Using Computer Vision System for Detecting Tiredness
Martínez Bolaños, Francisco (2015)
Lataukset:
Martínez Bolaños, Francisco
Metropolia Ammattikorkeakoulu
2015
All rights reserved
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-201603293624
https://urn.fi/URN:NBN:fi:amk-201603293624
Tiivistelmä
The purpose of the thesis is to demonstrate an application of computer vision systems which are useful nowadays, especially in face recognition. Computer vision systems is a big field with multiple applications. We can compare image processing from its beginning when a camera looks at an image and end with the final processed image with human beings looking at an object and later in both human and machines, using that image, processed in the machines, for recognition of reality.
The reality is perceiving in our minds, through eyes. This process is also happening in the virtual reality of the artificial neurons. It is necessary to develop algorithms for “teaching” the computer system how to see and to act, giving us useful service. For face recognition the Haar Cascades is used with the OpenCV and EMGU libraries, both open source, with the Windows Visual Studio 2013.
Finally, we have to validate all, and if not good, to change it in brief all we must follow a research method. A confusion matrix will give us the accuracy in order to achieve the validation of the program The results of face detection and recognitions were successful.
The reality is perceiving in our minds, through eyes. This process is also happening in the virtual reality of the artificial neurons. It is necessary to develop algorithms for “teaching” the computer system how to see and to act, giving us useful service. For face recognition the Haar Cascades is used with the OpenCV and EMGU libraries, both open source, with the Windows Visual Studio 2013.
Finally, we have to validate all, and if not good, to change it in brief all we must follow a research method. A confusion matrix will give us the accuracy in order to achieve the validation of the program The results of face detection and recognitions were successful.