Dimensionality Reduction and Reconstruction using Mirroring Neural Networks and Object Recognition based on Reduced Dimension Characteristic Vector

Details Dimensionality Reduction and Reconstruction using Mirroring Neural Networks and Object Recognition based on Reduced Dimension Characteristic Vector Dimensionality Reduction and Reconstruction using Mirroring Neural Networks and Object Recognition based on Reduced Dimension Characteristic Vector

2007-12-06

arxiv.org/abs/0712.0932v1

IEEE International Conference On Advances in Computer Vision and Information Tech. (IEEE, ACVIT-07), pp. 348 - 353 (2007)

Computer Science

Computer Vision and Pattern Recognition

Presented in IEEE International Conference on Advances in Computer Vision and Information Technology (ACVIT-07), Nov. 28-30 20

Scientific paper

In this paper, we present a Mirroring Neural Network architecture to perform non-linear dimensionality reduction and Object Recognition using a reduced lowdimensional characteristic vector. In addition to dimensionality reduction, the network also reconstructs (mirrors) the original high-dimensional input vector from the reduced low-dimensional data. The Mirroring Neural Network architecture has more number of processing elements (adalines) in the outer layers and the least number of elements in the central layer to form a converging-diverging shape in its configuration. Since this network is able to reconstruct the original image from the output of the innermost layer (which contains all the information about the input pattern), these outputs can be used as object signature to classify patterns. The network is trained to minimize the discrepancy between actual output and the input by back propagating the mean squared error from the output layer to the input layer. After successfully training the network, it can reduce the dimension of input vectors and mirror the patterns fed to it. The Mirroring Neural Network architecture gave very good results on various test patterns.

Affiliated with

Also associated with

No associations

Rating

Dimensionality Reduction and Reconstruction using Mirroring Neural Networks and Object Recognition based on Reduced Dimension Characteristic Vector does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Dimensionality Reduction and Reconstruction using Mirroring Neural Networks and Object Recognition based on Reduced Dimension Characteristic Vector, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Dimensionality Reduction and Reconstruction using Mirroring Neural Networks and Object Recognition based on Reduced Dimension Characteristic Vector will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-91873