This paper investigates using image registration through spatial transformation to incrementally improve eigenface detection in training sets containing non-centered head orientation. In identifying a new face, a training set of faces is created from a scene. After face detection in an image, these faces may exhibit different head orientations. The use of several images combined through image r...

College women enrolled in a strength training class were evaluated before and after the class using a combination of physical fitness measures, including weight, percentage of body fat, body circumference, and strength measures. Forty-nine subjects participated in strength training, twice a week for a total of 12 weeks. At the end of the class, participants were asked to respond to 9 open-ended...

We introduce EnhanceGAN, an adversarial learning based model that performs automatic image enhancement. Traditional image enhancement frameworks involve training separate models for automatic cropping or color enhancement in a fully-supervised manner, which requires expensive annotations in the form of image pairs. In contrast to these approaches, our proposed EnhanceGAN only requires weak supe...

Remarkable results have been obtained using image models based on image patches, for example sparse generative models for image inpainting, noise reduction and superresolution, sparse texture segmentation or texton models. In this paper we propose a powerful and yet simple approach for segmentation using dictionaries of image patches with associated label data. The approach is based on ideas fr...

A new method for feature extraction and recognition, namely the fuzzy bidirectional weighted sum criterion (FBWSC) is proposed in this paper. FBWSC defines the row directional fuzzy image optimal image projection matrix. Subsequently, each sample in the original training sample set is transformed using the row directional optimal image projection matrix, and the row directional feature training...

The task of image super-resolution is to up sample a low resolution (LR) image while recovering sharp edges and high frequency details. In this paper, a single image superresolution algorithm via canonical correlation analysis (CCA) is proposed. This method is based on the assumption that the corresponding LR and high resolution (HR) images have high correlation coefficients when transformed in...

Deep learning models have a large number of free parameters that must be estimated by efficient training of the models on a large number of training data samples to increase their generalization performance. In real-world applications, the data available to train these networks is often limited or imbalanced. We propose a sampling method based on the radial transform in a polar coordinate syste...

In previous work [2] we considered the problem of image interpolation from an adaptive optimal recovery point of view. We showed how a training set S determines a quadratic signal class and how to use this signal class to perform image interpolation. In [2] the training set S was taken from the low resolution version of the image we were interpolating. In this paper we continue our discussion o...

SMILE (Scanning Memory Image LatticE) is a lazy learning framework based on a memory image lattice scanning technique. To classify an unseen instance, the instances in the training set will generate a memory image lattice in terms of the similarities between the training instances and the unseen instance. An exploration algorithm of memory image lattice is designed to search an appropriate set ...