Browsing by Author "Chang, Hsuan-Shao"

Now showing 1 - 2 of 2

A COLOR DIFFERENTIATED FUZZY C-MEANS (CDFCM) BASED IMAGE SEGMENTATION ALGORITHM
(2012)
Tsai, Min-Jen
;
Chang, Hsuan-Shao
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Image segmentation is a very important process in digital image/video processing and computer vision applications. It is often used to partition an image into separated parts for further processes. For some applications (i.e., concept-based image retrieval), a successful segmentation algorithm is necessary to identity the objects effectively. In addition, how to tag the objects after the segmentation associated with keywords is also a challenge for researchers. In this study, we proposed a color differentiated fuzzy c-means (CDFCM) framework for effective image segmentation to achieve segmented objects within image which is useful for further annotation. In our experiments, we compared our approach with other FCM techniques on synthetic image with excellent performance. Furthermore, CDFCM outperforms other approaches by using the Berkeley image segmentation data set with layered annotation, which can be applied for additional operations.
The Design of a Hybrid Feature Detector for Adult Images
(2013)
Tsai, Min-Jen
;
Chang, Hsuan-Shao
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Adult image detection is an important issue lately due to the parental control needs. Skin color detector is a typical solution for adult image detection. However, the performance needs to be improved due to the lack of color photo diversity. Even Bag-of-Visual-Words (BoVWs) approaches is another scheme to solve this problem, it is not easy to get efficient solution. In this paper, a hybrid feature detector for adult images is proposed. The method normalizes the local feature and global feature to become a hybrid feature which combines the benefits between BoVWs and skin-color-detector. Experimental results demonstrate that its computation time is shorter than the one of BoVWs technique and almost equivalent to the one of skin-color-detector. The most important fact of all is that the hybrid feature detector has achieved better accuracy ratio than the results by using BoVWs or skin-color-detector techniques.