Natural Date Fruit Environment Classification Using CNN

Abstract

The date Fruit dataset was created to address
the requirements of many applications in the
pre- harvesting and harvesting stages. The two
most important applications are automatic
harvesting and visual yield estimation. The
dataset is divided into two subsets and each of
them is oriented into one of these two
applications. The first dataset consists of 8079
images of more than 350 date bunches
captured from 29 date palms. The date bunches
belong to five date types: Naboot Saif, Khalas,
Barhi, Meneifi, and Sullaj. The pictures of date
bunches were captured using a color camera in
six imaging sessions. The imaging sessions
covered all date maturity stages: immature,
Khalal, Rutab, and Tamar. The dataset is
provided with a large degree of variations to
reflect the challenges in natural environments
and date Fruit orchards. These variations in
images include different angels and scales,
different daylight conditions having poor
illumination images, and date bunches covered
by bags. The dataset is fully labeled according to
type, maturity, and harvesting decision. We can
use this dataset in many applications including
Fruit detection, segmentation, classification,
maturity analysis, and automatic harvesting.
The second dataset contains images, videos,
and weight measurements to help in many
applications such as yield estimation. In this
dataset, we marked date bunches for selected
palms, recorded 360° video for each palm, and
measured their data (height, trunk
circumference, total yield, number of bunches,
and weight of bunches). We also captured
images of each bunch from different angles
before harvesting and on a graph paper after
harvesting. Both datasets have been arranged
with a coding scheme to simplify referring,
linking, and facilitating future extensions