This paper provides a comprehensive review of existing works including the characteristics of Chi... more This paper provides a comprehensive review of existing works including the characteristics of Chinese characters ’ complex stroke crossing and challenges, which is still a largely unexplored subject for off-line text-independent Chinese handwriting identification.
Journal of Telecommunication, Electronic and Computer Engineering, 2017
This paper presents a method using retrieval mechanism along with Gray-Level Difference Method (G... more This paper presents a method using retrieval mechanism along with Gray-Level Difference Method (GLDM) feature extraction, an approach based on the textural features which is firstly introduced for off-line, text-independent Chinese writer identification. A widely used performance evaluation database HIT-MW has been used for conducting the experiment. An improvement in the identification rates has been revealed in the experimental evaluations by decreasing the search space using a writer retrieval mechanism prior to identification.
2020 6th International Conference on Interactive Digital Media (ICIDM), 2020
Digital watermarking is being used for increasing the level of effectiveness and security of the ... more Digital watermarking is being used for increasing the level of effectiveness and security of the documents transfer over the internet, especially in the biomedical field. This study examined and explored the new working domain for medical image watermarking by introducing a Dynamic Visibility Threshold (DVT) as a crossover from pure mathematics over the traditional fixed visibility threshold. Initially, for providing higher robustness against the watermarking attacks, the watermarking process is done on Slantlet Transform, an improved version of Discrete Wavelet Transform. By investigating the root of the medical image properties, we introduce the descriptive statistics namely Quantile Theory to deliver a dynamic value from the biomedical itself for the embedding process. Later, we had identified that the Third Quartile is the most optimum value for the DVT in terms of higher imperceptibility. This paper uses a standard dataset from BRAINIX, a medical database provided by OsiriX, Pixmeo SARL, and the effectiveness of the proposed method is analysed using MATLAB R2013a. The most obvious finding to emerge from this study is the convergence of descriptive statistics from pure mathematics and medical image watermarking from computer science, therefore shine new light on dynamic visibility threshold through mathematical theories. With the presence of descriptive statistics, quartile theory is being used to increase the imperceptibility of the watermarking in biomedical images.
This paper provides a comprehensive review of existing works including the characteristics of Chi... more This paper provides a comprehensive review of existing works including the characteristics of Chinese characters’ complex stroke crossing and challenges, which is still a largely unexplored subject for off-line text-independent Chinese handwriting identification.
2020 6th International Conference on Interactive Digital Media (ICIDM), 2020
Recent developments in writer identification have led new directions, which is writer identificat... more Recent developments in writer identification have led new directions, which is writer identification integrated with retrieval mechanism for boosting the performance applications of writer identification when a database is getting larger in size and retrieval of documents from expanding databases is becoming difficult. Issues on datasets used by previous studies directly impacts accuracy of the writer identification deteriorates as database size increases. Until now, in the research on writer identification researchers have been mainly interested in “writer identification without retrieval mechanism” approach. This paper provides a review on the state of the art for writer identification with retrieval mechanism throughout three major languages, namely English, Chinese, and Arabic. Up to date, truly little attention has been paid to the role of retrieval mechanism or documents in English language identification; the growth on Arabic and Chinese is far from satisfactory in comparison to its extensive usage. A search of the literature revealed few studies for writer identification with single retrieval mechanism. Seamless integration of such strategies in current forensic handwriting experience is yet unclear. A consistently reliable and efficient, fully automated writer recognition (AWR) and a powerful handwritten document retrieval system as an emerging technology are real challenging issues might be taken by upcoming researchers. It is still considered a fresh field and still has large room for research.
This paper provides a comprehensive review of existing works including the characteristics of Chi... more This paper provides a comprehensive review of existing works including the characteristics of Chinese characters ’ complex stroke crossing and challenges, which is still a largely unexplored subject for off-line text-independent Chinese handwriting identification.
Journal of Telecommunication, Electronic and Computer Engineering, 2017
This paper presents a method using retrieval mechanism along with Gray-Level Difference Method (G... more This paper presents a method using retrieval mechanism along with Gray-Level Difference Method (GLDM) feature extraction, an approach based on the textural features which is firstly introduced for off-line, text-independent Chinese writer identification. A widely used performance evaluation database HIT-MW has been used for conducting the experiment. An improvement in the identification rates has been revealed in the experimental evaluations by decreasing the search space using a writer retrieval mechanism prior to identification.
2020 6th International Conference on Interactive Digital Media (ICIDM), 2020
Digital watermarking is being used for increasing the level of effectiveness and security of the ... more Digital watermarking is being used for increasing the level of effectiveness and security of the documents transfer over the internet, especially in the biomedical field. This study examined and explored the new working domain for medical image watermarking by introducing a Dynamic Visibility Threshold (DVT) as a crossover from pure mathematics over the traditional fixed visibility threshold. Initially, for providing higher robustness against the watermarking attacks, the watermarking process is done on Slantlet Transform, an improved version of Discrete Wavelet Transform. By investigating the root of the medical image properties, we introduce the descriptive statistics namely Quantile Theory to deliver a dynamic value from the biomedical itself for the embedding process. Later, we had identified that the Third Quartile is the most optimum value for the DVT in terms of higher imperceptibility. This paper uses a standard dataset from BRAINIX, a medical database provided by OsiriX, Pixmeo SARL, and the effectiveness of the proposed method is analysed using MATLAB R2013a. The most obvious finding to emerge from this study is the convergence of descriptive statistics from pure mathematics and medical image watermarking from computer science, therefore shine new light on dynamic visibility threshold through mathematical theories. With the presence of descriptive statistics, quartile theory is being used to increase the imperceptibility of the watermarking in biomedical images.
This paper provides a comprehensive review of existing works including the characteristics of Chi... more This paper provides a comprehensive review of existing works including the characteristics of Chinese characters’ complex stroke crossing and challenges, which is still a largely unexplored subject for off-line text-independent Chinese handwriting identification.
2020 6th International Conference on Interactive Digital Media (ICIDM), 2020
Recent developments in writer identification have led new directions, which is writer identificat... more Recent developments in writer identification have led new directions, which is writer identification integrated with retrieval mechanism for boosting the performance applications of writer identification when a database is getting larger in size and retrieval of documents from expanding databases is becoming difficult. Issues on datasets used by previous studies directly impacts accuracy of the writer identification deteriorates as database size increases. Until now, in the research on writer identification researchers have been mainly interested in “writer identification without retrieval mechanism” approach. This paper provides a review on the state of the art for writer identification with retrieval mechanism throughout three major languages, namely English, Chinese, and Arabic. Up to date, truly little attention has been paid to the role of retrieval mechanism or documents in English language identification; the growth on Arabic and Chinese is far from satisfactory in comparison to its extensive usage. A search of the literature revealed few studies for writer identification with single retrieval mechanism. Seamless integration of such strategies in current forensic handwriting experience is yet unclear. A consistently reliable and efficient, fully automated writer recognition (AWR) and a powerful handwritten document retrieval system as an emerging technology are real challenging issues might be taken by upcoming researchers. It is still considered a fresh field and still has large room for research.
Uploads
Papers by Gloria Jennis Tan