Limits...
Intelligent foreign particle inspection machine for injection liquid examination based on modified pulse-coupled neural networks.

Ge J, Wang Y, Zhou B, Zhang H - Sensors (Basel) (2009)

Bottom Line: Proper mechanisms and improved spin/stop techniques are proposed to avoid the appearance of air bubbles, which increases the algorithms' complexity.Modified PCNN is adopted to segment the difference images, judging the existence of foreign particles according to the continuity and smoothness properties of their moving traces.Preliminarily experimental results indicate that the inspection machine can detect the visible foreign particles effectively and the detection speed, accuracy and correct detection rate also satisfying the needs of medicine preparation.

View Article: PubMed Central - PubMed

Affiliation: College of Electrical and Information Engineering, Hunan University, China; E-Mail: yaonan@hnu.cn (Y-N.W.).

ABSTRACT
A biologically inspired spiking neural network model, called pulse-coupled neural networks (PCNN), has been applied in an automatic inspection machine to detect visible foreign particles intermingled in glucose or sodium chloride injection liquids. Proper mechanisms and improved spin/stop techniques are proposed to avoid the appearance of air bubbles, which increases the algorithms' complexity. Modified PCNN is adopted to segment the difference images, judging the existence of foreign particles according to the continuity and smoothness properties of their moving traces. Preliminarily experimental results indicate that the inspection machine can detect the visible foreign particles effectively and the detection speed, accuracy and correct detection rate also satisfying the needs of medicine preparation.

No MeSH data available.


Illumination Styles: (a) Silhouette illumination. (b) Bottom light reflection illumination.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3297148&req=5

f6-sensors-09-03386: Illumination Styles: (a) Silhouette illumination. (b) Bottom light reflection illumination.

Mentions: Illumination is the key part in the inspection machine. Good illumination can improve the system's resolution and simplify the detection algorithms; otherwise thorny problems like random spots, overexposure etc. can be caused. To acquire high-definition, stable luminance images, LED lights are selected. For detection of black foreign particles like hair, carbide, a 2-D arrayed LED panel shown in Figure 6(a) is put behind of the bottle facing the camera. High-contrast images can be achieved because of the particles' obstruction of light. To detect white particles like glass fragments, a round condensing LED is installed underneath the bottle and a plastic blackboard standing behind, as shown in Figure 6(b). Reflected lights can reach the camera as the glass fragment falls. Sample images can be found in Figures 10 and Figure 11.


Intelligent foreign particle inspection machine for injection liquid examination based on modified pulse-coupled neural networks.

Ge J, Wang Y, Zhou B, Zhang H - Sensors (Basel) (2009)

Illumination Styles: (a) Silhouette illumination. (b) Bottom light reflection illumination.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3297148&req=5

f6-sensors-09-03386: Illumination Styles: (a) Silhouette illumination. (b) Bottom light reflection illumination.
Mentions: Illumination is the key part in the inspection machine. Good illumination can improve the system's resolution and simplify the detection algorithms; otherwise thorny problems like random spots, overexposure etc. can be caused. To acquire high-definition, stable luminance images, LED lights are selected. For detection of black foreign particles like hair, carbide, a 2-D arrayed LED panel shown in Figure 6(a) is put behind of the bottle facing the camera. High-contrast images can be achieved because of the particles' obstruction of light. To detect white particles like glass fragments, a round condensing LED is installed underneath the bottle and a plastic blackboard standing behind, as shown in Figure 6(b). Reflected lights can reach the camera as the glass fragment falls. Sample images can be found in Figures 10 and Figure 11.

Bottom Line: Proper mechanisms and improved spin/stop techniques are proposed to avoid the appearance of air bubbles, which increases the algorithms' complexity.Modified PCNN is adopted to segment the difference images, judging the existence of foreign particles according to the continuity and smoothness properties of their moving traces.Preliminarily experimental results indicate that the inspection machine can detect the visible foreign particles effectively and the detection speed, accuracy and correct detection rate also satisfying the needs of medicine preparation.

View Article: PubMed Central - PubMed

Affiliation: College of Electrical and Information Engineering, Hunan University, China; E-Mail: yaonan@hnu.cn (Y-N.W.).

ABSTRACT
A biologically inspired spiking neural network model, called pulse-coupled neural networks (PCNN), has been applied in an automatic inspection machine to detect visible foreign particles intermingled in glucose or sodium chloride injection liquids. Proper mechanisms and improved spin/stop techniques are proposed to avoid the appearance of air bubbles, which increases the algorithms' complexity. Modified PCNN is adopted to segment the difference images, judging the existence of foreign particles according to the continuity and smoothness properties of their moving traces. Preliminarily experimental results indicate that the inspection machine can detect the visible foreign particles effectively and the detection speed, accuracy and correct detection rate also satisfying the needs of medicine preparation.

No MeSH data available.