Image orientation detection requires high-level scene understanding. Humans use object recognition and contextual scene information to correctly orient images. In literature, the problem of image orientation detection is mostly confronted by using low-level vision features, while some approaches incorporate few easily detectable semantic cues to gain minor improvements. The vast amount of semantic content in images makes orientation detection challenging, and therefore there is a large semantic gap between existing methods and human behavior. Also, existing methods in literature report highly discrepant detection rates, which is mainly due to large differences in datasets and limited variety of test images used for evaluation. In this work, for the first time, we leverage the power of deep learning and adapt pre-trained convolutional neural networks using largest training dataset to-date for the image orientation detection task. An extensive evaluation of our model on different public datasets shows that it remarkably generalizes to correctly orient a large set of unconstrained images; it also significantly outperforms the state-of-the-art and achieves accuracy very close to that of humans. 1

Single image haze removal is a very challenging and ill-posed problem. The existing haze removal methods in literature, including the recently introduced deep learning methods, model the problem of haze removal as that of estimating intermediate parameters, viz., scene transmission map and atmospheric light. These are used to compute the haze-free image from the hazy input image. Such an approach only focuses on accurate estimation of intermediate parameters, while the aesthetic quality of the haze-free image is unaccounted for in the optimization framework. Thus, errors in the estimation of intermediate parameters often lead to generation of inferior quality haze-free images. In this paper, we present CANDY (Conditional Adversarial Networks based Dehazing of hazY images), a fully end-to-end model which directly generates a clean haze-free image from a hazy input image. CANDY also incorporates the visual quality of haze-free image into the optimization function; thus, generating a superior quality haze-free image. To the best of our knowledge, this is the first work in literature to propose a fully end-to-end model for single image haze removal. Also, this is the first work to explore the newly introduced concept of generative adversarial networks for the problem of single image haze removal. The proposed model CANDY was trained on a synthetically created haze image dataset, while evaluation was performed on challenging synthetic as well as real haze image datasets. The extensive evaluation and comparison results of CANDY reveal that it significantly outperforms existing state-of-theart haze removal methods in literature, both quantitatively as well as qualitatively.Both the authors are affiliated with Samsung R&D Institute India -Bangalore

No abstract

No abstract

Abstract-Being one of the most powerful and fastest way of communication, the popularity of email has led to untoward rise of email spam. Spam are unwanted and unsolicited messages and the subsequent rise of spam received by email users has become a serious security threat. Automatic filtering of spam emails, hence, is a promising and research worthy area whereupon extensive work has been reported about attempts to design machine learning based classifiers. Herein feature selection technique can be conveniently applied for developing efficient machine learning based classifiers. However, feature selection techniques provide a mechanism to identify suitable and relevant features (attributes) for any knowledge discovery task. The choice of selecting a suitable feature selection technique is always a key question of research. The present paper compares and discusses the effectiveness of two feature selection methods i.e. Chi-square and Info-gain on machine learning techniques namely Bayes algorithm, tree-based algorithm and support vector machine with a purpose to design a classifier for spam email filtering. The experiment is performed using 10-fold cross-validation and performance measures such as accuracy, precision, recall are used to compare the results.