Hitachi High-tech Corporation

Kentaro Ohira

Yasutaka Toyoda

Masayoshi Ishikawa

Masaki Hasegawa

Noriyuki Kaneoka

Katsunori Onuki

Tomohiko Ogata

Takefumi Kakinuma

Toshinori Yamauchi

According to the present invention, an image recognition system calculates importance of a feature for each target shape recognized in an image and for each type of feature, and determines correctness of a recognition result by comparing the importance with a statistic for each type of feature, for each target shape.

Image recognition system

It is necessary to guarantee performance by quantitatively evaluating the defect detection sensitivity of an inspection device for using the mirror electron image to detect defect in a semiconductor substrate. The size and position of accidentally formed defects are random, however, and this type of quantitative evaluation has been difficult. This semiconductor substratefor evaluation is for evaluating the defect detection sensitivity of an inspection device and comprises a plurality of first indentationsthat are formed through the pressing, with a first pressing load, of an indenter having a prescribed hardness and shape into the semiconductor substrate for evaluation. Further, a mirror electron image of the plurality of first indentations of the semiconductor substrate for evaluation is acquired, and the defect detection sensitivity of an inspection device is evaluated through the calculation of the defect detection rate of the plurality of first indentations in the acquired mirror electron image.

Semiconductor substrate for evaluation and method using same to evaluate defect detection sensitivity of inspection device

Growing community of inventors

Tokyo, Japan

Kentaro Ohira