Energy aware fuzzy color segmentation algorithm - An application to criminal identification using mobile devices

被引：0
作者：
Department of Computer Science and Engineering, Manonmaniam Sundaranar University, Tirunelveli, Tamil Nadu 627 012, India [1 ]
机构：
[1] Department of Computer Science and Engineering, Manonmaniam Sundaranar University, Tirunelveli
来源：
Int. J. Wavelets Multiresolution Inf. Process. | 2008年 / 5卷 / 707-718期
关键词：
Feature extraction; Fuzzy modeling; Image segmentation; Information retrieval; Region of interest; Similarity measurements;
D O I：
10.1142/S0219691308002604
中图分类号：
学科分类号：
摘要：
Since its advent, the use of digital camera in mobile phones is getting more popular, where information retrieval based on visual appearance of an object is very useful when specific parameters for the object are not known. Though it is well-liked, it needs energy aware algorithms to carry out the various tasks such as segmentation and feature extraction. In this paper, a new energy aware fuzzy color segmentation algorithm is proposed and which has been applied for face segmentation in criminal identification using mobile devices. The criminals in the application are in three classes. They are New Criminal (NC), Suspected Criminal (SC) and Confirmed Criminal (CC). It is basically a mobile image-based content search engine that takes photographs of criminals as image queries and finds their relevant contents by matching them to the similar contents in the criminal databases. The energy aware fuzzy color segmentation is used to obtain the most significant parts of an image - facial regions of the persons and which are used in building image-based queries to the databases. Content search methodology in the application is also improved through the fuzzy modeling to make the application more flexible and simpler. Through the experiment conducted, it has been found that the proposed color segmentation algorithm is more robust and it reduces the computational time in searching process by minimizing the number of false cases. It could detect the faces in the images where the other known algorithms have failed to detect. © 2008 World Scientific Publishing Company.
引用
收藏
页码：707 / 718
页数：11
相关论文
共 15 条
  • [1] Mensa B., Briinig M., Segmentation of human faces in color images using connected operators, Proc. IEEE Int. Conf. Image Processing, ICIP'99, pp. 632-636, (1999)
  • [2] Chai D., Ngan K.N., Face segmentation using skin color map in videophone application, IEEE Trans. Circuits Syst. Vid. Tech, 9, 4, pp. 551-564, (1999)
  • [3] Gausemeier I., Et al., Development of a real time image based object recognition method for mobile AR-devices, Proc. 2nd Int. Conf. Computer Graphics, Virtual Reality, Visualization and Interaction, AFRIGRAPH '03, pp. 133-139, (2003)
  • [4] Li H., Forchheimer R., Location of face using color cues, Proc. Picture Coding Symposium, (1993)
  • [5] Torres H., Reutter J.Y., Lorente L., The importance of color information in face recognition, Proc. IEEE Conf. Image Processing, ICIP'99, pp. 627-631, (1999)
  • [6] Sobottka K., Pitas I., Looking for faces and facial features in color images, Pattern Recogn. Image Anal, 7, 1, pp. 36-40, (1997)
  • [7] Abdel-Mottaleb M., Elgammal A., Face detection in complex enviorments from color images, Proc. Conf. Image Processing, pp. 622-626, (1999)
  • [8] Yang M.H., Ahuja N., Detecting human faces in color image, Proc. Int. Conf. Image Processing 1998, pp. 127-139, (1998)
  • [9] Yang M.H., Kriegman D.J., Ahuja N., Detecting faces in images: A survey, Trans. Pattem Anal. Mach. Intell, 24, 1, pp. 34-58, (2002)
  • [10] Reinders M.J.T., Model adaptation for image coding, Delft University of Technology, Department of Electrical Engineering Theory Group, (1995)
12