The paper tries to analyze the possibilities of classification of hemp fiber plant seeds in order to provide an image recognition sorting system that can estimate the quality of the fiber hemp seeds destined for human consumption. Systems that can optically grade cereal grains are already available in the agricultural industry. The automatic classification systems for seeds take in consideration the size, shape, color and texture in order to assess the quality of nutritional seeds.This work investigates the classification possibilities of image systems using photo images acquired by an RGB camera. The article presents the experimental stand and devices used for the image analysis of the fiber hemp seeds probes. The method for the selection of the representative pixels of the quality seeds is described and finally the results for the classification of the ratio of ripe seeds versus unripe seeds are presented in graphs. Conclusions are formulated and discussed.
The paper shows how closed-loop control procedure, using the algorithm Proportional Integrative derivative (PID) was applied to improve the photo and video cameras stability correction in real time. The stability system contains an Attitude Heading reference System (AHRS) sensor that is connected to a microcontroller that will make the operations for measuring angles of rotation (roll, pitch and yaw) acquired from a camera displaced on a suspended cable. Closed loop PID algorithm applied to stabilize the system was implemented as programming subroutines dedicated to Atmega162 microcontroller, at which they were recorded and processed in real time as input signals sensor information measured by the AHRS system. Programming based on a closed loop process control through actuators ordered 3 servo-motors for real-time correction of camera rotation angles. In this way it could be provided the positioning cameras error compensation, the errors being caused by different perturbing external factors. The adopted solution has achieved a cost reduction necessary to stabilize the cameras placed in mobile systems. The solution ensures also to increase the stabilization efficiency reported to the case of human operator intervention.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.