An Objectionable Image Detection System Based on Region of Interest

Skin information combined saliency detection for classifying objectionable images

“…The center point of salient region is the centroid of saliency map and there is the relationship between the size of saliency region and the 1 st order central moment of saliency map [8]. Therefore, the size of salient region is calculated using the 1 st order central moment of saliency map as following equation: (4) where α is the constant, w' and h' are the 1 st order central moment of saliency map along the x and y direction respectively.…”

“…Figure 1. From left to right: input image, saliency map using the method presented by Achanta et al [8], skin information combined saliency map, results of our salient region detection.…”

Recent Advances in Region-of-interest Video Coding

“…The detecting results are stored in the memory layer, and help the perceptual layer to detect the temporal static objects. In addition, (Jeong, 2006) proposes an objectionable image detection system based on the R O I . T h e s y s t e m p r o p o s e d b y ( J e o n g , 2 0 0 6 ) e x c e l s i n t h a t R O I d e t e c t i o n m e t h o d i s specialized in objectionable image detection.…”

“…In addition, a novel feature consisting of weighted SCD based on ROI and skin color structure descriptor is presented for classifying objectionable image. Using the ROI detection method, (Jeong, 2006) can reduce the noisy information in image and extract more accurate features for classifying objectionable image. Further, (Lin et al, 2005) uses genetic programming (GP) to synthesize composite operators and composite features from combinations of primitive operations and primitive features for object detection.…”