Earticle

There are shortcomings in the currently used traditional CCD imaging system which can automatically recognize banknote image defect, such as the need to manually extract the defect characteristics and low accuracy rate of detection results. This paper briefly introduced the advantage of convolution Neural Network (CNN) in image classification and designed a image defect identification method based on convolutional neural network (CNN). The experimental results on data sets show that the identification accuracy rate of this method is 95.6%, which is significantly better than traditional identification method.

지폐는 반다공성의 지류로서 접힘과 마모로 인한 표면의 손상 가능성과 지폐 고유의 요철과 형 광물질이 포함된 특성으로 인하여 지문감식이 어려울 때가 있다. 이런 경우에는 광학적인 방법을 이용 하여 사진촬영 방법에 의존하지만 지폐의 형광 무늬들의 간섭 때문에 사진 촬영만으로는 만족할만한 지문정보를 얻기가 어렵다. 따라서 지폐에 유류된 잠재지문을 효과적으로 도출하기 위하여 자석 형광 분말을 이용하여 현출을 시도하였다. 또한, 형광사진촬영을 통하여 취득한 지문사진을 포토샵에서 색 상, 채도, 명도 그리고 흑백대비를 조절함으로써 보다 선명한 지문사진을 얻을 수 있었다. 이러한 지문 정보 개선방법은 기존의 형광사진 촬영방법과 포토샵 활용능력만으로도 누구나 쉽게 활용할 수 있으며 반다공성 특성을 가진 다른 증거물에도 적용이 가능하다.

Sometimes banknote is difficult to identify fingerprint on it. Owing to its characteristics like the damage of the surface because of folding and abrasion, unevenness, and containing fluorescent materials as semi-porous paper. In this case, it is required to depend on the photography using the optical method. However, because of the interference of fluorescent patterns on banknotes, it is hard to get the satisfactory fingerprint information only from the photography. Therefore, we used magnetic fluorescent powder in order to effectively develop the latent fingerprint on banknotes. By adjusting color, saturation, brightness, and contrast of black and white of the fingerprint photo acquired through the fluorescent photography in Photoshop, it has been improved to much clearer fingerprint photo. This type of methods to improve fingerprint information can be easily used by anyone who is aware of how to take the fluorescent photos and also to use photoshop. It can be also applied to other evidences showing the semi-porous characteristic.