لخّصلي

Computer vision systems are already widely employed in different
segments of agricultural production and industrial food production.It was identified that there are gaps to be filled with the develop-
ment of intelligent devices that use computer vision and artificial in-
telligence for automation of tasks in the field, as well as their integra-
tion with agricultural machines and drones.Finally, our intention that this survey would present diverse appli-
cations and techniques of machine learning, image and video proces-
sing in order to motivate more researchers to apply them for solving
agricultural problems currently open.Wheat, oat and barley cultivars, for instance,
could benefit from a computer system that aims to reduce complexity
and costs in the gluten-containing grains classification from images.Referen

Computer vision systems are already widely employed in different
segments of agricultural production and industrial food production.
They can be used in grading systems for orange, papaya, almond, po-
tato, lemon, wheat, corn, rice, and soybean. Its use is justifiable due to
the benefits obtained. The use of such systems provides a simple and
objective analysis of the samples, producing accurate descriptive data.
Through these systems it is possible to automate laborious tasks, in a
non-destructive way, producing adequate data for future analysis.
It was identified that there are gaps to be filled with the develop-
ment of intelligent devices that use computer vision and artificial in-
telligence for automation of tasks in the field, as well as their integra-
tion with agricultural machines and drones. Expanding the use of GPUs
and advanced artificial intelligence techniques are also promising al-
ternatives for future work. Wheat, oat and barley cultivars, for instance,
could benefit from a computer system that aims to reduce complexity
and costs in the gluten-containing grains classification from images.
Finally, our intention that this survey would present diverse appli-
cations and techniques of machine learning, image and video proces-
sing in order to motivate more researchers to apply them for solving
agricultural problems currently open. The study of the presented works
and the problems that they set out to solve together with the new ad-
vances in computer vision and artificial intelligence can lead to new
solutions for agriculture bringing gains of production, quality, and food
security.
Referen