Open Science Research Excellence

M Morri

Publications

4

Publications

4
4195
Usability Evaluation Framework for Computer Vision Based Interfaces
Abstract:
Human computer interaction has progressed considerably from the traditional modes of interaction. Vision based interfaces are a revolutionary technology, allowing interaction through human actions, gestures. Researchers have developed numerous accurate techniques, however, with an exception to few these techniques are not evaluated using standard HCI techniques. In this paper we present a comprehensive framework to address this issue. Our evaluation of a computer vision application shows that in addition to the accuracy, it is vital to address human factors
Keywords:
Usability evaluation, cognitive walkthrough, think aloud, gesture recognition.
3
6842
Combining Skin Color and Optical Flow for Computer Vision Systems
Abstract:
Skin color is an important visual cue for computer vision systems involving human users. In this paper we combine skin color and optical flow for detection and tracking of skin regions. We apply these techniques to gesture recognition with encouraging results. We propose a novel skin similarity measure. For grouping detected skin regions we propose a novel skin region grouping mechanism. The proposed techniques work with any number of skin regions making them suitable for a multiuser scenario.
Keywords:
Bayesian tracking, chromaticity space, optical flowgesture recognition
2
10000538
Mean Velocity Modeling of Open-Channel Flow with Submerged Rigid Vegetation
Abstract:

Vegetation affects the mean and turbulent flow structure. It may increase flood risks and sediment transport. Therefore, it is important to develop analytical approaches for the bed shear stress on vegetated bed, to predict resistance caused by vegetation. In the recent years, experimental and numerical models have both been developed to model the effects of submerged vegetation on open-channel flow. In this paper, different analytic models are compared and tested using the criteria of deviation, to explore their capacity for predicting the mean velocity and select the suitable one that will be applied in real case of rivers. The comparison between the measured data in vegetated flume and simulated mean velocities indicated, a good performance, in the case of rigid vegetation, whereas, Huthoff model shows the best agreement with a high coefficient of determination (R2=80%) and the smallest error in the prediction of the average velocities.

Keywords:
Analytic Models, Comparison, Mean Velocity, Vegetation.
1
10005964
The Determination of Aflatoxins in Paddy and Milled Fractions of Rice in Guyana: Preliminary Results
Abstract:

A survey was conducted in the five rice-growing regions in Guyana to determine the presence of aflatoxins in multiple fractions of rice in June/October 2015 growing season. The fractions were paddy, steamed paddy, cargo rice, white rice and parboiled rice. Samples were analyzed by High Performance Liquid Chromatography. A subset of the samples was further analyzed by enzyme-linked immunosorbent assay (ELISA) for concurrence. All analyses were conducted at the University of Missouri, USA. Of the 186 samples tested, 16 had aflatoxin concentrations greater than 20 ppb the recommended limit for aflatoxins in food according to the United States Food and Drug Administration. An additional three samples had aflatoxin B1 concentrations greater than the European Union Commission maximum levels for aflatoxin B1 in rice at 5 µg/kg and total aflatoxins (B1, B2, G1 and G2) at 10 µg/kg. The survey indicates that there is no widespread aflatoxin problem in rice in Guyana. The incidence of aflatoxins appears to be localized.

Keywords:
Aflatoxins, enzyme-linked immunosorbent assay, high-performance liquid chromatography, rice fractions.