scholarly journals An Artificial-Intelligence-Driven Predictive Model for Surface Defect Detections in Medical MEMS

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6141
Author(s):  
Amin Amini ◽  
Jamil Kanfoud ◽  
Tat-Hean Gan
Keyword(s):  
Defect Detection ◽  
Surface Defects ◽  
Quality Standard ◽  
Human Interaction ◽  
Raw Material ◽  
Micro Electro Mechanical Systems ◽  
Medical Apparatus ◽  
Machine Learning Approach ◽  
Plenoptic Camera ◽  
Early Phases

With the advancement of miniaturization in electronics and the ubiquity of micro-electro-mechanical systems (MEMS) in different applications including computing, sensing and medical apparatus, the importance of increasing production yields and ensuring the quality standard of products has become an important focus in manufacturing. Hence, the need for high-accuracy and automatic defect detection in the early phases of MEMS production has been recognized. This not only eliminates human interaction in the defect detection process, but also saves raw material and labor required. This research developed an automated defects recognition (ADR) system using a unique plenoptic camera capable of detecting surface defects of MEMS wafers using a machine-learning approach. The developed algorithm could be applied at any stage of the production process detecting defects at both entire MEMS wafer and single component scale. The developed system showed an F1 score of 0.81 U on average for true positive defect detection, with a processing time of 18 s for each image based on 6 validation sample images including 371 labels.

AUTOMATED VISION INSPECTION OF TIMBER SURFACE DEFECT: A REVIEW

2015 ◽  
Vol 77 (20) ◽  
Author(s):  
Ummi Rabaah Hashim ◽  
Siti Zaiton Hashim ◽  
Azah Kamilah Muda
Keyword(s):  
Feature Extraction ◽  
Defect Detection ◽  
Surface Defect ◽  
Surface Defects ◽  
Raw Material ◽  
Special Focus ◽  
Automated Inspection ◽  
Extraction Techniques ◽  
Vision Inspection ◽  
Surface Defect Detection

Automated inspection has proven to be of great importance in increasing the quality of timber products, optimising raw material resources, increasing productivity as well as reducing error related to human labour. This paper reviews automated inspection of timber surface defects with a special focus on vision inspection. Previous works on sensors utilised are presented and can be used as a reference for future researchers. General approaches to solving the problem of wood surface defect detection can be categorised into segmentation and non-segmenting approaches. The weaknesses and strengths of each approach are discussed along with feature extraction techniques and classifiers implemented in timber surface defect detection. Furthermore, insights into the practicality of implementing automated vision inspection of timber defects were also discussed. This paper shall benefit researchers and practitioners in understanding different approaches, sensors, feature extraction techniques as well as classifiers that have been implemented in automated inspection of timber surface defects, thus providing some direction for future research.

Lightweight detection algorithm for fine-grained surface defects of aerospace seal rings

2021 ◽  
pp. 1-18
Author(s):  
Hui Liu ◽  
Boxia He ◽  
Yong He ◽  
Xiaotian Tao
Keyword(s):  
Feature Extraction ◽  
Defect Detection ◽  
Surface Defect ◽  
Surface Defects ◽  
Detection Algorithm ◽  
Seal Ring ◽  
Fine Grained ◽  
Aerospace Applications ◽  
Surface Defect Detection ◽  
The Mean

The existing seal ring surface defect detection methods for aerospace applications have the problems of low detection efficiency, strong specificity, large fine-grained classification errors, and unstable detection results. Considering these problems, a fine-grained seal ring surface defect detection algorithm for aerospace applications is proposed. Based on analysis of the stacking process of standard convolution, heat maps of original pixels in the receptive field participating in the convolution operation are quantified and generated. According to the generated heat map, the feature extraction optimization method of convolution combinations with different dilation rates is proposed, and an efficient convolution feature extraction network containing three kinds of dilated convolutions is designed. Combined with the O-ring surface defect features, a multiscale defect detection network is designed. Before the head of multiscale classification and position regression, feature fusion tree modules are added to ensure the reuse and compression of the responsive features of different receptive fields on the same scale feature maps. Experimental results show that on the O-rings-3000 testing dataset, the mean condition accuracy of the proposed algorithm reaches 95.10% for 5 types of surface defects of aerospace O-rings. Compared with RefineDet, the mean condition accuracy of the proposed algorithm is only reduced by 1.79%, while the parameters and FLOPs are reduced by 35.29% and 64.90%, respectively. Moreover, the proposed algorithm has good adaptability to image blur and light changes caused by the cutting of imaging hardware, thus saving the cost.

scholarly journals Standardization of Mango (Mangifera Indica L.) Peel Simplisia of Gadung Variety

2021 ◽  
Vol 1 (1) ◽  
pp. 1-8
Author(s):  
Andini Andini ◽  
Cindy Fernanda Putri
Keyword(s):  
Moisture Content ◽  
Mangifera Indica ◽  
Quality Standard ◽  
Ash Content ◽  
Water Soluble ◽  
Raw Material ◽  
Yellow Colour ◽  
Water Soluble Compound ◽  
Mango Peel ◽  
Compound Concentration

Mango peel (Mangfera indica L.) has many pharmacological effects as a traditional medicine. Therefore, standardization of mango peel simplisia needs to be done as a preparation of phytopharmaca raw material. This research aimed to obtain standardization of mango peel simplisia include specific and non-specific parameter. The research procedures include plant determination, simplisia preparation as well as specific standardization test (includes organoleptic, water-soluble compound concentration, and ethanol solution compound concentration) and nonspecific standardization test (includes moisture content, dried shrinkage, total ash content and acid insoluble ash content). The specific organoleptic parameters of dried mango peel simplisia have a distinctive sweet aroma, bitter taste, and brownish yellow colour. Water-soluble and ethanol-soluble concentrations are 22,36% ± 1,17% and 9,56% ± 0,07%. Moisture content is 9,09% ± 1,44%. Dried shrinkage rate is 0,19% ± 0,04%. Total ash and acid insoluble ash contents are 4,11% ± 0,10% and 0,14% ± 0,03%. The mango peel simplisia has met the quality standard of the raw material.

scholarly journals Geochemical And Mineralogical Assessment Of Secondary Gypsum In Al-Najaf, Iraq And Employment As Raw Material For Cement Industry

2021 ◽  
Vol 72 ◽  
pp. 215-222
Author(s):  
Mohanad R.A. Al-Owaidi ◽  
◽  
Mohammed L. Hussein ◽  
Ruaa Issa Muslim ◽  
◽  
...  
Keyword(s):  
Portland Cement ◽  
Raw Materials ◽  
Chemical Properties ◽  
Quality Standard ◽  
Cement Industry ◽  
Raw Material ◽  
Insoluble Residue ◽  
Mineralogical Study ◽  
The Mean ◽  
Industry Success

The Portland cement industry is one of the strategic industries in any country. The basis of an industry success is the availability of raw materials and, the low extraction in addition to transportation costs. The Bahr Al-Najaf region is abundant with limestone rocks but lacks primary gypsum. An investigation had been carried out to identify the source of secondary gypsum as an alternative to primary gypsum. Twelve boreholes were drilled for a depth of 2 m, as the thickness of suitable secondary gypsum layer ranges from 1 to 1.5 m. The mineralogical study revealed the predominance of gypsum followed by quartz and calcite, with an average of 62.9%, 19.6% and 14.35%, respectively. The geochemical analysis revealed that the content of SO3 is appropriate and ranging from 41.92% to 32.89% with an average of 37.73%. The SO3 content is within an acceptable range. The mean abundance of the major oxides of the study area may be arranged as SO3 > CaO> SiO2> MgO> Al2O> Fe2O3. The insoluble residue was at an acceptable rate. The laboratory experiments for milling secondary gypsum with clinker has successfully proven the production of Portland cement that matches the limits of the Iraqi Quality Standard (IQS) No. 5 of 1984. Great care must be taken when using secondary gypsum; secondary gypsum must be mixed well to maintain the chemical properties before blending with clinker and utilizing in the cement mill in the cement plant.

Computer Vision Based Technique for Surface Defect Detection of Apples

2014 ◽  
pp. 111-121
Author(s):  
C. J. Prabhakar ◽  
S. H. Mohana
Keyword(s):  
Computer Vision ◽  
Defect Detection ◽  
Surface Defects ◽  
Quality Standards ◽  
Production Costs ◽  
Automatic Inspection ◽  
Segmentation Technique ◽  
Surface Defect Detection ◽  
Fruit Grading

The automatic inspection of quality in fruits is becoming of paramount importance in order to decrease production costs and increase quality standards. Computer vision techniques are used in fruit industry for fruit grading, sorting, and defect detection. In this chapter, we review recent approaches for automatic inspection of quality in fruits using computer vision techniques. Particularly, we focus on the review of advances in computer vision techniques for automatic inspection of quality of apples based on surface defects. Finally, we present our approach to estimate the defects on the surface of an apple using grow-cut and multi-threshold based segmentation technique. The experimental results show that our method effectively estimates the defects on the surface of apples significantly more effectively than color based segmentation technique.

Unsupervised fabric defect detection based on a deep convolutional generative adversarial network

2019 ◽  
Vol 90 (3-4) ◽  
pp. 247-270 ◽  
Author(s):  
Guanghua Hu ◽  
Junfeng Huang ◽  
Qinghui Wang ◽  
Jingrong Li ◽  
Zhijia Xu ◽  
...  
Keyword(s):  
Defect Detection ◽  
Surface Defects ◽  
Generative Adversarial Network ◽  
Query Image ◽  
Training Strategy ◽  
Fabric Defect Detection ◽  
Adversarial Network ◽  
Fabric Defect ◽  
Pixel Value ◽  
Textured Materials

Detecting and locating surface defects in textured materials is a crucial but challenging problem due to factors such as texture variations and lack of adequate defective samples prior to testing. In this paper we present a novel unsupervised method for automatically detecting defects in fabrics based on a deep convolutional generative adversarial network (DCGAN). The proposed method extends the standard DCGAN, which consists of a discriminator and a generator, by introducing a new encoder component. With the assistance of this encoder, our model can reconstruct a given query image such that no defects but only normal textures will be preserved in the reconstruction. Therefore, when subtracting the reconstruction from the original image, a residual map can be created to highlight potential defective regions. Besides, our model generates a likelihood map for the image under inspection where each pixel value indicates the probability of occurrence of defects at that location. The residual map and the likelihood map are then synthesized together to form an enhanced fusion map. Typically, the fusion map exhibits uniform gray levels over defect-free regions but distinct deviations over defective areas, which can be further thresholded to produce a binarized segmentation result. Our model can be unsupervisedly trained by feeding with a set of small-sized image patches picked from a few defect-free examples. The training is divided into several successively performed stages, each under an individual training strategy. The performance of the proposed method has been extensively evaluated by a variety of real fabric samples. The experimental results in comparison with other methods demonstrate its effectiveness in fabric defect detection.

Rail Defect Detection Using Fiber Optic Sensors and Wavelet Algorithms

2018 ◽  
Author(s):  
Saied Taheri ◽  
Behzad Moslehi ◽  
Vahid Sotoudeh ◽  
Brad M. Hopkins
Keyword(s):  
Defect Detection ◽  
Surface Defects ◽  
New Technology ◽  
Interaction Model ◽  
High Amplitude ◽  
Detection Algorithms ◽  
Simple Detection ◽  
Surface Irregularities ◽  
Signal Processing Algorithms ◽  
Low Amplitude

Early detection of rail defects can avoid derailments and costly damage to the train and railway infrastructure. Small breaks, cracks or corrugations on the rail can quickly propagate after only a few train cars have passed over it, creating a potential derailment. The current technology makes use of a dedicated instrumented car or a separate railway monitoring vehicle to detect large breaks. These cars are usually equipped with accelerometers mounted on the axle or side frame. The simple detection algorithms use acceleration thresholds which are set at high values to eliminate false positives. As a result, rail surface defects that produce low amplitude acceleration signatures may not be detected, and special track components that produce high amplitude acceleration signatures may be flagged as defects. This paper presents the results of a feasibility study conducted to develop new and more advanced sensory systems as well as signal processing algorithms capable of detecting various rail surface irregularities. A dynamic wheel-rail interaction model was used to simulate train dynamics as a result of rail defects and to assess the potential of this new technology on rail defect detection. In a future paper, we will present experimental data in support of the proposed model and simulations.

Sign in / Sign up

Export Citation Format

Share Document