In fish farms and shops, feeder fish are usually packed in
plastic bags, to be sold to customers. Packing involves
counting the fish to get the right quantity required by
customers. However, the counting process is time
consuming and can be subjected to human error.
In this paper, we explore how this feeder fish counting can
be automated using image processing [1]. Studies such as
those in [2] and [3] include some possible ways of fish
counting. However, they are designed for bodies of water
with different varieties of fish so they include some form of
fish species detection algorithm so as to be able to count the
number for each species. In addition, fish tracking
algorithms are also used in the counting of fish. Thus, their
suggested methods are computationally intensive and will
increase costs and slow down the counting speed. For feeder
fish counting, the problem is simplified because it only
involves one species of fish which look similar in shape and
size to each other so fish species detection is not needed.
Fish tracking will be important in cases in which fish may
swim in and out of the video frame so the total number of
fish may vary. Since the number of fish in the plastic bag is
fixed, fish tracking is not essential although it will improve
the accuracy. We instead aim to find a simple-to-execute
method that can do the counting operation quickly with good
accuracy.