Title :
Detection Model of Knotty Erotic Image
Author :
Li Yonggang ; Yin Haiming
Author_Institution :
Dept. of Comput. Sci. & Technol., Jiaxing Univ., Jiaxing, China
Abstract :
Detection model of knotty erotic image is designed to detect special erotic image, such as nude chat image and advertising prostitution image, which are difficulty identified by conventional algorithm. Text information and skin-color information are detected in the image detection windows set according to the characteristic of images. The classification of the images is determined according to the detection result in the detection windows and the position relationship of the detection windows. Experimental results demonstrate that the model can obtain good results in detecting special erotic image.
Keywords :
image classification; image colour analysis; object detection; image characteristic; image classification; image detection windows set; knotty erotic image; nude chat image; position relationship; prostitution image advertisement; skin-color information; text information; Advertising; Computational modeling; Databases; Feature extraction; Image color analysis; Image recognition; Skin; Chaos-RBF Neural Network; Identification; Oil Film Parameter; Transient Conditions;
Conference_Titel :
Intelligent Systems Design and Engineering Applications, 2013 Fourth International Conference on
Conference_Location :
Zhangjiajie
Print_ISBN :
978-1-4799-2791-3
DOI :
10.1109/ISDEA.2013.466
