Search

Your search keyword '"Karl Thurnhofer-Hemsi"' showing total 3 results
Start Over Author "Karl Thurnhofer-Hemsi" Publisher springer
3 results on '"Karl Thurnhofer-Hemsi"'

1. Optimization of Convolutional Neural Network ensemble classifiers by Genetic Algorithms

Author

Cristian Accino, Ezequiel López-Rubio, Miguel A. Molina-Cabello, and Karl Thurnhofer-Hemsi

Subjects
business.industry, Computer science, Quantitative Biology::Tissues and Organs, Deep learning, 0206 medical engineering, Image processing, 02 engineering and technology, Machine learning, computer.software_genre, 020601 biomedical engineering, Convolutional neural network, medical image processing, Task (project management), Set (abstract data type), ComputingMethodologies_PATTERNRECOGNITION, Genetic algorithm, convolutional neural networks, 0202 electrical engineering, electronic engineering, information engineering, Benchmark (computing), 020201 artificial intelligence & image processing, Breast cancer classification, Artificial intelligence, business, computer
Abstract

Breast cancer exhibits a high mortality rate and it is the most invasive cancer in women. An analysis from histopathological images could predict this disease. In this way, computational image processing might support this task. In this work a proposal which employes deep learning convolutional neural networks is presented. Then, an ensemble of networks is considered in order to obtain an enhanced recognition performance of the system by the consensus of the networks of the ensemble. Finally, a genetic algorithm is also considered to choose the networks that belong to the ensemble. The proposal has been tested by carrying out several experiments with a set of benchmark images. Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.

Published
2019

2. Blood Cell Classification Using the Hough Transform and Convolutional Neural Networks

Author

Miguel A. Molina-Cabello, María Jesús Rodríguez-Espinosa, Karl Thurnhofer-Hemsi, Ezequiel López-Rubio, and Rafael Marcos Luque-Baena

Subjects
0301 basic medicine, Artificial neural network, Disease detection, Computer science, business.industry, Deep learning, Blood cell classification, Células sanguíneas - Clasificación, Pattern recognition, Image processing, Convolutional neural network, Hough transform, law.invention, Circle Hough transform, 03 medical and health sciences, Redes neuronales (Informática), 030104 developmental biology, 0302 clinical medicine, law, 030220 oncology & carcinogenesis, Blood cell detection, Convolutional neural networks, Artificial intelligence, business
Abstract

https://doi.org/10.1007/978-3-319-77712-2_62 The detection of red blood cells in blood samples can be crucial for the disease detection in its early stages. The use of image processing techniques can accelerate and improve the effectiveness and efficiency of this detection. In this work, the use of the Circle Hough transform for cell detection and artificial neural networks for their identification as a red blood cell is proposed. Specifically, the application of neural networks (MLP) as a standard classification technique with (MLP) is compared with new proposals related to deep learning such as convolutional neural networks (CNNs). The different experiments carried out reveal the high classification ratio and show promising results after the application of the CNNs. Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.

Published
2018

3. Vehicle Type Detection by Convolutional Neural Networks

Author

Karl Thurnhofer-Hemsi, Rafael Marcos Luque-Baena, Miguel A. Molina-Cabello, and Ezequiel López-Rubio

Subjects
Vehicle tracking system, Computer science, 02 engineering and technology, Machine learning, computer.software_genre, Convolutional neural network, Probabilistic self-organizing maps, 0202 electrical engineering, electronic engineering, information engineering, Range (statistics), Image resolution, Background features, Foreground detection, business.industry, Background modeling, 020206 networking & telecommunications, Pattern recognition, Performance results, Task (computing), Redes neuronales (Informática), 020201 artificial intelligence & image processing, Convolutional neural networks, Artificial intelligence, business, Vehicle type, computer
Abstract

In this work a new vehicle type detection procedure for traffic surveillance videos is proposed. A Convolutional Neural Network is integrated into a vehicle tracking system in order to accomplish this task. Solutions for vehicle overlapping, differing vehicle sizes and poor spatial resolution are presented. The system is tested on well known benchmarks, and multiclass recognition performance results are reported. Our proposal is shown to attain good results over a wide range of difficult situations. Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.

Published
2017

Catalog

Books, media, physical & digital resources
See catalog results