作者: Rupali Patil , Amrita Manjrekar
关键词:
摘要: The feature extraction-coding-pooling framework improves the performance of image classification because it generates robust and discriminative representation. proposed system uses saliency driven multi-scale nonlinear diffusion filtering with linear distance coding (LDC) method for classification. images at small, mid high scale concatenation information these scales produces using LDC. class manifolds generated by this are given as input to retrieval which finally retrieves all those relevant supplied image.