Biomedical subjects

T E Olson

Publications and source records attributed to T E Olson.

3 recordsLinked to original sources

PubMed2002

Modeling a parallel L4 neuron array of the fly (Musca domestica) vision system with a sequential processor.

At RMBS 2001 Olson presented a novel approach to image edge detection based on the vision system of the common house fly, Musca domestica [1]. Biologically based vision systems are inherently parallel and the vision related cells form a self-contained cartridge, ommatidium, which is duplicated across the surface of the fly's eye. Histological evidence provides the interconnection both within the vision cartridge and the connections to adjacent cartridges. Due to the parallel nature of biologically inspired vision systems, they outperform computer based digital vision systems in speed performance and memory requirements. Olson provided a model of the cartridge with its intra- and inter-connections. This model, rendered in MATLAB and Excel, demonstrated the feasibility of edge detection in the first several synaptic cellular connections within the cartridge. His results demonstrated how edge detection and object movements are easily obtained using a biologically based vision model. He demonstrated the model using simple rectangular and circular objects. We term this work Olson's Algorithm. We have extended Olson's Algorithm into a high-resolution model using a standard off-the-shelf frame grabber. Although, the frame grabber is a digitally based instrument, its image planes are used to model the photoreceptor layer (R1-R6), the L1, L2 monopolar cell layer, and also the monopolar L4 cell layer. The connections between these cells are programmed in "C". The high-resolution model demonstrates the feasibility of using a biologically based vision system in a real world application. Furthermore, it allows object segmentation, movement, and tracking to be modeled prior to implementation in parallel analog hardware.

Algorithms↗

PubMed2001

Utilizing image processing techniques to compute herbivory.

Leafy spurge (Euphorbia esula L. sensu lato) is a perennial weed species common to the north-central United States and southern Canada. The plant is a foreign species toxic to cattle. Spurge infestation can reduce cattle carrying capacity by 50 to 75 percent [1]. University of Wyoming Entomology doctoral candidate Vonny Barlow is conducting research in the area of biological control of leafy spurge via the Aphthona nigriscutis Foudras flea beetle. He is addressing the question of variability within leafy spurge and its potential impact on flea beetle herbivory. One component of Barlow's research consists of measuring the herbivory of leafy spurge plant specimens after introducing adult beetles. Herbivory is the degree of consumption of the plant's leaves and was measured in two different manners. First, Barlow assigned each consumed plant specimen a visual rank from 1 to 5. Second, image processing techniques were applied to "before" and "after" images of each plant specimen in an attempt to more accurately quantify herbivory. Standardized techniques were used to acquire images before and after beetles were allowed to feed on plants for a period of 12 days. Matlab was used as the image processing tool. The image processing algorithm allowed the user to crop the portion of the "before" image containing only plant foliage. Then Matlab cropped the "after" image with the same dimensions, converted the images from RGB to grayscale. The grayscale image was converted to binary based on a user defined threshold value. Finally, herbivory was computed based on the number of black pixels in the "before" and "after" images. The image processing results were mixed. Although, this image processing technique depends on user input and non-ideal images, the data is useful to Barlow's research and offers insight into better imaging systems and processing algorithms.

Algorithms↗

PubMed2001

Modeling the L4 neuron of the fly (Musca domestica) vision system.

Vision systems based on digital image processing techniques are limited in a variety of areas, particularly speed and memory. Contrast enhancement, image segmentation, object recognition, and object tracking require extensive processing. Biological vision systems drastically outperform computer based digital vision systems in these areas. The animal retina is composed of processing layers with specialized neural cells designed to enhance contrast, segment images, and even produce temporal information. In the vision system of the fly, Musca domestica, the L1, L2, and L4 monopolar cells are of particular interest. The photoreceptor terminals R1 through R6 and L1 and L2 form a cartridge with current shunting inhibition that enhances contrast at the first synaptic contact. L1 and L2 cells are thought to exaggerate contrast while also providing a data reduction encoding scheme to increase communication efficiency with L4 cells and the inner plexiform layer. Research conducted by the authors attempts to simulate the encoding scheme of L1, L2, and L4, and the interactions of these three monopolar cells. This paper proposes that L1 and L2 encode edge information and orientation related to a single cartridge via a sinusoidal modulation scheme. L4 mediates information processing between cartridges via three bi-directional dendritic communication with adjacent L4 cells. Finally, we propose that L4 also synthesizes and forwards the edge orientation information and image movement information to the medulla. A single cartridge simulation was conducted using Matlab. Simulation results will be compared to actual signals taken from the fly eye. Because the fly eye is modular, the goal of this research is to implement the L1, L2, and L4 cell function in analog hardware--the result being a real-time parallel analog vision system.

Animals↗