Jim parker - Profile on Academia.edu (original) (raw)

Papers by Jim parker

Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001

Randomness and Generative Art

International Journal of Innovative Research in Computer and Communication Engineering, 2020

Art in general can be thought of as a stochastic process. No two drawings or paintings are exactl... more Art in general can be thought of as a stochastic process. No two drawings or paintings are exactly alike, and cannot be as long as humans are involved. Generative art, the defining of an artwork using an algorithm, can result in very precise duplications of artworks but this is rarely interesting. Art is a human activity and artworks are a means of communication between humans, even in the generative domain. Adding randomness to a generative work makes it seem more human, and often more interesting. How much randomness should there be? What is the context of the random features? Why is randomness interesting? These things will be discussed, along with some ideas on how to use randomness as a tool in creating artworks.

A fast temporal compression/expansion algorithm for sampled audio

Proceedings of the 2007 conference on Future Play - Future Play '07, 2007

An algorithm for compressing or expanding the duration of an arbitrary sound is presented, in whi... more An algorithm for compressing or expanding the duration of an arbitrary sound is presented, in which the frequencies present in the sound are not changed by the process. This means that music can be slowed without changing the key, and that sped up or slowed down voices can still be recognized. The process can be performed in a small fraction

IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991

An approach to licence plate recognition

Proceedings of Visual Interface'97, 1997

... [5] genetic algorithm to find the license plate [6] output: bounding box with the best score ... more ... [5] genetic algorithm to find the license plate [6] output: bounding box with the best score (from GA) Each of these steps will be discussed in appropri-ate detail. 2. Pre-processing and edgedetection The first step converts an RGB image to a gray-level image, using the method ...

CHI '03 extended abstracts on Human factors in computer systems - CHI '03, 2003

IEEE Computer Graphics and Applications, 2009

The first course in Canada on Serious Game development was run at the University of Calgary as a ... more The first course in Canada on Serious Game development was run at the University of Calgary as a joint Fine Arts and Computer Science course. The assessment in the course was based on a project, and the game project used was a simulation of impaired driving called the 'Booze Cruise'. The game was designed in conjunction with the alcohol unit from the Calgary Police Service, and was intended to show how difficult it would be to drive while impaired. A huge media response occurred when the game was announced in October of 2007, including print, radio, and television both nationally and internationally. This is a summary of the design process for that game, relates the stages of development, and summarizes the response by the media, the University, and by NGOs.

This contest involved the running and evaluation of computer vision and pattern recognition techn... more This contest involved the running and evaluation of computer vision and pattern recognition techniques on different data sets with known groundtruth. The contest included three areas; binary shape recognition, symbol recognition and image $ow estimation. A package was made available for each area. Each package contained either real images with manual groundtruth or programs to generate data sets of ideal as well as noisy images with known groundtruth. They also contained programs to evaluate the results of an algorithm according to the given groundtruth. These evaluation criteria included the generation of confusion matrices, computation of the misdetection and false alarm rates and other peij4ormance measures suitable for the problems. This paper sumniarizes the data generation for each area and experimental results for a total of six participating algorithms.

processing and vision, video game technologies, and computer simulations. With a Ph.D. in Informa... more processing and vision, video game technologies, and computer simulations. With a Ph.D. in Informatics from the State University of Gent, Dr. Parker has taught computer science, art, and drama at the University of Calgary in Canada, where he is a full professor. He has more than 150 technical papers and four books to his credit, as well as video games such as the Booze Cruise, a simulation of impaired driving designed to demonstrate its folly, and a number of educational games. Jim lives on a small ranch near Cochrane, Alberta, Canada with family and a host of legged and winged creatures. vii

Computers in Physics, 1993

The computational technique known as simulated annealing, which originally was used to solve prob... more The computational technique known as simulated annealing, which originally was used to solve problems in combinatiorial optimization, can be quite effectively used to fit functions of many parameters to a set of data. This paper discusses the application of simulated annealing to the fitting of Moffat functions to crowded field star images. Overlapping star profiles can be fit simultaneously and missed stars can be located based on the χ 2 value of the fit, and the resulting functional model yields excellent photometric results. This method has been integrated into a photometry system which allows the user to select the accuracy of the results at the expense of time needed to perform the calculations.

Academia Letters, 2022

Because of the precision with which the computer hardware can draw and because of the prefect rep... more Because of the precision with which the computer hardware can draw and because of the prefect reproducibility of a computer algorithm, computer renderings are too good. One of the defining aspects of human art is its creation of a relative view of a scene. The human representation, including and perhaps especially, involving approximations and interpretations, is a more emotionally and aesthetically pleasing image. A small library for human-like primitives is described.

Here we describe a new technique for synthesizing sounds from samples, using the block spectral G... more Here we describe a new technique for synthesizing
sounds from samples, using the block spectral Gaussian
pyramid method originally devised for texture synthesis in
computer graphics.

Two approaches to setting programming assignments are compared , using actual assignment and solu... more Two approaches to setting programming assignments are compared , using actual assignment and solutions from two distinct CS102 lecture sections during the same semester. The complexity and effort represented by the solutions is compared using software engineering metrics, giving a measure of the effectiveness of the two assignment sets, and student performance in successor courses is also examined.

An enhanced reality user interface uses aspects of the real world and simulated computer percepti... more An enhanced reality user interface uses aspects of the real world and simulated computer perception to yield a simpliﬁed and natural user interface. Here we use the game of solitaire as the base application, and use hand gestures as input, in particular those that would be used if playing the game with real cards. Our output scheme uses audio, especially voice descriptions of cards and relative hand positions, in three dimensional sound. The result is a game that is playable by anyone using any flat surface with no actual cards and no need to touch or look at the computer. A large class of interfaces can profit from these ideas, and they allow visually impaired users expanded access to existing systems. A design parameter of the system is that the user need not touch the computer in order to play the game.

We explain the need for formal collaboration between stu- dents in the arts and computer science ... more We explain the need for formal collaboration between stu-
dents in the arts and computer science students, and argue that this should be encouraged at an early stage of their education. Two speciﬁc courses that foster this sort of cooperation are described.

Due to the variety of the artistic experience, and the quite
distinct natures of the different artistic media, computer science has not been a cooperative or understanding partner of the artist, and in turn artists have been hesitant and awkward about adopting digital media as a part of their daily work. Effective joint efforts between artists and computer scientists require a comprehension of the opportunities and problems in both sets of disciplines. We should offer computer science students the opportunity to work with artists in artistic endeavors at an early stage in their careers. We will thus create a new kind of graduate, one possessing an amalgam of the skill sets
from both ﬁelds. Where this may lead is impossible to tell,
except that it opens a range of possibilities that can’t be completely anticipated.

When analyzing handwritten signatures using a computer, a certain amount of variation within any ... more When analyzing handwritten signatures using a computer, a certain amount of variation within any particular class is to be expected. Successful recognition demands that this variation be less than that between two different signatures. This paper describes three simple ways to compare signatures that do not use any complicated or derivative feature measurements, each of which defines a distance between signatures that allows individual variation.

Signature verification using the shadow mask technique results in high success rates providing th... more Signature verification using the shadow mask technique results in high success rates providing the initial conditions are met, namely that signatures are written in a constant sized box provided for that purpose. In fact, the shadow mask algorithm implicitly uses scale as a feature, and this must be fixed if the method is to be used in a more general way.

Automating the process of pulp inspection has been attempted using off-line scanners and line sca... more Automating the process of pulp inspection has been attempted using off-line scanners and line scan equipment that examines the web. What is described here is a scheme that uses relatively simple image analysis methods and commonly available equipment.

The problem of classifying scientific data, in this case measurements from a respirometer, is add... more The problem of classifying scientific data, in this case measurements from a respirometer, is addressed. The use of shape and of multiple classification algorithms operating on the same data is addressed. The combination of many diverse methods increases the reliability of the classifier and should allow a wider variety of input data to be processed.

The use of prior behavior of a classiﬁer, as measured by the confusion matrix, can yield useful i... more The use of prior behavior of a classiﬁer, as measured
by the confusion matrix, can yield useful information for
merging multiple classiﬁers. In particular, a ranking of
possible classes can be produced which can allow
Borda type reconciliation methods to be applied. A sim-
ulation of multiple classiﬁers is used to evaluate this
idea, and compare with three other classiﬁer combina-
tion techniques.