-There are distinction between supervised ANN and unsupervised ANN for feature extraction. For supervised ANN information loss can be measured on predicted output variable as in supervised learning the learning set is given to computer. While in unsupervised ANN information loss not measured as any learning labels not provided to computer. Both supervised ANN and unsupervised ANN feature extraction methods have advantages as compared to Principal Component Analysis (PCA). ANNs are applicable for wide variety of problems and relatively easy to use. The Image processing is processing of an image using mathematical operations. In image processing image is taken as input and as output processed image or set of parameters related to image are given. Image processing follows sequence of steps like image acquisition, input pre-processing, image segmentation, feature extraction, classification, recognition and post-processing. So, ANN as classifier is used for classification stage. Arrange ANN architecture into layer is referred as MLP. MLP consist of input layer, hidden layers and output layer. Hidden layers neurons must be in between number of input layer neurons and output layer neurons.
Article Details
Unique Paper ID: 144132
Publication Volume & Issue: Volume 3, Issue 7
Page(s): 54 - 59
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024