Robust image registration based on feedforward neural networks

Abstract

A novel approach to accurate and robust image registration using feedforward neural networks is presented. Common registration schemes utilize some form of similarity measures in order to evaluate affine transformation parameters. In the proposed scheme, feedforward neural networks are employed as means of providing translation, rotation and scaling parameters with respect to reference and observed image sets. Discrete Cosine Transform (DCT) features are extracted as inputs to the network. Experimental results with several deformed and noisy images indicate that the proposed algorithm is both accurate and remarkably robust to diverse noisy conditions.

Isomap and Neural Networks Based Image Registration Scheme

“…In another experiment, we compare the proposed method with the other methods in reference [1] and [2] under different noisy conditions. In the proposed method, we choose d=10 .While in Zernike moment-based method, d=58 and 17 hidden neurons, and in DCT-based method, d=64 and 18 hidden neurons.…”

“…Recently, Itamar Ethanany [1] proposed to use feedforward neural network (FNN) to register an attacked image through 144 Discrete Cosine Transform (DCT) -base band coefficients as the feature vector. But this method has too large lumber of input feature vectors for the un-orthogonality of DCT based space thus expose low computational efficiency and high requirements on computer performance.…”

Two-Dimensional PCA Combined with PCA for Neural Network Based Image Registration

“…Recently, Itamar Ethanany [2] proposed to use feedforward neural network (FNN) to register a distorted image through 144 Discrete Cosine Transform (DCT) -base band coefficients as the feature vector. But this method has too large lumber of input feature vectors for the un-orthogonality of DCT based space, thus expose low computational efficiency and high requirements on computer performance.…”

Efficient and accurate image alignment using TSK-type neuro-fuzzy network with data-mining-based evolutionary learning algorithm

“…Such methods demonstrated high alignment speed since it only needs to feed the extracted feature vectors into the trained neural network to estimate the transformation parameters. For example, Ethanany et al [1] presented a feedforward neural network (FNN) to align images through 144 discrete cosine transform (DCT) coefficients as the feature vectors. Their study showed that the FNN demonstrated high tolerance in deformed and noisy images.…”

“…Thus, it raises a challenge to provide an efficient affine transformation. To this end, neural network-based methods have widespread to address this challenge because such methods often feed global features of inspected images into a trained neural network to estimate affine transformation parameters [1][2][3][4]. In other words, neural networks are helpful for designing image alignment systems.…”