SEMCOG: a hybrid object-based image database system and its modeling, language, and query processing

Author(s):  
Wen-Syan Li ◽  
K. Selcuk Candan
1999 ◽  
pp. 231-250 ◽  
Author(s):  
Vincent Oria ◽  
M. Tamer Özsu ◽  
Duane Szafron ◽  
Paul J. Iglinski

2012 ◽  
pp. 502-513
Author(s):  
Takeshi Toda ◽  
PaoMin Chen ◽  
Shinya Ozaki ◽  
Kazunobu Fujita ◽  
Naoko Ideguchi

In Japan, electronic health record systems are gradually becoming popular at large hospitals, but are not yet frequently implemented in clinics. This is due to both prohibitive costs and a lack of interest in checking electronic health records on the part of patients. Doctors also may be opposed to showing patients their health records, as it then may require a doctor to let patients observe images to check for improvement of symptoms at follow-up. In this study, the authors developed a database system of dermatological images accessible to both doctors and patients. In this system, doctors can photograph affected skin areas and tag the images with keywords, such as patient ID or name, disease or diagnosis, symptoms, affected bodily regions, and free wards. The images and keyword tags are transmitted to a database housed on an Internet server. The authors implemented this system on a smartphone for quick and easy access during medical examination and on a tablet terminal for patients to use while waiting in the clinic. Using the tablet terminal, a doctor and patient may check for improvement of symptoms together.


Author(s):  
Chengcui Zhang ◽  
Liping Zhou ◽  
Wen Wan ◽  
Jeffrey Birch ◽  
Wei-Bang Chen

Most existing object-based image retrieval systems are based on single object matching, with its main limitation being that one individual image region (object) can hardly represent the user’s retrieval target, especially when more than one object of interest is involved in the retrieval. Integrated Region Matching (IRM) has been used to improve the retrieval accuracy by evaluating the overall similarity between images and incorporating the properties of all the regions in the images. However, IRM does not take the user’s preferred regions into account and has undesirable time complexity. In this article, we present a Feedback-based Image Clustering and Retrieval Framework (FIRM) using a novel image clustering algorithm and integrating it with Integrated Region Matching (IRM) and Relevance Feedback (RF). The performance of the system is evaluated on a large image database, demonstrating the effectiveness of our framework in catching users’ retrieval interests in object-based image retrieval.


Author(s):  
Chengcui Zhang ◽  
Liping Zhou ◽  
Wen Wan ◽  
Jeffrey Birch ◽  
Wei-Bang Chen

Most existing object-based image retrieval systems are based on single object matching, with its main limitation being that one individual image region (object) can hardly represent the user’s retrieval target, especially when more than one object of interest is involved in the retrieval. Integrated Region Matching (IRM) has been used to improve the retrieval accuracy by evaluating the overall similarity between images and incorporating the properties of all the regions in the images. However, IRM does not take the user’s preferred regions into account and has undesirable time complexity. In this article, we present a Feedback-based Image Clustering and Retrieval Framework (FIRM) using a novel image clustering algorithm and integrating it with Integrated Region Matching (IRM) and Relevance Feedback (RF). The performance of the system is evaluated on a large image database, demonstrating the effectiveness of our framework in catching users’ retrieval interests in object-based image retrieval.


1990 ◽  
Author(s):  
Antonio Turtur ◽  
Mario Fantini ◽  
Franco Prampolini

PLoS ONE ◽  
2019 ◽  
Vol 14 (4) ◽  
pp. e0214720
Author(s):  
Hao Li ◽  
Yi-Cheng Tu ◽  
Bo Zeng

Sign in / Sign up

Export Citation Format

Share Document