DEFECT DETECTION IN APPLES BY MEANS OF X-RAY IMAGING

AbstractWith the improvement of electronic circuit production methods, such as reduction of component size and the increase of component density, the risk of defects is increasing in the production line. Many techniques have been incorporated to check for failed solder joints, such as X-ray imaging, optical imaging and thermal imaging, among which X-ray imaging can inspect external and internal defects. However, some advanced algorithms are not accurate enough to meet the requirements of quality control. A lot of manual inspection is required that increases the specialist workload. In addition, automatic X-ray inspection could produce incorrect region of interests that deteriorates the defect detection. The high-dimensionality of X-ray images and changes in image size also pose challenges to detection algorithms. Recently, the latest advances in deep learning provide inspiration for image-based tasks and are competitive with human level. In this work, deep learning is introduced in the inspection for quality control. Four joint defect detection models based on artificial intelligence are proposed and compared. The noisy ROI and the change of image dimension problems are addressed. The effectiveness of the proposed models is verified by experiments on real-world 3D X-ray dataset, which saves the specialist inspection workload greatly.

Download Full-text

A Lightweight Deep Network for Defect Detection of Insert Molding Based on X-ray Imaging

Sensors ◽

10.3390/s21165612 ◽

2021 ◽

Vol 21 (16) ◽

pp. 5612

Author(s):

Benwu Wang ◽

Feng Huang

Keyword(s):

Defect Detection ◽

Molding Process ◽

X Ray ◽

Deep Network ◽

X Ray Imaging ◽

Common Causes ◽

Model Size ◽

The One ◽

Image Defect ◽

Insert Molding

Aiming at the abnormality detection of industrial insert molding processes, a lightweight but effective deep network is developed based on X-ray images in this study. The captured digital radiography (DR) images are firstly fast guide filtered, and then a multi-task detection dataset is constructed using an overlap slice in order to improve the detection of tiny targets. The proposed network is extended from the one-stage target detection method of yolov5 to be applicable to DR defect detection. We adopt the embedded Ghost module to replace the standard convolution to further lighten the model for industrial implementation, and use the transformer module for spatial multi-headed attentional feature extraction to perform improvement on the network for the DR image defect detection. The performance of the proposed method is evaluated by consistent experiments with peer networks, including the classical two-stage method and the newest yolo series. Our method achieves a mAP of 93.6%, which exceeds the second best by 3%, with robustness sufficient to cope with luminance variations and blurred noise, and is more lightweight. We further conducted ablation experiments based on the proposed method to validate the 32% model size reduction owing to the Ghost module and the detection performance enhancing effect of other key modules. Finally, the usability of the proposed method is discussed, including an analysis of the common causes of the missed shots and suggestions for modification. Our proposed method contributes a good reference solution for the inspection of the insert molding process.

Download Full-text

Defects of Platelet Function Recognized by X-Ray Imaging and Scanning Electron Microscopy

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100119806 ◽

1985 ◽

Vol 43 ◽

pp. 610-613

Author(s):

M.G. Baldini ◽

S. Morinaga ◽

D. Minasian ◽

R. Feder ◽

D. Sayre ◽

...

Keyword(s):

Electron Microscopy ◽

Scanning Electron Microscopy ◽

Cell Biology ◽

Imaging Technique ◽

Human Platelets ◽

X Rays ◽

X Ray ◽

X Ray Imaging ◽

Complex Phenomena ◽

Scanning Electron

Contact X-ray imaging is presently developing as an important imaging technique in cell biology. Our recent studies on human platelets have demonstrated that the cytoskeleton of these cells contains photondense structures which can preferentially be imaged by soft X-ray imaging. Our present research has dealt with platelet activation, i.e., the complex phenomena which precede platelet appregation and are associated with profound changes in platelet cytoskeleton. Human platelets suspended in plasma were used. Whole cell mounts were fixed and dehydrated, then exposed to a stationary source of soft X-rays as previously described. Developed replicas and respective grids were studied by scanning electron microscopy (SEM).

Download Full-text

Designing high-resolution slow scan CCD-based TEM camera systems

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s042482010012936x ◽

1992 ◽

Vol 50 (2) ◽

pp. 946-947

Author(s):

James F. Mancuso ◽

William B. Maxwell ◽

Russell E. Camp ◽

Mark H. Ellisman

Keyword(s):

Fiber Optics ◽

Ccd Camera ◽

High Energy ◽

Phosphor Layer ◽

X Ray ◽

Light Production ◽

Camera Systems ◽

X Ray Imaging ◽

Electron Image ◽

Scintillating Fiber

The imaging requirements for 1000 line CCD camera systems include resolution, sensitivity, and field of view. In electronic camera systems these characteristics are determined primarily by the performance of the electro-optic interface. This component converts the electron image into a light image which is ultimately received by a camera sensor.Light production in the interface occurs when high energy electrons strike a phosphor or scintillator. Resolution is limited by electron scattering and absorption. For a constant resolution, more energy deposition occurs in denser phosphors (Figure 1). In this respect, high density x-ray phosphors such as Gd2O2S are better than ZnS based cathode ray tube phosphors. Scintillating fiber optics can be used instead of a discrete phosphor layer. The resolution of scintillating fiber optics that are used in x-ray imaging exceed 20 1p/mm and can be made very large. An example of a digital TEM image using a scintillating fiber optic plate is shown in Figure 2.

Download Full-text

Ionic homeostasis and subcellular element compartmentation

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s042482010013434x ◽

1990 ◽

Vol 48 (2) ◽

pp. 150-151

Author(s):

Ann LeFurgey ◽

Peter Ingram ◽

J.J. Blum ◽

M.C. Carney ◽

L.A. Hawkey ◽

...

Keyword(s):

Leishmania Major ◽

Ionic Homeostasis ◽

X Ray ◽

Functional Studies ◽

Cell Compartments ◽

X Ray Imaging ◽

Resolution Electron ◽

Multiple Cell ◽

Role Of Zn

Subcellular compartments commonly identified and analyzed by high resolution electron probe x-ray microanalysis (EPXMA) include mitochondria, cytoplasm and endoplasmic or sarcoplasmic reticulum. These organelles and cell regions are of primary importance in regulation of cell ionic homeostasis. Correlative structural-functional studies, based on the static probe method of EPXMA combined with biochemical and electrophysiological techniques, have focused on the role of these organelles, for example, in maintaining cell calcium homeostasis or in control of excitation-contraction coupling. New methods of real time quantitative x-ray imaging permit simultaneous examination of multiple cell compartments, especially those areas for which both membrane transport properties and element content are less well defined, e.g. nuclei including euchromatin and heterochromatin, lysosomes, mucous granules, storage vacuoles, microvilli. Investigations currently in progress have examined the role of Zn-containing polyphosphate vacuoles in the metabolism of Leishmania major, the distribution of Na, K, S and other elements during anoxia in kidney cell nuclel and lysosomes; the content and distribution of S and Ca in mucous granules of cystic fibrosis (CF) nasal epithelia; the uptake of cationic probes by mltochondria in cultured heart ceils; and the junctional sarcoplasmic retlculum (JSR) in frog skeletal muscle.

Download Full-text