Cellular Automata is significantly applying to image processing operations. The description about the use of training of cellular automata for filtering the salt and pepper noise in binary images is given by this paper. The selection of best rule set has been performed on the basis of objective function peak signal to noise ratio values between original and filtered image. The proposed method i...

We consider the problem of correcting misclassifications in images by using context based or spatial information. We describe a graph-based method for correcting misclassifications that occur in primary local image recognition. The proposed method is applied in a training-based optimization framework, using genetic algorithms. Numerical simulation results are presented to confirm that once the ...

Example-based super-resolution is an image interpolation algorithm which uses a database of training images to create plausible high-frequency details in zoomed images [Freeman et al. 2002]. The algorithm is fairly simple, however its performance heavily depends on the database. In particular, when the characteristics of a target image to be magnified are different from the training images, the...

A natural solution for one-shot learning is to augment training data to handle the data deficiency problem. However, directly augmenting in the image domain may not necessarily generate training data that sufficiently explore the intra-class space for one-shot classification. Inspired by the recent vocabulary-informed learning, we propose to generate synthetic training data with the guide of th...

We present another set of experiments conducted on the widely used IAPRTC-12 [6] dataset. We use the same tag annotation and image training-test split as described in [7] for our experiments. There are 291 unique tags and 19627 images in IAPRTC12. The dataset is split to 17341 training images and 2286 testing images. We further separate 15% from the training images as our validation set. Table ...

Machine learning techniques have facilitated image retrieval by automatically classifying and annotating images with keywords. Among them Support Vector Machines (SVMs) are used extensively due to their generalization properties. However, SVM training is notably a computationally intensive process especially when the training dataset is large. In this thesis distributed computing paradigms have...

Adversarial training has proved to be competitive against supervised learning methods on computer vision tasks. However, studies have mainly been confined to generative tasks such as image synthesis. In this paper, we apply adversarial training techniques to the discriminative task of learning a steganographic algorithm. Steganography is a collection of techniques for concealing the existence o...