li, Wenchao; Jiang, Yatong; Yan, Chenggang

doi:10.1016/j.jvcir.2019.05.016

Cited by 35 publications

(17 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Principal component analysis (PCA) [62] was adopted to obtain the coordinate axis of the cattle point cloud and establish a new coordinate system. The processing flow is as follows:…”

Section: Methodsmentioning

confidence: 99%

Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

Huang

Guo

Rao

et al. 2019

Sensors

View full text Add to dashboard Cite

For the time-consuming and stressful body measuring task of Qinchuan cattle and farmers, the demand for the automatic measurement of body dimensions has become more and more urgent. It is necessary to explore automatic measurements with deep learning to improve breeding efficiency and promote the development of industry. In this paper, a novel approach to measuring the body dimensions of live Qinchuan cattle with on transfer learning is proposed. Deep learning of the Kd-network was trained with classical three-dimensional (3D) point cloud datasets (PCD) of the ShapeNet datasets. After a series of processes of PCD sensed by the light detection and ranging (LiDAR) sensor, the cattle silhouettes could be extracted, which after augmentation could be applied as an input layer to the Kd-network. With the output of a convolutional layer of the trained deep model, the output layer of the deep model could be applied to pre-train the full connection network. The TrAdaBoost algorithm was employed to transfer the pre-trained convolutional layer and full connection of the deep model. To classify and recognize the PCD of the cattle silhouette, the average accuracy rate after training with transfer learning could reach up to 93.6%. On the basis of silhouette extraction, the candidate region of the feature surface shape could be extracted with mean curvature and Gaussian curvature. After the computation of the FPFH (fast point feature histogram) of the surface shape, the center of the feature surface could be recognized and the body dimensions of the cattle could finally be calculated. The experimental results showed that the comprehensive error of body dimensions was close to 2%, which could provide a feasible approach to the non-contact observations of the bodies of large physique livestock without any human intervention.

show abstract

“…Principal component analysis (PCA) [62] was adopted to obtain the coordinate axis of the cattle point cloud and establish a new coordinate system. The processing flow is as follows:…”

Section: Methodsmentioning

confidence: 99%

Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

Huang

Guo

Rao

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Therefore, we only compared recent related work based on conventional machine learning methods for END PCA is commonly used to reduce the high-dimensional space of the deep features extracted using DCNNs. It was used extensively in References [39][40][41][42][43][44][45][46] to lower the dimension of deep features used in training SVM classifiers and to also lower the SVM's complexity. SVM classifiers have very effective performance in classification tasks with limited training samples.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning Techniques for Automatic Detection of Embryonic Neurodevelopmental Disorders

2020

View full text Add to dashboard Cite

The increasing rates of neurodevelopmental disorders (NDs) are threatening pregnant women, parents, and clinicians caring for healthy infants and children. NDs can initially start through embryonic development due to several reasons. Up to three in 1000 pregnant women have embryos with brain defects; hence, the primitive detection of embryonic neurodevelopmental disorders (ENDs) is necessary. Related work done for embryonic ND classification is very limited and is based on conventional machine learning (ML) methods for feature extraction and classification processes. Feature extraction of these methods is handcrafted and has several drawbacks. Deep learning methods have the ability to deduce an optimum demonstration from the raw images without image enhancement, segmentation, and feature extraction processes, leading to an effective classification process. This article proposes a new framework based on deep learning methods for the detection of END. To the best of our knowledge, this is the first study that uses deep learning techniques for detecting END. The framework consists of four stages which are transfer learning, deep feature extraction, feature reduction, and classification. The framework depends on feature fusion. The results showed that the proposed framework was capable of identifying END from embryonic MRI images of various gestational ages. To verify the efficiency of the proposed framework, the results were compared with related work that used embryonic images. The performance of the proposed framework was competitive. This means that the proposed framework can be successively used for detecting END.

show abstract

“…In order to formalise the acquired specialist knowledge with the use of video recordings, it is necessary to apply image analysis methods. Previously, such methods dealt with the extraction of data or information from images [10]. The result of this type of analysis is not the image but the data received, such as in the numerical form [11,12].…”

Section: Methods and Techniques For Generating Workplace Proceduresmentioning

confidence: 99%

“…These techniques include Principal Component Analysis (PCA), the Singular Value Decomposition algorithm (SVD), and Linear Discriminant Analysis (LDA). PCA is a method for reducing dimensions and is used to reduce the size of large data sets by converting a set of variables to a smaller set that contains most of the information of the large set [10,[13][14][15]. PCA relies on processing a large amount of information contained in mutually correlated input data into a set of new data, with orthogonally corresponding features.…”

Section: Methods and Techniques For Generating Workplace Proceduresmentioning

confidence: 99%

A Model for Generating Workplace Procedures Using a CNN-SVM Architecture

Patalas‐Maliszewska

Halikowski

2019

Symmetry

View full text Add to dashboard Cite

(1) Background: Improving the management and effectiveness of employees’ learning processes within manufacturing companies has attracted a high level of attention in recent years, especially within the context of Industry 4.0. Convolutional Neural Networks with a Support Vector Machine (CNN-SVM) can be applied in this business field, in order to generate workplace procedures. To overcome the problem of usefully acquiring and sharing specialist knowledge, we use CNN-SVM to examine features from video material concerning each work activity for further comparison with the instruction picture’s features. (2) Methods: This paper uses literature studies and a selected workplace procedure: repairing a solid and using a fuel boiler as the benchmark dataset, which contains 20 s of training and a test video, in order to provide a reference model of features for a workplace procedure. In this model, the method used is also known as Convolutional Neural Networks with Support Vector Machine. This method effectively determines features for the further comparison and detection of objects. (3) Results: The innovative model for generating a workplace procedure, using CNN-SVM architecture, once built, can then be used to provide a learning process to the employees of manufacturing companies. The novelty of the proposed methodology is its architecture, which combines the acquisition of specialist knowledge and formalising and recording it in a useful form for new employees in the company. Moreover, three new algorithms were created: an algorithm to match features, an algorithm to detect each activity in the workplace procedure, and an algorithm to generate an activity scenario. (4) Conclusions: The efficiency of the proposed methodology can be demonstrated on a dataset comprising a collection of workplace procedures, such as the repair of the solid fuel boiler. We also highlighted the impracticality for managers of manufacturing companies to support learning processes in a company, resulting from a lack of resources to teach new employees.

show abstract

Image classification base on PCA of multi-view deep representation

Cited by 35 publications

References 24 publications

Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

Body Dimension Measurements of Qinchuan Cattle with Transfer Learning from LiDAR Sensing

Deep Learning Techniques for Automatic Detection of Embryonic Neurodevelopmental Disorders

A Model for Generating Workplace Procedures Using a CNN-SVM Architecture

Contact Info

Product

Resources

About