Search

The primary objective of this research study is to develop a mobile application that measures coffee bean moisture by using image processing, supervised learning, and computer imaging. Coffee beans must have moisture content between 10% and 12% to certify their quality. An image database is built, imaging protocols are defined, and an algorithm is developed and integrated into a mobile application that coffee growers can use. Testing and sampling is conducted using mid to lower end cell phones. The software is validated both in the laboratory and in the field, proving to be 99% efficient. The digital image app's acceptability is over 80% among coffee growers. It is concluded that machine learning processes can be adapted to solve coffee farming and agroindustry challenges. [ABSTRACT FROM AUTHOR]

In this paper we address the problem of automatic emotion recognition and classification through video. Nowadays there are excellent results focused on lab-made datasets, with posed facial expressions. On the other hand there is room for a lot of improvement in the case of 'in the wild' datasets, where light, face angle to the camera, etc. are taken into account. In these cases it could be very harmful to work with a small dataset. Currently, there are not big enough datasets of adequately labeled faces for the task. We use Generative Adversarial Networks in order to train models in a semi-supervised fashion, generating realistic face images in the process, allowing the exploitation of a big cumulus of unlabeled face images. [ABSTRACT FROM AUTHOR]

Copyright of CES Medicina is the property of Universidad CES and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)