Book Chapter10.1007/978-3-319-62428-0_11
Neural-Network Based Algorithm for Algae Detection in Automatic Inspection of Underwater Pipelines
Edgar Medina,Mariane R. Petraglia,Jose Gabriel R. C. Gomes +2 more
- 23 Oct 2016
- pp 141-148
9
TL;DR: The algorithm comprises a neural network and a wavelet-based feature extractor that takes into account an appropriate algae texture description, as well as the neural network architecture that results in the optimal classifier performance.
read more
Abstract: Automatic inspection of underwater pipelines has been a growing challenge for the detection and classification of events, most often performed by Remotely Operated Vehicles (ROVs) and Autonomous Underwater Vehicles (AUVs). This article describes an algorithm for algae detection in underwater pipelines. The algorithm comprises a neural network and a wavelet-based feature extractor. Statistical parameters of the wavelet coefficients that take into account an appropriate algae texture description, as well as the neural network architecture that results in the optimal classifier performance, are selected. A post-processing algorithm, based on clustering of neighboring detection positions, was implemented to enhance the system response. The success rate of the resulting neural network classifier is 93.60%. When compared to support-vector machines (SVMs), the proposed classifier presents similar performance with the advantage of running significantly faster.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Machine Learning and Deep Learning Based Computational Approaches in Automatic Microorganisms Image Recognition: Methodologies, Challenges, and Developments
TL;DR: A systematic review of research done using machine learning (ML) and deep leaning techniques in image recognition of different microorganisms is presented in this paper, which investigates certain research questions to analyze the studies concerning image pre-processing, feature extraction, classification techniques, evaluation measures, methodological limitations and technical development over a period of time.
Pipeline tracking and event classification for an automatic inspection vision system
Felipe R. Petraglia,Roberto Campos,Jose Gabriel R. C. Gomes,Mariane R. Petraglia +3 more
- 01 May 2017
TL;DR: Algorithms designed to segment the pipelines and to classify some important events are described, including a deep convolutional neural network algorithm and a wavelet-based multilayer perceptron that outperforms the perceptron algorithm for different event classes and without requiring manual feature extraction.
41
Advances in Computational Intelligence
Grigori Sidorov,Oscar Herrera-Alcántara +1 more
- 01 Jan 2017
TL;DR: The results show that as a tendency the presence of the NE helps to classify, but there are specific authors when NE do not help and even make the classification worse (about 10% of experimental data).
19
Identifying Bacteria Species on Microscopic Polyculture Images Using Deep Learning
TL;DR: In this paper , a multi-label classification method based on multiple instance learning was proposed to further shorten the diagnosis time by analyzing polyculture images, which achieved an ROC AUC above 0.9.
•Dissertation
Classification of underwater pipeline events using deep convolutional neural networks
José Gabriel R. C. Gomes
- 28 Feb 2017
TL;DR: A inspecao automatica de dutos submarinos tem sido uma tarefa de crescente importância para a deteccao de diferentes tipos oficiais de eventos, dos quais destacam-se armadura exposta, presenca de algas, flanges e manta.
References
An Active Contour and Kalman Filter for Underwater Target Tracking and Navigation
Muhammad Asif,Mohd Rizal Arshad +1 more
- 01 Dec 2006
TL;DR: In this article, an AUV vision system is developed that can detect and track underwater installation such as oil or gas pipeline, and power or telecommunication cables for inspection and maintenance application.
Texture Image Classification Using Perceptual Texture Features and Gabor Wavelet Features
Muwei Jian,Lei Liu,Feng Guo +2 more
- 18 Jul 2009
TL;DR: Three new texture features which are proved to be in accordance with human visual perception are introduced and include directionality, contrast and coarseness in wavelet domain.
24
Pixel-based Classification Method for Detecting Unhealthy Regions in Leaf Images
Satish Madhogaria,Marek Schikora,Wolfgang Koch,Daniel Cremers +3 more
- 01 Jan 2011
TL;DR: A pixel-based, non-probabilistic classification algorithm for the automatic detection of unhealthy regions in leaf images based on a model plant, which forms the ideal basis for the usage of the proposed algorithm in biological researches concerning plant disease control mechanisms.
18
Rotation-invariant texture features extraction using Dual-Tree Complex Wavelet Transform
TL;DR: This paper proposes a new rotation invariant texture extraction technique using Principal Components Analysis (PCA) and Dual-Tree Complex Wavelet Transform (DT-CWT), and proves the approximate shift invariance, good directional selectivity; computational efficiency properties of DT-C WT make it a good candidate for representing the rotation-invariant texture features.
14
Improving Pedestrian Detection Using Support Vector Regression
Mounir Errami,Mohammed Rziza +1 more
- 01 Mar 2016
TL;DR: The use of basic statistical operators to adapt support vector regression (SVR) to binary classification and the obtained results prove the high performance of the proposed classification approach.
13