No abstract

No abstract

In epidemic situations such as the novel coronavirus (COVID-19) pandemic, face masks have become an essential part of daily routine life. The face mask is considered as a protective and preventive essential of everyday life against the coronavirus. Many organizations using a fingerprint or card-based attendance system had to switch towards a face-based attendance system to avoid direct contact with the attendance system. However, face mask adaptation brought a new challenge to already existing commercial biometric facial recognition techniques in applications such as facial recognition access control and facial security checks at public places. In this paper, we present a methodology that can enhance existing facial recognition technology capabilities with masked faces. We used a supervised learning approach to recognize masked faces together with in-depth neural network-based facial features. A dataset of masked faces was collected to train the Support Vector Machine classifier on state-of-the-art Facial Recognition Feature vector. Our proposed methodology gives recognition accuracy of up to 97% with masked faces. It performs better than exiting devices not trained to handle masked faces.

No abstract

Agrochemicals, which are very efficacious in protecting crops, also cause environmental pollution and pose serious threats to farmers' health upon exposure. In order to cut down the environmental and human health risks associated with agrochemical application, there is a need to develop intelligent application equipment that could detect and recognize crops/weeds, and spray precise doses of agrochemical at the right place and right time. This paper presents a machine-learning based crop/weed detection system for a tractor-mounted boom sprayer that could perform site-specific spraying on tobacco crop in fields. An SVM classifier with a carefully chosen feature combination (texture, shape, and color) for tobacco plant has been proposed and 96% classification accuracy has been achieved. The algorithm has been trained and tested on a real dataset collected in local fields with diverse changes in scale, orientation, background clutter, outdoor lighting conditions, and variation between tobacco and weeds. Performance comparison of the proposed algorithm has been made with a deep learning based classifier (customized for real-time inference). Both algorithms have been deployed on a tractor-mounted boom sprayer in tobacco fields and it has been concluded that the SVM classifier performs well in terms of accuracy (96%) and real-time inference (6 FPS) on an embedded device (Raspberry Pi 4).