Search Results (21)

With the advancement of automation in modern agriculture, the demand for intelligence in the post-picking sorting of fruits and vegetables is increasing. As a significant global agricultural product, the defect detection and sorting of tomato is essential to ensure quality and improve economic value. However, the traditional detection method (manual screening) is inefficient and involves high labor intensity. Therefore, a defect detection model named YOLO-RGDD is proposed based on YOLOv12s to identify five types of tomato surface defects (scars, gaps, white spots, spoilage, and dents). Firstly, the original C3k2 module and A2C2f module of YOLOv12 were replaced with RFEM in the backbone network to enhance feature extraction for small targets without increasing computational complexity. Secondly, the Dysample–Slim-Neck of the YOLO-RGDD was developed to reduce the computational complexity and enhance the detection of minor defects. Finally, dynamic convolution was used to replace the conventional convolution in the detection head in order to reduce the model parameter count. The experimental results show that the average precision, recall, and F1-score of the proposed YOLO-RGDD model for tomato defect detection reach 88.5%, 85.7%, and 87.0%, respectively, surpassing advanced object recognition detection algorithms. Additionally, the computational complexity of the YOLO-RGDD is 16.1 GFLOPs, which is 24.8% lower than that of the original YOLOv12s model (21.4 GFLOPs), facilitating the model’s deployment in automated agricultural production. Full article

Accurate and efficient white-spot defects detection for the surface of galvanized strip steel is one of the most important guarantees for the quality of steel production. It is a fundamental but “hard” small target detection problem due to its small pixel occupation in low-contrast images. By fully exploiting the low-rank and sparse prior information of a surface defect image, a Schatten-p norm-based low-rank tensor decomposition (SLRTD) method is proposed to decompose the defect image into low-rank background, sparse defect, and random noise. Firstly, the original defect images are transformed into a new patch-based tensor mode through data reconstruction for mining valuable information of the defect image. Then, considering the over-shrinkage problem in the low-rank component estimation caused by a vanilla nuclear norm and a weighted nuclear norm, a nonlinear reweighting strategy based on a Schatten $p$-norm is incorporated to improve the decomposition performance. Finally, a solution framework is proposed via a well-designed alternating direction method of multipliers to obtain the white-spot defect target image by a simple segmenting algorithm. The white-spot defect dataset from a real-world galvanized strip steel production line is constructed, and the experimental results demonstrate that the proposed SLRTD method outperforms existing state-of-the-art methods qualitatively and quantitatively. Full article

The deep learning architecture YOLO (You Only Look Once) has demonstrated its superior visual detection performance in various computer vision tasks and has been widely applied in the field of automatic surface defect detection. In this paper, we propose a lightweight YOLOv8-based method for the quality inspection of car body welding spots. We developed a TA-YOLOv8 network structure which has an improved Task-Aligned (TA) head detection, designed to handle a small sample size, imbalanced positive and negative samples, and high-noise characteristics of Body-in-White welding spot data. By learning with fewer parameters, the model achieves more efficient and accurate classification. Additionally, our algorithm framework can perform anomaly segmentation and classification on our open-world raw datasets obtained from actual production environments. The experimental results show that the lightweight module improves the processing speed by an average of 2.8%, with increases in detection the mAP@50-95 and recall rate of 1.35% and 0.1226, respectively. Full article

The flavor substances produced by the division of baijiu yeast during the winemaking process often determine the quality of white wine, and the difficulty of storing and transporting high-quality baijiu yeast is a bottleneck that restricts the development of China’s baijiu industry. It is widely accepted that drying microorganisms such as baijiu yeast is the best way to improve its storage and transport performance. Spray drying, as one of the most widely used microbial drying processes, with a high efficiency and low cost, is the hot spot of current research in the field of microbial drying, but it has the inherent defect of a low drying survival rate. In order to address this inherent defect, the present study was carried out with a high-quality white wine yeast, Modified Sporidiobolus Johnsonii A (MSJA), as the target. Firstly, an orthogonal experiment, Steep Hill Climbing experiment, and response surface experiment were sequentially designed to optimize the type and amount of protective agent added in the spray-drying process of MSJA. Then, the effects of glutamyl transaminase (TGase) treatment on the drying process of MSJA were revealed with the help of advanced equipment, such as laser particle sizer, environmental scanning electron microscope (ESEM), and Fourier-transform infrared scanner (FTIR). The results showed that the addition of “TGase-treated soybean isolate protein (SPI) + lactic protein (LP)” as an in vitro bacterial protectant and “14.15% trehalose + 7.10% maltose + 14.04% sucrose” TGase treatment can promote the cross-linking of protective proteins, reduce the distance between MSJA bacteria and protective proteins, and increase the glass transition temperature to enhance the protective effect of protective proteins, so as to improve the survival rate of MSJA during spray drying. Full article

This paper presents an enhanced Faster R-CNN model for detecting surface defects in resistance welding spots, improving both efficiency and accuracy for body-in-white quality monitoring. Key innovations include using high-confidence anchor boxes from the RPN network to locate welding spots, using the SmoothL1 loss function, and applying Fast R-CNN to classify detected defects. Additionally, a new pruning model is introduced, reducing unnecessary layers and parameters in the neural network, leading to faster processing times without sacrificing accuracy. Tests show that the model achieves over 90% accuracy and recall, processing each image in about 15 ms, meeting industrial requirements for welding spot inspection. Full article

Nematodes pose significant challenges for the fish processing industry, particularly in white fish. Despite technological advances, the industry still depends on manual labor for the detection and extraction of nematodes. This study addresses the initial steps of automatic nematode detection and differentiation from other common defects in fish fillets, such as skin remnants and blood spots. VideometerLab 4, an advanced Multispectral Imaging (MSI) System, was used to acquire 270 images of 50 Atlantic cod fillets under controlled conditions. In total, 173 nematodes were labeled using the Segment Anything Model (SAM), which is trained to automatically segment objects of interest from only few representative pixels. With the acquired dataset, we study the potential of identifying nematodes through their spectral signature. We incorporated normalized Canonical Discriminant Analysis (nCDA) to develop segmentation models trained to distinguish between different components within the fish fillets. By incorporating multiple segmentation models, we aimed to achieve a satisfactory balance between false negatives and false positives. This resulted in 88% precision and 79% recall for our annotated test data. This approach could improve process control by accurately identifying fillets with nematodes. Using MSI minimizes unnecessary inspection of fillets in good condition and concurrently boosts product safety and quality. Full article

Traits such as shape, size, and color often influence the economic and sentimental value of a horse. Around the world, horses are bred and prized for the colors and markings that make their unique coat patterns stand out from the crowd. The underlying genetic mechanisms determining the color of a horse’s coat can vary greatly in their complexity. For example, only two genetic markers are used to determine a horse’s base coat color, whereas over 50 genetic variations have been discovered to cause white patterning in horses. Some of these white-causing mutations are benign and beautiful, while others have a notable impact on horse health. Negative effects range from slightly more innocuous defects, like deafness, to more pernicious defects, such as the lethal developmental defect incurred when a horse inherits two copies of the Lethal White Overo allele. In this review, we explore, in detail, the etiology of white spotting and its overall effect on the domestic horse to Spot the Pattern of these beautiful (and sometimes dangerous) white mutations. Full article

In the secondary metals refining processes, vacuum arc remelting (VAR) and electroslag remelting (ESR), the consumable electrode is commonly produced by vacuum induction melting (VIM) which employs the regrettably primitive casting technique of simply pouring into the open top of the mold. Despite the vacuum, the resulting oxidizing conditions and the immensely powerful turbulence accompanying the top-pouring of the electrode is now known to create a substantial density of serious cracks. The cracks in the cast electrode are bifilms (double oxide films), which in turn are proposed to be responsible for the major faults of the VAR ingot, including undetectable, horizontal macroscopic cracks, white spots (clean and dirty varieties) and in-fallen crown. The remedial action to solve all these issues at a stroke is the provision of a counter-gravity cast electrode, cast in air or vacuum, or provision of any similar electrode substantially free from bifilm defects. The ESR process is also described, explaining the reasons for its significantly reduced sensitivity to the top-poured VIM electrode, but indicating that with an improved electrode, this already nearly reliable process has the potential for perfect reliability. The target of this critical overview is an assessment of the potential of these secondary refining processes to produce, for the first time, effectively defect-free metals, metals we can trust. Full article

Dental fluorosis is an irreversible defect in dental enamel caused by long-term undesired fluoride intake during tooth formation. The clinical manifestations may range from white spots to dark brown areas, which can initially represent only an aesthetic problem, but they can also lead to functional problems—in severe cases, pitting and fractures can occur. The aim of this cross-sectional study in a cluster of 215 Kenyan adolescents was to evaluate oral health status—especially with respect to fluorosis and dental caries risk factors—in the Nairobi suburbs. Clinical data were recorded using DMFT and TF indices in accordance with the WHO standards. A multivariate model with logistic regression was carried out. In total, 36.7% of individuals presented carious lesions. The DMFT index was 0.87 in the total sample. Around 78.6% were affected by mild-to-severe forms of fluorosis. Statistically significant associations were found between the presence of caries and consuming sweets during (OR = 3.9) and between meals (OR = 3.6), consuming soft drinks during (OR = 2.8) and between meals (OR = 4.3), tooth-brushing frequency (OR = 2.8), use of toothbrush and toothpaste (OR = 3.8), presence of bleeding (OR = 10.2), and calculus (OR = 12.1). It is critical to give people sufficient knowledge and to educate the communities to mobilize the implementation of preventive measures, such as reducing fluoride ingestion and paying attention to the dangers of drinking untreated water, in order to develop strategies to ensure equitable access to medical services and promote oral prevention programs to significantly reduce the impact of oral diseases. Full article

Using a new implantation technique with multielement molecular ions consisting of carbon, hydrogen, and phosphorus, namely, CH₂P molecular ions, we developed an epitaxial silicon wafer with proximity gettering sinks under the epitaxial silicon layer to improve the gettering capability for metallic impurities. A complementary metal-oxide-semiconductor (CMOS) image sensor fabricated with this novel epitaxial silicon wafer has a markedly reduced number of white spot defects, as determined by dark current spectroscopy (DCS). In addition, the amount of nickel impurities gettered in the CH₂P-molecular-ion-implanted region of this CMOS image sensor is higher than that gettered in the C₃H₅-molecular-ion-implanted region; and this implanted region is formed by high-density black pointed defects and deactivated phosphorus after epitaxial growth. From the obtained results, the CH₂P-molecular-ion-implanted region has two types of complexes acting as gettering sinks. One includes carbon-related complexes such as aggregated C–I, and the other includes phosphorus-related complexes such as P₄–V. These complexes have a high binding energy to metallic impurities. Therefore, CH₂P-molecular-ion-implanted epitaxial silicon wafers have a high gettering capability for metallic impurities and contribute to improving the device performance of CMOS image sensors. (This manuscript is an extension from a paper presented at the 6th IEEE Electron Devices Technology & Manufacturing Conference (EDTM 2022)). Full article

Background: Early Childhood Caries (ECC) is a prevalent chronic pathology, and it has a negative impact on the oral and general health of the child patient. Aim: To evaluate the knowledge, attitudes and practices of Spanish paediatricians regarding early childhood caries according to the professional’s years of experience. Material and Methods: A cross-sectional questionnaire was conducted by Spanish paediatricians via WhatsApp and e-mails from January to April 2021. Data were analysed using Chi-squared test, Fisher’s exact test and Cramer’s V test. Results: There were a total of 359 participants. Most respondents were women (81.3%) with up to 10 years of professional experience (31.2%) in primary health care and public health. In most cases, participants had an excellent knowledge of primary dentition (90.8%), but they ignored (56%) when the first visit to the dentist should occur. Regarding the aetiological factors of caries, oral hygiene and prevention, a lower rate of knowledge was observed. The majority of participants (80.8%) were not able to identify white spot lesions and enamel defects (76%). They considered that their knowledge in oral health was deficient, highlighting the need to increase their training. Less experienced paediatricians were found to have higher success rates. Conclusions: The level of knowledge and attitudes regarding early childhood caries of the evaluated paediatricians should be improved. Paediatricians had difficulties in identifying early caries lesions and enamel defects. Nevertheless, a higher level of knowledge and positive attitudes towards dental caries has been detected among paediatricians with fewer years of professional experience. Full article

X-linked adrenoleukodystrophy (X-ALD) is a neurodegenerative disease caused by pathogenic variants in ABCD1 resulting in defective peroxisomal oxidation of very long-chain fatty acids. Most male patients develop adrenal insufficiency and one of two neurologic phenotypes: a rapidly progressive demyelinating disease in mid-childhood (childhood cerebral X-ALD, ccALD) or an adult-onset spastic paraparesis (adrenomyeloneuropathy, AMN). The neurodegenerative course of ccALD can be halted if patients are treated with hematopoietic stem cell transplantation at the earliest onset of white matter disease. Newborn screening for X-ALD can be accomplished by measuring C26:0-lysophosphatidylcholine in dried blood spots. In Nebraska, X-ALD newborn screening was instituted in July 2018. Over a period of 3.3 years, 82,920 newborns were screened with 13 positive infants detected (4 males, 9 females), giving a birth prevalence of 1:10,583 in males and 1:4510 in females. All positive newborns had DNA variants in ABCD1. Lack of genotype-phenotype correlations, absence of predictive biomarkers for ccALD or AMN, and a high proportion of ABCD1 variants of uncertain significance are unique challenges in counseling families. Surveillance testing for adrenal and neurologic disease in presymptomatic X-ALD males will improve survival and overall quality of life. Full article

Background: The early identification of children who have experienced adversity is critical for the timely delivery of interventions to improve coping and reduce negative consequences. Self-report is the usual practice for identifying children with exposure to adversity. However, physiological characteristics that signal the presence of disease or other exposures may provide a more objective identification strategy. This protocol describes a case–control study that assesses whether exposure to adversity is more common in children with tooth enamel anomalies compared to children without such anomalies. Methods: For 150 mother–child pairs from a pediatric dental clinic in Toronto, Canada, maternal interviews will assess the child’s adverse and resilience-building experiences. Per child, one (exfoliated or extracted) tooth will be assessed for suspected enamel anomalies. If anomalies are present, the child is a case, and if absent, the child is a control. Tooth assessment modalities will include usual practice for dental exams (visual assessment) and modalities with greater sensitivity to identify anomalies. Conclusion: If structural changes in children’s teeth are associated with exposure to adversity, routine dental exams could provide an opportunity to screen children for experiences of adversity. Affected children could be referred for follow-up. Full article

The ballasted track superstructure is characterized by a relative quick deterioration of track geometry due to ballast settlements and the accumulation of sleeper voids. The track zones with the sleeper voids differ from the geometrical irregularities with increased dynamic loading, high vibration, and unfavorable ballast-bed and sleeper contact conditions. This causes the accelerated growth of the inhomogeneous settlements, resulting in maintenance-expensive local instabilities that influence transportation reliability and availability. The recent identification and evaluation of the sleeper support conditions using track-side and on-board monitoring methods can help planning prevention activities to avoid or delay the development of local instabilities such as ballast breakdown, white spots, subgrade defects, etc. The paper presents theoretical and experimental studies that are directed at the development of the methods for sleeper support identification. The distinctive features of the dynamic behavior in the void zone compared to the equivalent geometrical irregularity are identified by numeric simulation using a three-beam dynamic model, taking into account superstructure and rolling stock dynamic interaction. The spectral features in time domain in scalograms and scattergrams are analyzed. Additionally, the theoretical research enabled to determine the similarities and differences of the dynamic interaction from the viewpoint of track-side and on-board measurements. The method of experimental investigation is presented by multipoint track-side measurements of rail-dynamic displacements using high-speed video records and digital imaging correlation (DIC) methods. The method is used to collect the statistical information from different-extent voided zones and the corresponding reference zones without voids. The applied machine learning methods enable the exact recent void identification using the wavelet scattering feature extraction from track-side measurements. A case study of the method application for an on-board measurement shows the moderate results of the recent void identification as well as the potential ways of its improvement. Full article

Pre-eruptive enamel lesions occur during tooth formation and include fluorosis, traumatic hypomineralization, and molar incisor hypomineralization. Minimally invasive treatment approaches, such as microabrasion, should be considered for these cases. This article presents a case series of three patients with pre-eruptive enamel defects in esthetically compromised tooth regions which were treated with the microabrasion technique: two fluorosis cases, moderate and advanced, and one hypomineralization case of traumatic etiology. In Cases 1 and 3, there was a significant improvement in esthetics with a total resolution of the enamel defects. However, a slight yellowish coloration may be detected at close observation. In Case 2 (advanced fluorosis), although there was no full resolution of the white spots, there was a clear improvement in esthetics. Microabrasion is a safe and effective, minimally invasive treatment for pre-eruptive enamel lesions. It does not require local anesthesia, it is less destructive than restorative interventions, and allows good esthetic outcomes with no significant postoperative sensitivity. Its efficacy is directly related to the lesions’ severity and depth. Although there are some limitations, further improvement can be achieved with dental bleaching. More invasive treatments might be considered if results are still unsatisfactory. Full article