In this paper we present a framework that allows for the automatic identification of sporting activities using commonly available smartphones. We extract discriminative informational features from smartphone accelerometers using the Discrete Wavelet Transform (DWT). Despite the poor quality of their accelerometers, smartphones were used as capture devices due to their prevalence in today's society. Successful classification on this basis potentially makes the technology accessible to both elite and non-elite athletes. Extracted features are used to train different categories of classifiers. No one classifier family has a reportable direct advantage in activity classification problems to date; thus we examine classifiers from each of the most widely used classifier families. We investigate three classification approaches; a commonly used SVM-based approach, an optimized classification model and a fusion of classifiers. We also investigate the effect of changing several of the DWT input parameters, including mother wavelets, window lengths and DWT decomposition levels. During the course of this work we created a challenging sports activity analysis dataset, comprised of soccer and field-hockey activities. The average maximum F-measure accuracy of 87% was achieved using a fusion of classifiers, which was 6% better than a single classifier model and 23% better than a standard SVM approach.

Abstract:The Fourier plane encryption algorithm is subjected to a known-plaintext attack. The simulated annealing heuristic algorithm is used to estimate the key, using a known plaintext-ciphertext pair, which decrypts the ciphertext with arbitrarily low error. The strength of the algorithm is tested by using this estimated key to decrypt a different ciphertext which was also encrypted using the same original key. We assume that the plaintext is amplitude-encoded real-valued image, and analyze only the mathematical algorithm rather than a real optical system that can be more secure. The Fourier plane encryption algorithm is found to be susceptible to a known-plaintext heuristic attack.

We perform a numerical analysis on the double random phase encryption͞decryption technique. The key-space of an encryption technique is the set of possible keys that can be used to encode data using that technique. In the case of a strong encryption scheme, many keys must be tried in any brute-force attack on that technique. Traditionally, designers of optical image encryption systems demonstrate only how a small number of arbitrary keys cannot decrypt a chosen encrypted image in their system. However, this type of demonstration does not discuss the properties of the key-space nor refute the feasibility of an efficient brute-force attack. To clarify these issues we present a key-space analysis of the technique. For a range of problem instances we plot the distribution of decryption errors in the key-space indicating the lack of feasibility of a simple brute-force attack.

This study examined perceptual differentiation of specular from diffuse shading for the recovery of surface color and gloss. In Experiment 1, we parametrically varied the mesoscale relief height of globally planar surfaces, specular sharpness and the orientation of the surface relative to the light source. We obtained psychophysical matches for perceived color saturation and value (HSV), but also considered whether the main effects could be influenced by color space used when transforming data to perceptually-uniform CIE LCH space. Results revealed strong interactions between perceived color attributes and the lighting conditions, the structure of specular reflections, and surface relief. Declines in saturation were observed with increasing specular roughness (using an HSV color representation), but no similar decline was observed in chroma (using a CIE LCH color representation). Experiment 2 found strong negative correlations between perceived gloss and specular roughness. Perceived gloss also depended on mesoscopic relief height and orientation of the surface relative to the light source. Declines in perceived gloss moderately accounted for the variability in color saturation and value matches obtained in Experiment 1. We found information about perceived specular coverage could further improve the model's accountability of perceived color saturation and lightness (Experiment 3). These findings together suggest that perceived color saturation and color value depends on the visual system's ability to distinguish the underlying diffuse shading from specular highlights in images.