RAMY Greeting Feature using HAAR cascade classifier and HOG Algorithm for Asia Pacific College
Abstract
Purpose –A self-maneuvering robot called RAMY will be installed in the lobby of the Asia Pacific College (APC) building. For guests at APC, as well as for professors, students, and visitors, RAMY will act as an information hub. information about the available courses, the cost of tuition, the location of the rooms, etc. The RAMY greeting function is the subject of this study. The welcome features employ facial detection and identification, and they greet the person if they are detected.
Method –The researchers made use of HAAR Cascade for facial detection, HOG algorithm for feature extraction and classification, and pyttsx3 for the text-to-speech greeting.
Results – The results showed that accuracy has a scale of good with 85.16%, reliability has a scale of poor with 87%, and robustness with an excellent with 3.45m. From the results, the greeting feature has a low performance on recognition rates but still works great at far distances.
Conclusion – The researchers conclude that the lighting on the faces has a significant impact on the rate of recognition. To greet someone, however, you don't need to be close to the RAMYbot because the greeting feature works over great distances.
Recommendations – While currently trained datasets are being delivered, training time can be decreased by using an approach that can retain pre-trained models.
Practical Implications – The software will lessen the interactions involving close physical contact for people who need to ask questions.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited.
