Ensemble Convolutional Neural Networks With Knowledge Transfer for Leather Defect Classification in Industrial Settings

Aslam, Masood; Khan, Tariq M.; Holmes, Geoff; Naffa, Rafea

doi:10.1109/access.2020.3034731

Cited by 16 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our literature review, quality inspection use cases are those that do not detect defects or missing parts but the state of an object. For example, determining the state of woven fabrics or leather quality is a use case we considered to be only quality inspection [55,56]. Damage detection, also referred to as defect detection in the literature, summarizes all VI use cases that classify or detect at least one type of damage.…”

Section: Overview Of Visual Inspection Use Casesmentioning

confidence: 99%

Deep Learning for Automated Visual Inspection in Manufacturing and Maintenance: A Survey of Open- Access Papers

Hütten,

Alves Gomes,

Hölken

et al. 2024

ASI

View full text Add to dashboard Cite

Quality assessment in industrial applications is often carried out through visual inspection, usually performed or supported by human domain experts. However, the manual visual inspection of processes and products is error-prone and expensive. It is therefore not surprising that the automation of visual inspection in manufacturing and maintenance is heavily researched and discussed. The use of artificial intelligence as an approach to visual inspection in industrial applications has been considered for decades. Recent successes, driven by advances in deep learning, present a possible paradigm shift and have the potential to facilitate automated visual inspection, even under complex environmental conditions. For this reason, we explore the question of to what extent deep learning is already being used in the field of automated visual inspection and which potential improvements to the state of the art could be realized utilizing concepts from academic research. By conducting an extensive review of the openly accessible literature, we provide an overview of proposed and in-use deep-learning models presented in recent years. Our survey consists of 196 open-access publications, of which 31.7% are manufacturing use cases and 68.3% are maintenance use cases. Furthermore, the survey also shows that the majority of the models currently in use are based on convolutional neural networks, the current de facto standard for image classification, object recognition, or object segmentation tasks. Nevertheless, we see the emergence of vision transformer models that seem to outperform convolutional neural networks but require more resources, which also opens up new research opportunities for the future. Another finding is that in 97% of the publications, the authors use supervised learning techniques to train their models. However, with the median dataset size consisting of 2500 samples, deep-learning models cannot be trained from scratch, so it would be beneficial to use other training paradigms, such as self-supervised learning. In addition, we identified a gap of approximately three years between approaches from deep-learning-based computer vision being published and their introduction in industrial visual inspection applications. Based on our findings, we additionally discuss potential future developments in the area of automated visual inspection.

show abstract

Section: Overview Of Visual Inspection Use Casesmentioning

confidence: 99%

Deep Learning for Automated Visual Inspection in Manufacturing and Maintenance: A Survey of Open- Access Papers

Hütten,

Alves Gomes,

Hölken

et al. 2024

ASI

View full text Add to dashboard Cite

show abstract

“…With the introduction of ML, feature handcrafting is finalized by decisions provided by a learning network, sufficiently trained on a mid-size dataset and performing the classification task or an incomplete defect detection [14]. Manual feature extraction through traditional image processing consists in thresholding, transforming, or modeling images [15]. However, traditional ML performance are hindered by low generalization ability of hand-crafted features because they fit specific operating conditions (e.g., imaging acquisition scheme) and other changing factors in dynamic and timevarying large-scale production [16].…”

Section: ) Systems With Hand-crafted Featuresmentioning

confidence: 99%

“…An improved fine tuning option is released by Hridoy et al [104] that freeze all pre-trained weights except for the last 14 convolutional layers and the fully connected layers. Aslam et al [15] compare three learning fine tuning strategies: on first k layers, or bottom k layers and standard fine tuning of the network. Althubiti et al [105] provide accurate classification of products based on pre-trained CNN with VGG16 as backbone.…”

Section: B: Transfer Learningmentioning

confidence: 99%

“…The two learners get the same input image and contained some differences in the architecture; finally, outputs were averaged to get the final decision. Aslam et al [15] dispose an ensemble of recent CNN architectures combining couples among DenseNet-201, ResNet 50 , Xception and EfficientNet-b3. Su et al [109] proposed an ensemble classifier made by AlexNet and GoogLeNet [69], where the classification output of each one was considered only if a reasonable higher confidence score was predicted for test image, otherwise the sample was evaluated from an experienced human.…”

Section: D: Ensemble Learning Strategymentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for Automatic Vision-Based Recognition of Industrial Surface Defects: A Survey

et al. 2023

View full text Add to dashboard Cite

Automatic vision-based inspection systems have played a key role in product quality assessment for decades through the segmentation, detection, and classification of defects. Historically, machine learning frameworks, based on hand-crafted feature extraction, selection, and validation, counted on a combined approach of parameterized image processing algorithms and explicated human knowledge. The outstanding performance of deep learning (DL) for vision systems, in automatically discovering a feature representation suitable for the corresponding task, has exponentially increased the number of scientific articles and commercial products aiming at industrial quality assessment. In such a context, this article reviews more than 220 relevant articles from the related literature published until February 2023, covering the recent consolidation and advances in the field of fully-automatic DL-based surface defects inspection systems, deployed in various industrial applications. The analyzed papers have been classified according to a bi-dimensional taxonomy, that considers both the specific defect recognition task and the employed learning paradigm. The dependency on large and high-quality labeled datasets and the different neural architectures employed to achieve an overall perception of both well-visible and subtle defects, through the supervision of fine or/and coarse data annotations have been assessed. The results of our analysis highlight a growing research interest in defect representation power enrichment, especially by transferring pre-trained layers to an optimized network and by explaining the network decisions to suggest trustworthy retention or rejection of the products being evaluated.

show abstract

“…Typically, there are three types of tasks for defect inspection with neural networks -classification, detection and segmentation (Tabernik et al, 2020). In the case of defect classification, transfer learning helps to increase the network's ability to detect defective surfaces (Aslam et al, 2020;Wu and Lv, 2021). For segmentation, most methods are based on the U-Net architecture (Ronneberger et al, 2015) taking advantage of convolutional layers that automatically extract features from the images of the surfaces Hao et al, 2021;Huang et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Continual prune-and-select: class-incremental learning with specialized subnetworks

et al. 2023

View full text Add to dashboard Cite

We introduce a new continual (or lifelong) learning algorithm called LDA-CP&S that performs segmentation tasks without undergoing catastrophic forgetting. The method is applied to two different surface defect segmentation problems that are learned incrementally, i.e. providing data about one type of defect at a time, while still being capable of predicting every defect that was seen previously. Our method creates a defect-related subnetwork for each defect type via iterative pruning and trains a classifier based on linear discriminant analysis (LDA). At the inference stage, we first predict the defect type with LDA and then predict the surface defects using the selected subnetwork. We compare our method with other continual learning methods showing a significant improvement -mean Intersection over Union better by a factor of two when compared to existing methods on both datasets. Importantly, our approach shows comparable results with joint training when all the training data (all defects) are seen simultaneously * .

show abstract

Ensemble Convolutional Neural Networks With Knowledge Transfer for Leather Defect Classification in Industrial Settings

Cited by 16 publications

References 37 publications

Deep Learning for Automated Visual Inspection in Manufacturing and Maintenance: A Survey of Open- Access Papers

Deep Learning for Automated Visual Inspection in Manufacturing and Maintenance: A Survey of Open- Access Papers

Deep Learning for Automatic Vision-Based Recognition of Industrial Surface Defects: A Survey

Continual prune-and-select: class-incremental learning with specialized subnetworks

Contact Info

Product

Resources

About