A New Image Recognition and Classification Method Combining Transfer Learning Algorithm and MobileNet Model for Welding Defects

Pan, Haihong; Pang, Zaijun; Wang, Yaowei; Wang, Yijue; Chen, Lin

doi:10.1109/access.2020.3005450

Cited by 146 publications

(58 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, the original annotation of public datasets is kept for a fair comparison with peer methods. For images with larger sizes, a sliding window can be used to process the image clip by clip [45]. Our original dataset is also included for testing:…”

Section: ) Datasetsmentioning

confidence: 99%

Hierarchical Convolutional Neural Network With Feature Preservation and Autotuned Thresholding for Crack Detection

et al. 2021

View full text Add to dashboard Cite

Drone imagery is increasingly used in automated inspection for infrastructure surface defects, especially in hazardous or unreachable environments. In machine vision, the key to crack detection rests with robust and accurate algorithms for image processing. To this end, this paper proposes a deep learning approach using hierarchical convolutional neural networks with feature preservation (HCNNFP) and an intercontrast iterative thresholding algorithm for image binarization. First, a set of branch networks is proposed, wherein the output of previous convolutional blocks is half-sizedly concatenated to the current ones to reduce the obscuration in the down-sampling stage taking into account the overall information loss. Next, to extract the feature map generated from the enhanced HCNN, a binary contrast-based autotuned thresholding (CBAT) approach is developed at the post-processing step, where patterns of interest are clustered within the probability map of the identified features. The proposed technique is then applied to identify surface cracks on the surface of roads, bridges or pavements. An extensive comparison with existing techniques is conducted on various datasets and subject to a number of evaluation criteria including the average F-measure (AF β ) introduced here for dynamic quantification of the performance. Experiments on crack images, including those captured by unmanned aerial vehicles inspecting a monorail bridge. The proposed technique outperforms the existing methods on various tested datasets especially for GAPs dataset with an increase of about 1.4% in terms of AF β while the mean percentage error drops by 2.2%. Such performance demonstrates the merits of the proposed HCNNFP architecture for surface defect inspection.INDEX TERMS deep learning, crack detection, hierarchical convolutional neural network, feature preserving, thresholding.

show abstract

Section: ) Datasetsmentioning

confidence: 99%

Hierarchical Convolutional Neural Network With Feature Preservation and Autotuned Thresholding for Crack Detection

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In particular, the MobileNet network was proposed as a lightweight network that requires less parameters and computation, but with better performance than certain deep networks with high complexity. In the MobileNet network, a new convolution method, called depthwise separable convolution, was proposed, which is widely used in image classification [67][68]. In recent years, researchers have made great efforts in remote sensing scene classification.…”

Section: Related Workmentioning

confidence: 99%

Branch Feature Fusion Convolution Network for Remote Sensing Scene Classification

Shi

Wang

2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have outstanding advantages in the classification of remote sensing scenes. Deep CNN models with better classification performance typically have high complexity, while shallow CNN models with low complexity rarely achieve good classification performance for remote sensing images with complex spatial structures. In this paper, we proposed a new lightweight CNN classification method based on branch feature fusion (LCNN-BFF) for remote sensing scene classification. In contrast to a conventional single linear convolution structure, the proposed model had a bilinear feature extraction structure. The branch feature fusion (BFF) method was utilized to fuse the feature information extracted from the two branches, which improved the classification accuracy. In addition, combining depthwise separable convolution (DSC) and conventional convolution (CConv) to extract image features greatly reduced the complexity of the model on the premise of ensuring the accuracy of classification. We tested the method on four standard data sets. The experimental results showed that, compared with recent classification methods, the number of weight parameters of the proposed method only accounted for less than 5% of the other methods; however, the classification accuracy was equivalent to or even superior to certain high-performance classification methods. The python code for the paper can be downloaded from here: https://github.com/scp19801980/Remote-sensing-scene-classificati on.

show abstract

“…Total of 301 brain MRI images were used for the methods. The precision of the suggested methods varies from 94 to 96 percent.Haihong et al [16] suggested a new approach by integrating transfer learning and MobileNet to minimize time consumption and manual work required to evaluate welding defect images. GDXray, a public database was used to validate the method.…”

Section: Literature Reviewmentioning

confidence: 99%

AutismNet: Recognition of Autism Spectrum Disorder from Facial Expressions using MobileNet Architecture

2021

IJATCSE

View full text Add to dashboard Cite

Autism Spectrum Disorder (ASD) is associated with neurodevelopmental disorders that deter the development of social interaction and communication abilities. Diagnosis of autism is one of the challenging tasks for researchers and doctors since the diagnosisis based on abnormalities in brain functions that may not flourish until the disorder is fully established. Facial expression analysis can be an effective solution for thediagnosis of autism in an early stage by exploiting a child’s expressions using automated systems. This research work aims to recognize autism from facial expressions using a deep learning model. The proposed model was implemented using Convolutional Neural Network (CNN) that is developed by the MobileNet model. The technique transfer learning was also implemented in this research work to amplify the performance of the model. The experimental result showed that the MobileNet model with a transfer learning approach couldprovide satisfactory results in the recognition task by achieving thehighest validation accuracy of 89%and test accuracy of 87%. The F1-score and precision value also advocated the reliability of our recognitionof theapproach by achieving the highest score of 87% for both metrics

show abstract

A New Image Recognition and Classification Method Combining Transfer Learning Algorithm and MobileNet Model for Welding Defects

Cited by 146 publications

References 28 publications

Hierarchical Convolutional Neural Network With Feature Preservation and Autotuned Thresholding for Crack Detection

Hierarchical Convolutional Neural Network With Feature Preservation and Autotuned Thresholding for Crack Detection

Branch Feature Fusion Convolution Network for Remote Sensing Scene Classification

AutismNet: Recognition of Autism Spectrum Disorder from Facial Expressions using MobileNet Architecture

Contact Info

Product

Resources

About