TY - GEN

T1 - Distributed system for detection of biological contaminants

AU - Grishkin, Valery

AU - Smirnov, Konstantin

AU - Stepenko, Nikolai

PY - 2016

Y1 - 2016

N2 - The paper proposes a distributed system for detecting the types of biological contaminants existing on objects' surfaces. The system implements biofouling detection method based on an image processing technique. The system processes a series of object images obtained in the visible and near infrared spectral ranges. One image in the series is marked as a base imag e. All images of the series are converted to one common shooting point and to one common angle. The object of interest is detected in the base image, and then the background is removed from all images. To recognize the type of biological contaminants, we use a pre-trained classifier based on support vector machine method. The proposed detection method has an obvious parallelism in data processing. Each image in the series, except the base, can be processed independently. Therefore it is quite easy to implement this method on a computing cluster. The central host of the cluster is used to implement non-parallel branches of the image-processing algorithm. These branches are namely interactive segmentation, a search for key points in the base image, and classifier training. The central host also solves the problems of data distribution among cluster nodes and of synchronization of nodes. Other nodes of a cluster are processing other images in a series, except the base image. They implement a search for key points, convert all images to a common shooting point, remove the background, and identify types of biofouling. After processing, we form the map of pollution for each image. This map then gets sent to the storage at the central node of the cluster.

AB - The paper proposes a distributed system for detecting the types of biological contaminants existing on objects' surfaces. The system implements biofouling detection method based on an image processing technique. The system processes a series of object images obtained in the visible and near infrared spectral ranges. One image in the series is marked as a base imag e. All images of the series are converted to one common shooting point and to one common angle. The object of interest is detected in the base image, and then the background is removed from all images. To recognize the type of biological contaminants, we use a pre-trained classifier based on support vector machine method. The proposed detection method has an obvious parallelism in data processing. Each image in the series, except the base, can be processed independently. Therefore it is quite easy to implement this method on a computing cluster. The central host of the cluster is used to implement non-parallel branches of the image-processing algorithm. These branches are namely interactive segmentation, a search for key points in the base image, and classifier training. The central host also solves the problems of data distribution among cluster nodes and of synchronization of nodes. Other nodes of a cluster are processing other images in a series, except the base image. They implement a search for key points, convert all images to a common shooting point, remove the background, and identify types of biofouling. After processing, we form the map of pollution for each image. This map then gets sent to the storage at the central node of the cluster.

KW - Biofouling identification

KW - Parallel image processing

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=85016178483&partnerID=8YFLogxK

M3 - Conference contribution

T3 - CEUR Workshop Proceedings

SP - 245

EP - 249

BT - Distributed Computing and Grid-technologies in Science and Education 2016

PB - RWTH Aahen University

T2 - 7th International Conference Distributed Computing and Gridtechnologies in Science and Education, GRID 2016

Y2 - 4 July 2016 through 9 July 2016

ER -