Detection of Defects on Irregular Structured Surfaces by Image Processing Methods for Feature Extraction

In the machining of precision components, a range of defects, including scratches, pits and uneven materials, will inevitably manifest on the surface of the components. Such defects not only result in a reduction in the quality and precision of the parts, but also have an impact on the overall quality, performance, and longevity of the equipment. It is therefore of particular importance to implement effective detection and repair procedures for surface defects in parts. The implementation of efficient detection methods enables the identification and rectification of defects in a prompt and effective manner, thereby ensuring the reliability and long-term stability of the equipment. In this work, we propose a deep neural network-based model that utilises deep convolutional neural networks (DCNNs) to extract features on the surface of parts, and gradually extracts the spatial and textural features of images through multiple convolutional layers and pooling layers. Subsequently, the aforementioned features are fed into the fully connected layer, where complex feature representations are further learned. Finally, the accurate classification of defect types is achieved through multilayer neural networks. The model is thus capable of effectively capturing and identifying different types of surface defects, thereby improving the accuracy and efficiency of identification. The experimental analysis demonstrates that the model exhibits high accuracy and robustness in the identification of different types of defects, thereby verifying its effectiveness and reliability in practical applications.

Additive manufacturing (AM) and machining in a single machine colloquially known as Hybrid manufacturing help to produce customized and complex products without assembling including greater design freedom and reduced material wastage. A CNC-based grinding mechanism is introduced in the same system to overcome those defects and enhance the quality. To increase productivity and improve product surface quality, evolving additive manufacturing demand and finishing subtractive processes must be combined on the same platform. For the additive manufacturing method, Fused Deposition Modeling (FDM) has been employed, and a grinding operation can be performed for surface finishing. A camera module is used to capture surface images for defect detection such as stringing, rashing, and surface cracking after the AM process. Convolutional Neural Network (CNN) is applied to the captured image for the defect detection process. If the CNN analysis reveals any surface defects, a grinding operation will be performed on the surface for better surface quality. The architecture has provided a platform to collect data from the image captured by the camera module for evaluating and identifying surface defects using CNN. CNN model provided 89% accuracy for surface defects detection. As a result, the CNC grinding operation can be done on that particular surface of the product for smoothing the partially roughened surfaces. Therefore, this study demonstrates to improve the surface quality, reduce cycle time, set up time reduction & improve the product's sustainability. The proposed approach of a hybrid manufacturing system also provides a basic framework to increase efficiency, reduce downtime, increase efficiency, improve end part consistencies of the product as a consequence of post-processing & defect detection in the same system, and enable I4.0

Automatic recognition of surface defects for hot-rolled steel strip based on deep attention residual convolutional neural network

Electrolytic capacitor surface defect detection based on deep convolution neural network

Self-mixing interferometry (SMI) is superior to other laser interferometry methods due to its simplicity and compactness. However, SMI signals are often complex and difficult to process due to interference in the form of variations in the effective reflectivity of the target, noisy signals, complex signal shapes, and other dependencies. Deep neural networks have been a very popular area of research in computer artificial intelligence in recent years, allowing more implicit features to be uncovered than traditional shallow machine learning. It has been shown that convolutional and back-propagation neural networks can be used for SMI signal processing. There are also studies that have used machine learning genetic algorithms for absolute distance measurement. Based on the above, this study used convolutional neural networks to form a deep neural network for absolute distance measurement based on SMI technology. We first trained the deep convolutional neural network at different feedback strengths. The results of the Convolutional Neural Network (CNN) model showed a coefficient of determination of 0.9987. which is consistent with the required model. The trained network was then used to estimate absolute distances with and without the addition of noise. The comparison proves that the proposed method is noise-proof and has high adaptability for measurements under different conditions.

Internal defects detection and classification in hollow cylindrical surfaces using single shot detection and MobileNet

With the explosive growth in seismic data acquisition and the successful application of deep convolutional neural networks (DCNN) to various image processing tasks within multidisciplinary fields, many researchers have begun to research DCNN based automatic seismic interpretation techniques. Due to the vast number of parameters considered in deep neural networks, deep learning methods usually require a large amount of data for training. However, collecting a large number of expert interpretations is very time consuming, so related research usually uses synthetic datasets and ignores the practical problems of field datasets. In this paper, we open-source a multi-gigabyte expert-labelled field dataset in response to the challenge of accessing large-scale expert-labelled field datasets. We show that 2D fault recognition within this dataset is an image segmentation or edge detection problem in the computer vision field, that can be expressed as a pixel-level fault/non-fault binary classification. Both types of DCNNs are compared, and we propose a novel fault recognition workflow, which involves processing and screening of seismic images and labels, training DCNNs and automatic numerical evaluation. We have also demonstrated for three case study datasets that effective image augmentation methods can reduce the required labelled crosslines while maintaining satisfactory performance. Our experimental results show that our workflow not only outperforms two state-of-the-art DCNN solutions but also achieves performance comparable to humans on an expert labelled image dataset, even predicting subtle faults that an expert interpreter did not annotate. We suggest that the proposed workflow could reduce the fault interpretation life cycle from months to hours and improve the quality, and define the confidence, of fault interpretation results.

Surface defect detection aims to classify and locate a certain defect that exists in the target surface area. It is an important part of industrial quality inspection. Most of the research on surface defect detection are currently based on convolutional neural networks (CNNs), which are more concerned with local information and lack global perception. Thus, CNNs are unable to effectively extract the defect features. In this paper, a defect detection method based on the Swin transformer is proposed. The structure of the Swin transformer has been fine-tuned so that it has five scales of output, making it more suitable for defect detection tasks with large variations in target size. A bi-directional feature pyramid network is used as the feature fusion part to efficiently fuse to the extracted features. The focal loss is used as a loss function to weight the hard- and easy-to-distinguish samples, potentially making the model fit the surface defect data better. To reduce the number of parameters in the model, a shared detection head was chosen for result prediction. Experiments were conducted on the flange surface defect dataset and the steel surface defect dataset, respectively. Compared with the classical CNNs target detection algorithm, our method improves the mean average precision (mAP) by about 15.4%, while the model volume and detection speed are essentially the same as those of the CNNs-based method. The experimental results show that our proposed method is more competitive compared with CNNs-based methods and has some generality for different types of defects.

Surface defect automatic detection has great significance for copper strip production. The traditional machine vision for surface defect automatic detection of copper strip needs artificial feature design, which has a long cycle, and poor ability of versatility and robustness. However, deep learning can effectively solve these problems. Therefore, based on the deep convolution neural network and the transfer learning strategy, an intelligent recognition model of surface defects of copper strip is established in this paper. Firstly, the defects were classified in accordance with the mechanism and morphology, and the surface defect dataset of copper strip was established by comprehensively adopting image acquisition and image augmentation. Then, a two-class discrimination model was established to achieve the accurate discrimination of perfect and defect images. On this basis, four CNN models were adopted for the recognition of defect images. Among these models, the EfficientNet model through transfer learning strategy had the best comprehensive performance with a recognition accuracy rate of 93.05%. Finally, the interpretability and deficiency of the model were analysed by the class activation map and confusion matrix, which point toward the direction of further optimization for future research.

Optical inspection using unmanned aerial vehicles is a popular trend for detection of surface defects on industrial infrastructure, and full automation is the next step in order to improve potential and reduce costs. Binary classification of the obtained visual image data into defect and defect-free sets is one sub-task of these systems and is still often carried out either completely manually by an expert or by using pre-defined features as classifiers for automatic image post-processing. In contrast, deep convolutional neural networks (CNN) are able to perform both the feature extraction and classification tasks simultaneously by internal hierarchical learning. In this work, custom CNNs and a transfer-learned AlexNet are applied to an experimental data set with artificial defects in order to analyze suitability and required network depth for such surface inspections. Experiments are performed using a set of 2500 camera images total, yielding a classification accuracy of up to 99 % with a single CNN. Thereby, the amount of actual defects that are falsely classified as negative are minimized. Results proof the general effectiveness of the methodology and motivate the application to specific inspection tasks.

In this paper, we propose a new method based on active infrared thermography (IRT) applied to assess the state of 3D-printed structures. The technique utilized here—active IRT—assumes the use of an external energy source to heat the tested material and to create a temperature difference between undamaged and defective areas, and this temperature difference is possible to observe with a thermal imaging camera. In the case of materials with a low value of thermal conductivity, such as the acrylonitrile butadiene styrene (ABS) plastic printout tested in the presented work, the obtained temperature differences are hardly measurable. Hence, the proposed novel IRT method is complemented by a dedicated algorithm for signal analysis and a multi-label classifier based on a deep convolutional neural network (DCNN). For the initial testing of the presented methodology, a 3D printout made in the shape of a cuboid was prepared. One type of defect was tested—surface breaking holes of various depths and diameters that were produced artificially by inclusion in the printout. As a result of examining the sample via the IRT method, a sequence of thermograms was obtained, which enabled the examination of the temporal representation of temperature variation over the examined region of the material. First, the obtained signals were analysed using a new algorithm to enhance the contrast between the background and the defect areas in the 3D print. In the second step, the DCNN was utilised to identify the chosen defect parameters. The experimental results show the high effectiveness of the proposed hybrid signal analysis method to visualise the inner structure of the sample and to determine the defect and size, including the depth and diameter.

Handwritten digit recognition is the intelligence of computers to recognize digits written by humans. But it becomes one of the most challenging tasks for machines as handwritten digits are not perfect and can be made with many different: flavors, size, thickness. Thus, as a solution to this problem, Handwriting digit recognition model comes into picture. Many machine learning techniques have been employed to solve the handwritten digit recognition problem. This paper focuses on Neural Network (NN) approaches. Among the three famous NN approaches: deep neural network (DNN), deep belief network (DBN) and convolutional neural network (CNN), the specialization of CNN as compared to other NN of being able to detect pattern is what makes it so useful for recognizing handwritten digits. Humans can very easily see, read & write any handwritten digits, when written in proper format. Even if the digits are not written in proper format we can use our logic and predict what digit it could be. But It is a hard task for the machine to recognize handwritten digits as these are not perfect and can be made with many different flavors. Thus handwritten digit recognition is the solution to this problem which uses the image of a digit and recognizes the digit present in the image. The handwritten digit recognition is the ability of computers to recognize human handwritten digits. The goal is to build a model that can efficiently and reliably recognize the digits and output the proper result. Amongst all the other neural networks, working and implementing a model using Convolution Neural Network gives out the most precise results. It is most popularly used for analyzing images as well as for other data analysis or classification problems. CNN has hidden layers called convolutional layers. These layers work the same way as other layers do but here we need to specify the no of filters each layer should have These filters are actually what detects the pattern. Patterns could be edges, corners, circles or any complex other objects like eyes, ears or even deeper full dogs, cats, etc. Thus, the specialization of CNN as compared to other NN of being able to detect patterns is what makes it so useful for recognizing handwritten digits Key Word: Neural Networks; Convolutional Neural Networks (CNN); Image Processing; Optical Character Recognition (OCR); MNIST Dataset

Context. The questions of adapting the convolution neural network classifier use in automatic speaker recognition system of critical use(ASRSCU) are considered. The research object is the individual features of the human speech process.Objective. Development of means for separating individual features from the speaker’s speech signal, increasing their informativeness asa result of the factor analysis, their visual representation for the use of the convolution neural network classifier, and optimizing itsarchitecture for the needs of ASRSCU.Method. Measures are proposed to optimize the speaker recognition procedure of the ASRSCU, for which the optimal way of informativefeatures representation and the method of increasing their informativeness are theoretically justified, the topology and measures for increasingof the speaker recognition process efficiency are justified. In particular, it is justified the use of power normalized cepstral coefficients (PNCC)for the description of phonograms recorded in noisy environment conditions. We propose to use Gabor filters to represent information thatwill be analyzed by a convolution neural network, an optimal method of factor analysis (a sparse main components analyzing method) toreduce of the features vector length while preserving its informativeness, an improved topology of the convolution neural network in whichthe Gabor filters are integrated in to the convolution layer, which allows them to optimize their parameters during the neural network trainingprocess, and in a fully connected layer a deep neural network with a bottleneck layer is used, whose weights after training are uses as inputs forthe GMM/HMM control classifier.Results. Methods of representation and optimization of the speaker’s individual features, methods for their visual presentation andimprovement of the topology of a convolution neural network for making speaker recognition on their basis.Conclusions. The obtained theoretical results have found empirical confirmation. In particular, the stability of an improved convolutionneural network to the noisy input phonograms proved to be higher than the results of an ordinary convolution neural network and a deep neuralnetwork. With an SNR increase up to 10 dB, the GMM/HMM classifier is more efficient than the neural network, which can be explained by the efficiency of the used UBM models, but it is much more resource-intensive. Also, the parameters of the Gabor filter bank frames thatprovide the most variable individual features from the speech signal for speaker recognition are determined empirically.

Evaluation of the benchmark datasets for testing the efficacy of deep convolutional neural networks

Deep Convolutional Neural Networks for Large-scale Speech Tasks