Browsing by Author "Hsu, Chien-Lun"

Now showing 1 - 2 of 2

Digital Forensics for Printed Character Source Identification
(2016)
Tsai, Min-Jen
;
Hsu, Chien-Lun
;
Yin, Jin-Sheng
;
Yuadi, Imam
;
資訊管理與財務金融系註：原資管所+財金所
Even digital content is widely used nowadays, printed documents are still ubiquitously accepted and circulated. Therefore, identifying the printed character source is essential for criminal investigations to authenticate the digital copies of the printed documents. This study carefully examines the important statistical features from Gray Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Spatial filters, Wiener filter, and Gabor filter to identify the printer source for Chinese characters by using support vector machine (SVM) and decision fusion of feature selection. Even the subject of printed Chinese character source identification has been investigated, the proposed technique further expands the feature space which achieves superior experimental results and outperforms the techniques described in the literatures. Therefore, the methodology proposed in this study can accomplish high classification accuracy rate which show promising applications for real world digital forensics.
Japanese Character based Printed Source Identification
(2015)
Tsai, Min-Jen
;
Hsu, Chien-Lun
;
Yin, Jin-Sheng
;
Yuadi, Imam
;
資訊管理與財務金融系註：原資管所+財金所
Due to the advances of digital technology, digital contents are widely accepted all over the world. Since the criminal counterfeits and copyright infringement is still under study for the new digital media, there is an increasing need called digital forensics, which involves the collection and analysis of the original digital device, has become an important issue. This study offers a universal approach to extract the important statistical features from Gray Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Spatial filter, Wiener filter and Gabor filter to identify the printer source for Japanese characters. The average experimental results achieves high identification rate at 94.23% which is significantly superior to the existing known method of using GLCM at 77.31%. The result is also better than the technique for Chinese character identification method at 88.77%. This superior testing performance demonstrates that the proposed identification technique is very effective for Japanese character based source laser printer identification.