Search results

The purpose of this paper is to apply an on‐line automatic inspection and measurement of surface defect of thin‐film transistor liquid‐crystal display (TFT‐LCD) panels in the polyimide coating process with a modified template matching method and back propagation neural network classification method.

By using the technique of searching, analyzing, and recognizing image processing methods, the target pattern image of TFT‐LCD cell defects can be obtained.

With template match and neural network classification in the database of the system, the program judges the kinds of the target defects characteristics, finds out the central position of cell defect, and analyzes cell defects.

The recognition speed becomes faster and the system becomes more flexible in comparison to the previous system. The proposed method and strategy, using unsophisticated and economical equipment, is also verified. The proposed method provides highly accurate results with a low‐error rate.

In terms of sample training, the principles of artificial neural network were used to train the sample detection rate. In sample analysis, character weight was implemented to filter the noise so as to enhance discrimination and reduce detection.

The paper describes how pre‐inspection image processing was utilized in collaboration with the system to excel the inspection efficiency of present machines as well as for reducing system misjudgment. In addition, the measure for improving cell defect inspection can be applied to production line with multi‐defects to inspect and improve six defects simultaneously, which improves the system stability greatly.

The purpose of this paper is to present an automatic inspection and control method for a reagent rapid test strip production system, with image processing techniques.

Fluorescence, color arrangement and combination matching with the database were used to identify the responses of biochemicals. The position accuracy and insufflation consistency between the control line and test line on a reagent rapid test strip will be analyzed from the image after series processing.

The system can identify failed products and regulate production conditions to insure that the quality standard is maintained. The idea edges of the control line and test line are the boundary at which a significant change occurs in the surface reflectance and illumination of the viewer. But the change of the real boundary of the test line may be insufficient for identification.

As the illumination of biological reagent images cannot be measured precisely in the production process, and the intensity of the background light source is difficult to control, there are always significant errors in the production process. If the environment at sampling could be precisely controlled, the accuracy of the system could be enhanced.

This study developed software architecture for a biological reagent production and inspection system. Future studies will focus on the implementation of testing, and improvement of the system, so that it can be applied to medical systems for the benefit of all patients.