Detection of defective pharmaceutical capsules and its types of defect using image processing techniques

Sanitary ceramic products, such as toilet and wash basin, are widely used in our daily life. Sanitary ceramics are expected to have some excellent physical properties, such as corrosion resistance, easy cleaning, and low water absorption. However, surface defects in sanitary ceramics are inevitable due to complex production processes and changing production environment. Therefore, surface defect detection must be performed in the manufacturing process of sanitary ceramics. There are many types of surface defects in sanitary ceramics, and different types of defects have large differences in characteristics and scales. Traditional detection methods with artificially designed features and classifiers are difficult to apply in this context. In addition, there are few studies on surface defect detection methods of sanitary ceramics based on deep neural networks. In this article, a lightweight real-time defect detection network based on the lightweight backbone MobileNetV3 is presented. The proposed network achieves multi-scale detection of surface defects in sanitary ceramics with a multi-layer feature pyramid. Combining region proposal network and anchor-free method, real-time defect detection is achieved. Finally, a detection head with channel attention structure and a low-level mixed feature classification strategy is used to perform defect classification with higher accuracy. Experimental results show that the proposed approach achieves at least 22.9% detection speed improvement and 35.0% average precision improvement while reducing memory consumption by at least 8.4% compared with the classic one-stage SSD, YOLO V3 and two-stage Faster R-CNN methods.

Eddy current testing is a nondestructive testing method, which is used to detect discontinuities and defects in conductive materials. Using this technique, two different types of artificial defects in a railhead were evaluated in order to analyze the relationship between different types of defects and eddy current signals, and to obtain data on the size of the rail surface defects and crack location. The actually used rail sample was also studied. Surface cracks and defects were clearly observed as amplitude and phase changes of detected signals. This study succeeds in quantitatively analyzing and discriminating the damage types.

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.

Defect classification is an important part of automated surface defect detection systems. Generally, the types of surface defects of industrial products are complex and diverse, and the correct defect type classification can help to subsequently extract the characteristic of defects. Moreover, defect classification can help to count the number of defect modes automatically and provide data support for the precise maintenance of product production. Due to the large number of surface defects and the small difference between defect types, traditional classification methods are difficult to classify defect accurately. Therefore, in order to improve the accuracy of defect image classification, this paper proposes a defect image classification method based on transfer learning and sparse coding. Firstly, a deep CNN feature extraction algorithm for defect images is proposed in combination with transfer learning. Then, the deep CNN features of the defect image are dimension-reduced and sparsely optimized using the sparse coding techniques, and the sparse CNN features are obtained. Finally, the sparse CNN features are classified to realize the defect type determination using the linear SVM. The accuracy of the proposed method is verified by using a steel surface defect image benchmark database, and the effectiveness of the proposed method is proved.

Micro-structural defects influence the performance of MEMS devices. For effective quality monitoring and assurance in mass-production of MEMS devices, it is necessary to conduct automatic defect inspection. In this paper, an approach based on image processing for automatic microstructure defect inspection is presented. In the approach, an Influence Region Template is built based on a reference microstructure image while it preserves the framework and restrains the tiny distortion of the reference, then the test microstructure image is compared with the Influencing Region Template for quality evaluation. By the approach, typical defects such as blocks in trenches or channels, transfixions between trenches or channels and missing of some part and so on, are detected and classified automatically, while some distortions which do not affect the function of the microstructures are ignored. Testing results show that the approach can conduct a high quality assurance while it can endure a given distortion tolerance of microstructures.

Efficient automated print defect mapping is valuable to the printing industry since such defects directly influence customer-perceived printer quality and manually mapping them is cost-ineffective. Conventional methods consist of complicated and hand-crafted feature engineering techniques, usually targeting only one type of defect. In this paper, we propose the first end-to-end framework to map print defects at pixel level, adopting an approach based on semantic segmentation. Our framework uses Convolutional Neural Networks, specifically DeepLab-v3+, and achieves promising results in the identification of defects in printed images. We use synthetic training data by simulating two types of print defects and a print-scan effect with image processing and computer graphic techniques. Compared with conventional methods, our framework is versatile, allowing two inference strategies, one being near real-time and providing coarser results, and the other focusing on offline processing with more fine-grained detection. Our model is evaluated on a dataset of real printed images.

It is necessary in factories to assess the severity of the surface defects of castings, as a slight surface defect will be taken as qualified when it brings no bad effect or it can be removed by the subsequent processing. In practical production, professional technicians visually inspect the surface defect severity according to their individual experience. Therefore, it is difficult for them to maintain the same standard and accuracy in the subjective, tedious and labor-intensive work. Recently, image processing techniques based on optical images have been applied to achieve better accuracy and high efficiency. Unfortunately, optical images cannot directly quantify surface depth, which works as a crucial factor in the practical assessment of surface defect severity. The surface roughness evaluation algorithm, which takes into account of both area and depth information of the assessed surface, was applied to directly characterize surface defect severity based on surface asperity rather than optical image. The results using standard casting pieces show that surface defect severity has no apparent dependence on surface roughness. However, the subsequent results show that the root-mean-squared-deviation (RMSD) of surface gradient of flow line defects positively correlates with the increase of defect severity. The other types of defect do not present such tendency. Thus, practical workpieces with flow line defects on the surface were used to verify the universality of this tendency. The results show that surface roughness of an unqualified workpiece is larger than that of a qualified workpiece after surface slope adjustment, but presents no obvious coincidence before the adjustment. In contrast, the RMSD of an unqualified workpiece, no matter before or after the adjustment, is larger than that of a qualified one.

LP is one of the pharmaceutical companies located in Serang, Banten. The production of the company is tablets, capsules, and syrup. Problems that occur at PT. LP is a product defect that occurs in capsule filling, especially in capsule A. The purpose of this study is to determine the defective products that occur in capsule A and to find out the proposed improvements that will be made to reduce product defects in capsule A. The research methods used are Statistical Process Control (SPC) and Fuzzy Failure Mode and Effect Analysis (F-FMEA). The population and samples used were defective capsule A during the production process from March 2022 to May 2023, with sampling techniques through production data, observation and interviews. And the results of research using a check sheet show that the percentage of defects reaches 6%, based on the pareto chart, the priority of improvement that needs to be done is for the dominant type of defect, namely the dented capsule reject reaches 90%, and on the control chart there are still control points that are outside the UCL and LCL. FMEA calculations, the RPN value of the capsule is dented on the head of the capsule or capsule body reaches 384, and the FRPN value is 6.76.

Precise adherence to the manufacturer’s instructions and requirements plays an important role in various installation processes. The presented paper deals with the evaluation of the effect of manufacturing imperfections and surface defects on the failure behaviour of flexible adhesive intended for façade application. The failure to comply with the accepted procedures is more common in construction practice than in other sectors of the industry, mostly due to the surrounding conditions and lack of trained supervision. Unfortunately, this may lead to premature failure of adhesively bonded joints and a considerable shortening of the service life of the entire construction. To determine the potential of the risk, five types of artificially applied (a) manufacturing imperfections: (1) application on wet adhesion promoter, (2) application after the expiry of the laying-time, (3) curing of samples at +1℃ (b) surface defects: (4) application on a wet substrate and (5) application on a dirty surface, were suggested. Moreover, the Taguchi L32 orthogonal array design was used to arrange the test setup of all possible combinations. The 1 K polyurethane adhesive was applied in tensile butt joints and single-lap shear joints composed of aluminium alloy and thermally modified wood substrates. The obtained results confirmed that non-observance of the required manufacturing techniques and recommended procedures can have a negative impact on the decrease of the adhesively bonded joint strength and deformation behaviour. Surprisingly, the most critical was not the combination of all suggested types of imperfections and defects. The performed one-way ANOVA revealed that the most perilous was the combination of types 2 and 4 in the tensile test with 77% joint strength reduction. In the shear test, the most critical was the combination of all types of imperfection and defects which led also to a 77% drop of shear strength.

Application of Shearlet transform to classification of surface defects for metals

The quality of smooth technical surfaces is characterized by the surface roughness and by surface defects. For a stable quality control, objective measuring conditions are necessary. The objective measurement of surface defects especially is an unsolved problem. For the investigation of the scattering characteristics of different surface defects, a measuring device was developed. With this measuring device, the type of defect and the angle dependent scattering intensity were measured and compared with theoretical calculations.

In the actual industrial production environment, the surface defects of products are subtle, and the number of different types of defect data samples is also quite small. Most deep learning models rely on a large number of training samples and parameters to achieve high-precision defect detection. At the same time, the edge computing layer in the actual industrial environment may also encounter transmission delays and insufficient resources. Training a proper model for a specific type of surface defect while simultaneously satisfying the real-time accuracy of defect detection is still a challenging task. To effectively deal with the above challenges, we propose an edge-cloud computing defect detection model based on the intrinsic mean feature detector in the Lie Group space. The modules in the model adopt a symmetrical structure, which can extract related features more effectively. Different from existing models, this model utilizes the Lie Group space intrinsic mean feature as a metric to characterize the essential attributes of different types of surface defects. In addition, we propose an intrinsic mean attention mechanism in the Lie Group manifold space that is easy to implement at the edge service layer without increasing the number of model parameters, thereby enhancing the detection performance of tiny surface defects. Extensive experiments on three publicly available and challenging datasets reveal the superiority of our model in terms of detection accuracy, real-time detection, number of parameters, and computational performance. In addition, our proposed model also shows competitiveness and advantages compared with state-of-the-art models.

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.

Mechanical parts often have surface defects such as scratches, cracks and pits during the production process, which seriously affect product quality and service life. To address this challenge, this paper proposes a method for detecting and quantifying surface defects of mechanical parts based on image processing. First, this paper uses high-resolution image acquisition technology to obtain surface images of mechanical parts, and improves image quality through preprocessing steps. Then, this paper uses edge detection, morphological operations, and image segmentation algorithms to extract the features of surface defects, thereby realizing automatic identification of defective areas. Finally, this paper combines the Faster R-CNN (Faster Region-Based Convolutional Neural Network) algorithm to further refine the classification and quantification of defects and obtain the specific location, size and type of defects. Experimental results show that among the 500 mechanical parts samples tested, the proposed method has a mean average precision (mAP) of 0.93 in surface defect detection. Compared with other image processing methods, this method has significantly improved defect detection accuracy and speed. Especially when processing higher-resolution images, the Faster R-CNN model can achieve efficient defect classification and quantification to meet the needs of real-time detection in industrial production.

To improve the accuracy and validity of ultrasonic detection for insulation pull rod, a suitable ultrasonic focusing probe and the corresponding analysis system are developed in this paper, considering the material property, structure characteristic and the features of typical internal defects. In addition, a series of samples containing typical defects were tested to acquire the time-domain and frequency-domain characteristics, based on which an effective method that use the echo amplitude of defect and the second peak of spectrum to identify the defects is proposed. Experimental results show that in case of void defects, the time interval between surface echo and defect echo increases with the increase of defect depth. On the contrary, the second peak of spectrum has negative correlation with the depth and size of the void defects. When insulation pull rob is subjected to strong stress, the insulation pull rob appears layered and degummed, which result in the echo of time-domain and frequency-domain was distorted a lot. In conclusion, the combination of the time-domain and frequency-domain characteristics can successfully diagnosis defects in insulation pull rod.