Research on Intelligent Data Analysis and Processing Algorithms for Quality Inspection

In modern industrial production, quality inspection and control play a crucial role in enhancing production efficiency and ensuring product reliability. Traditional inspection methods primarily rely on manual labor, which not only results in low efficiency but also introduces human error, leading to unstable inspection outcomes. With the advancement of science and technology, automated image processing technology has emerged, revolutionizing industrial testing. By leveraging computer vision and image analysis algorithms, automated image processing technology can rapidly and accurately identify and analyze defects and anomalies in images, significantly improving inspection efficiency and accuracy. This technology not only enables real-time monitoring of product quality on production lines but also provides data support for process optimization, driving industrial production toward intelligent and automated development.

Synthetic data has emerged as a vital tool in computer vision research, yet procedural generation using 3D computer graphics remains underexplored compared to generative adversarial networks (GANs). Our method offers greater control over generated images, making it particularly valuable for domains like industrial quality inspection, where real data is often sparse. We present a method for generating physically based rendered images of an injection-molded cup, simulating two common defects - short shot and color streak. The approach automates defect generation with variable size and severity, along with pixel-perfect segmentation masks, significantly reducing labeling effort. Synthetic data was combined with a small set of real images to train semantic segmentation models and explore domain expansion, such as inspecting parts in novel colors not represented in real-world datasets. Experiments demonstrate that the method enhances defect detection and is especially effective for domain expansion tasks, such as inspecting parts in new colors. However, challenges persist in segmenting smaller defects, underscoring the need for balanced synthetic datasets and probably also for customized loss functions.

The non-invasive evaluation of the heart through EectroCardioGraphy (ECG) has played a key role in detecting heart disease. The analysis of ECG signals requires years of learning and experience to interpret and extract useful information from them. Thus, a computerized system is needed to classify ECG signals with more accurate results effectively. Abnormal heart rhythms are called arrhythmias and cause sudden cardiac deaths. In this work, a Computerized Abnormal Heart Rhythms Detection (CAHRD) system is developed using ECG signals. It consists of four stages; preprocessing, feature extraction, feature optimization and classifier. At first, Pan and Tompkins algorithm is employed to detect the envelope of Q, R and S waves in the preprocessing stage. It uses a recursive filter to eliminate muscle noise, <i>T</i>-wave interference and baseline wander. As the analysis of ECG signal in the spatial domain does not provide a complete description of the signal, the feature extraction involves using frequency contents obtained from multiple wavelet filters; bi-orthogonal, Symlet and Daubechies at different resolution levels in the feature extraction stage. Then, Black Widow Optimization (BWO) is applied to optimize the hybrid wavelet features in the feature optimization stage. Finally, a kernel based Support Vector Machine (SVM) is employed to classify heartbeats into five classes. In SVM, Radial Basis Function (RBF), polynomial and linear kernels are used. A total of ∼15000 ECG signals are obtained from the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database for performance evaluation of the proposed CAHRD system. Results show that the proposed CAHRD system proved to be a powerful tool for ECG analysis. It correctly classifies five classes of heartbeats with 99.91% accuracy using an RBF kernel with 2^nd level wavelet coefficients. The CAHRD system achieves an improvement of ∼6% over random projections with the ensemble SVM approach and ∼2% over morphological and ECG segment based features with the RBF classifier.

In practical industrial inspection scenarios, the challenges of limited samples and severe domain shift render achieving reliable few-shot image classification a pressing challenge. In response to this, we propose a lightweight small-sample industrial quality inspection image classification and confidence calibration framework based on Fast AutoAugment. The framework employs EfficientNetV2 as the basic feature extractor, using an advanced policy search mechanism enabled by Fast AutoAugment, which successfully enhances the model’s generalization ability to defect features. In relation to feature fusion, we design a multi-branch feature fusion module that combines spatial attention, channel recalibration and contrast alignment mechanisms to further promote discriminant expression in small sample conditions. Additionally, we design an uncertainty calibration module based on Dirichlet distribution, which integrates task-adaptive priors and temperature scaling strategies to effectively calibrate the model’s confidence and reduce the risk of "overconfidence errors" in industrial settings. Experiments on the NEU-CLS industrial quality inspection dataset show that the proposed method outperforms the existing Few-shot baseline, demonstrating a classification accuracy that is 4.6%-7.1% higher than that of the existing few-shot baselines.

Industry 4.0 is revolutionizing the world of manufacturing by merging modern digital technologies with conventional production techniques. One of the most crucial advancements is the use of robotics and automated systems for quality checking, which improves accuracy, consistency, and real-time sensitivity. In this paper, deep robotics-based quality control systems are presented with an in-depth analysis focusing on the incorporation of artificial intelligence (AI), machine vision, and sensor networks. The transformation towards Industry 4.0 has heightened the demand for smart and automated quality inspection systems that can work with speed, accuracy, and flexibility. Traditional inspection methods tend to fail in meeting the increasing complexity and amount of contemporary manufacturing processes. Robotics and automation, enabled by machine learning, computer vision, and sensor fusion, offer a revolutionary solution to such issues. This paper contribution acknowledges the manner in which these technologies are transforming industrial quality assurance in the context of Industry 4.0.

Measuring the roundness of a circular workpiece is a crucial issue of quality control and inspection in industry. In this area, maximum inscribed circle (MIC) and Maximum circumscribing circle (MCC), Minimum zone circle (MZC) and Least Square Circle (LSC) are four commonly used methods. In particular, MIC, MCC, and MZC, which are non-linear constrained optimization problems, have not been thoroughly discussed lately. This study proposes a roundness measuring method that applies the Particle Swarm Optimization Algorithm (PSO) to compute MIC, MCC and MZC. To facilitate the PSO process, five different PSO methods are encoded using a radius (R) and circle center (x, y) and extensively evaluated using an experimental design, in which the impact of inertia weight, maximum velocity and the number of particles on the performance of the particle swarm optimizer is analyzed. The proposed method is verified with a set of testing images and benchmarked with the GA-based (Genetic Algorithm) method (Chen, 2000). The experimental results reveal that the PSO-based method effectively solved the MIC, MCC, and MZC problems and outperforms GA-based method in both accuracy and the efficiency. As a result, several industrial applications are presented to explore the effectiveness and efficiency of the proposed method.

Cucumber is a vegetable that is widely consumed by Indonesian people. However, cucumber plants are susceptible to disease attack which causes substantial yield loss. Examples of disease in cucumber plants are downy mildew, powdery mildew, and cucumber mozaic virus. This disease can be recognized visually because it has a characteristic color and texture. Through an image, information can be learned about the cucumber plant disease. This study aims to build a disease classification system on cucumber leaf images so that it can provide information on the type of disease. The application of the system consisting of pre-processing, feature extraction, classification, and evaluation stages. The pre-processing stages resizes the RGB image and then converts it to Grayscale. The feature extraction stage uses the GLCM (Gray Level Co-Occurence) method. The classification stage uses the K-NN (K-Nearest Neighbor) algorithm. Evaluation stage is a confusion matrix. The results of the cucumber leaf disease classification test used the K-Nearest Neighbor algorithm, produced the best accuracy value by using the neighborhood value k=1 reaching 90%.

An experimental investigation was conducted to explore the feasibility of replacing the current inspection method by a portable coordinate measuring machine (CMM) for daily quality inspection in automotive industry. The experiment focusses on inspecting stamped body parts due to the significant number of inspection points that could be time consuming for inspection activities. Two inspection methods were performed, i.e. the application of checking fixture (CF) which is the current method and the second method was using a portable CMM. Both inspections were performed onto the same loose freeform surface of an outer door panel. Factors related to inspection duration, economical and data reliability were all compared to understand the practicality of replacing the current inspection method with a portable CMM. It was found that a portable CMM provide a significant shorter inspection duration, more economical and better data reliability but at the same time is unable to match the performance of conventional inspection onto freeform surface. The conclusion was made that a portable CMM alone is not sufficient to replace the current inspection method thus require further study.

The Aim of the proposed paper is to recognize offline Hand written Telugu characters using Optical character recognition, OCR is one of the most popular and challenging topic of pattern recognition This paper proposes an OCR system for Telugu documents which comprises of three stages, namely pre-processing, feature extraction, and classification. In the preprocessing stage, we have employed median filtering on the input characters and applied normalization and skeletonization method over characters for extraction of boundary edge pixel points. In the feature extraction stage, initially the each character is divided into 3×3 grids and the corresponding centroid for all the nine zones are evaluated. With this we can identify the characters of different styles. There after, we have drawn the horizontal and vertical symmetric projection angel to the nearest pixel of the character which is dubbed as Binary External Symmetry Axis Constellation for unconstrained handwritten character. From which we have calculated the horizontal and vertical Euclidean distance for the same nearest pixel from centroid of each zone. Then we have calculated the mean Euclidean distance as well as the mean angular values of the zones. This is considered as the key feature values of our proposed system. Lastly, both support vector machine (SVM) and Quadratic discriminate Classifier (QDA) has been separately used as the classifier.

Motivated by the increasing popularity and success of attention mechanisms, we observe that popular convolutional attention models like Squeeze-and-Excite (SE) and Convolutional Block Attention Module (CBAM) rely on expensive multi-layer perceptron (MLP) layers. These MLP layers significantly increase computational complexity, making such models less applicable to 3D image contexts, where the data dimensionality and computational costs are inherently higher. In 3D medical imaging, such as pulmonary CT scans, efficient processing is crucial due to the large volume of data. Traditional 2D attention mechanisms, when generalized to 3D, increase the computational load, creating a demand for more efficient attention mechanisms that can operate effectively within a 3D tasks. In this work, we investigate the possibility of incorporating fully convolutional attention within 3D context. Particularly, we present two 3D fully convolutional attention blocks in which we demonstrate effectiveness within the 3D context. We demonstrate effectiveness of the proposed method using the pulmonary CT scans for 3D lung nodule detection. Building on existing 3D nodule detection methods, we present AttentNet, an automated lung nodule detection framework from CT images that performs detection as an ensemble of two stages, candidate proposal stage (Region Proposal Network), in which a high number of candidates is produced, and a false positive reduction stage to reduce the number of false alarms. Throughout our work, we compare the proposed 3D convolutional attention blocks to a number of popular 2D convolutional attention mechanisms by generalizing them to 3D modules, including SE units and CBAM channel attention and spatial attention units. We also compare these to Transformer self-attention units. For the False positive reduction stage, we incorporate a joint analysis approach that considers the variable nodule morphology by aggregating spatial information from different contextual levels. We use LUNA-16 lung nodule detection dataset to demonstrate the benefits of using the proposed fully convolutional attention blocks comparing to baseline popular lung nodule detection methods where no attention is used. It is worth noting that our work does not aim at achieving state-of-the-art results in the lung nodule detection task, rather to demonstrate the benefits of incorporating fully convolutional attention within a 3D context.

In this study, a computer-aided detection system was developed for detection and investigation of lung nodules in computed tomography images using image processing techniques. The computer aided detection system consists of four stages. First and second stages are preprocessing stages. First preprocessing stage is two-dimensional preprocessing stage and second preprocessing stage is three-dimensional preprocessing stage. Third stage of the developed system is the feature extraction stage. Five different groups of features are extracted from volume of interests in this stage. Last stage is the the nodule detection stage. The support vector machine algorithm is optimized using evolutionary algorithms to classify volume of interests using the features. The computer aided detection system achieves 93.76% sensitivity, 81.69% selectivity, 84.52% accuracy and 3.63 false positive per scan using only morphologic, statistical and histogram based features. After the inclusion of groups of outer surface statistical and outer surface GLCM and Gabor filter based textural features, performance rates of the computer aided detection system reaches 98.35% sensitivity, 90.42% selectivity, 92.28% accuracy and 2.33 false positive per scan. Results of experiments reveal that outer surface statistical and textural features are useful to increase sensitivity of the system. These features also decrease the number of false positives of the developed systemi

Opinions on social media can be used to determine user sentiment by using sentiment analysis concept. Sentiment analysis requires several important stages, namely, preprocessing, feature extraction and classification method stages. The preprocessing stage was carried out to eliminate inconsistent data. In previous research, punctuation marks removal was applied at the preprocessing stage which can eliminate the emoticon position. Emoticons are a combination of punctuation marks. According to previous research, the emoticon feature has no contribution in sentiment analysis. There is another suggestion to maintain an emoticon position like converting an emoticon into a more relevant word such as :) into a “smile”. However, the feature of emoticon weights has not been considered in the sentiment analysis process. In order to consider the role of emoticons and to improve sentiment analysis performance, we propose using a combination of machine learning and emoticon weights. We perform emoticon weight based on probability and sentiment score. Each probability value and sentiment score of the emoticon will be normalized using the z-score method. There are several machine learning methods that have the best classification success rates, namely, Naïve Bayes and SVM. Based on the evaluation results of the proposed model, the best accuracy is 87% - 89% when using the combination of machine learning and emoticon sentiment score. Based on the results also show that the emoticon sentiment score has a significant effect on the accuracy of sentiment analysis.

The term Data Fusion refers to integrating knowledge from at least two independent sources of information such that the result is more than merely the sum of all inputs. In our project, the knowledge about a given specimen comprises its acquisitions from optical 3D scans and Computed Tomography with a special focus on limited-angle artifacts. In industrial quality inspection those imaging techniques are commonly used for non-destructive testing. Additional sources of information are digital descriptions for manufacturing, or tactile measurements of the specimen. Hence, we have several representations comprising the object as a whole, each with certain shortcomings and unique insights. We strive for combining all their strengths and compensating their weaknesses in order to create an enhanced representation of the acquired object. To achieve this, the identification of correspondences in the representations is the first task. We extract a subset with prominent exterior features from each input because all acquisitions include these features. To this end, regional queries from random seeds on an enclosing hull are employed. Subsequently, the relative orientation of the original data sets is calculated based on their subsets, as those comprise the - potentially defective - areas of overlap. We consider global features such as principal components and barycenters for the alignment, since in this specific case classical point-to-point comparisons are prone to error. Our alignment scheme outperforms traditional approaches and can even be enhanced by considering limited-angle artifacts in the reconstruction process of Computed Tomography. An analysis of local gradients in the resulting volumetric representation allows to distinguish between reliable observations and defects. Lastly, tactile measurements are extremely accurate but lack a suitable 3D representation. Thus, we also present an approach for converting them in a 3D surface suiting our work flow. As a result, the respective inputs are now aligned with each other, indicate the quality of the included information, and are in compatible format to be combined in a subsequent step. The data fusion result permits more accurate metrological tasks and increases the precision of detecting flaws in production or indications of wear-out. The final step of combining the data sets is briefly presented here along with the resulting augmented representation, but in its entirety and details subject to another PhD thesis within our joint project.

Sparse random neural networks for online anomaly detection on sensor nodes

In industrial quality inspection, large amounts of data on the desired product appearance are available at the time of training, while significantly few defective samples are available. In this study, we proposed new memory-augmented adversarial autoencoders to detect and localize defects in real-time using defect-free samples alone for model training. This research was conducted by reconstructing images using an adversarial autoencoder and detection results from the Fréchet Markov distance (FMD). A threshold was determined based on the statistical characteristics of defect-free samples in the training set. Innovatively, we introduced a memory module and redesigned the reconstruction loss function to avoid the situation where the reconstruction ability is too strong or too poor, which lead to missing detection of defects. Then we proposed FMD, which can accurately measure the distance between the distribution of test samples and positive samples. Moreover, the statistics-based threshold determination method is used to meet different industrial needs. The accuracy, robustness, and computational overhead of the proposed MAA were evaluated using three datasets obtained from the production line and two benchmark datasets. The results indicated the effectiveness and ability of the proposed method to adapt to the real-time nature of industrial production.