Department of Information Technology

COLLEGE OF ENGINEERING

CENTRAL LUZON STATE UNIVERSITY

Science City of Muñoz, Nueva Ecija

AUTOMATED TILAPIA FINGERLINGS COUNTER

AND WEIGHING APPLICATION FOR CLSU
FRESHWATER AQUACULTURE

A Capstone Project
Presented to the
Faculty of the Department of Information Technology

In Partial Fulfillment
of the Requirements for the Course ITCAP 3200
IT Capstone Project 1

By:

Guibone, Rumzell Billy C.

Mateo, Jolyn E.
Tamayo, Ivy Joice V.

February 2022
 APPROVAL SHEET

This Capstone Project entitled “AUTOMATED TILAPIA FINGERLINGS

COUNTER AND WEIGHING APPLICATION FOR CLSU FRESHWATER
AQUACULTURE” was prepared and submitted by Tamayo, Ivy Joice V., Guibone,
Rumzell C., Mateo, Jolyn E., in partial fulfillment of the requirements for the degree
BACHELOR OF SCIENCE IN INFORMATION TECHNOLOGY has been examined
and hereby endorsed.

MS. CHEZALEA FAY PEÑA

Adviser
______________ _________________________________________________________
CAPSTONE PROJECT ORAL PRESENTATION COMMITTEE

DR. NEMESIO A. MACABALE JR. MR. CENON CONRADO DIVINA

Chair Member
______________________ _____________________
Date Signed Date Signed
______________ _________________________________________________________
Accepted and approved in partial fulfillment of the requirements for the degree
BACHELOR OR SCIENCE IN INFORMATION TECHNOLOGY.

DR. KHAVEE AGUSTUS W. BOTANGEN

Head, IT Department
_________________
Date

DR. THEODY B. SAYCO

Dean, College of Engineering
_________________
Date
 CERTIFICATION OF MANUSCRIPT PROOFREADING

This is to certify that the undersigned has reviewed and edited the manuscript of
Tamayo, Ivy Joice V., Guibone, Rumzell C., Mateo, Jolyn E., entitled “AUTOMATED
TILAPIA FINGERLINGS COUNTER AND WEIGHING APPLICATION FOR
CLSU FRESHWATER AQUACULTURE”. This further certifies that the scope of
editing is for proper English language, grammar, punctuation, spelling, and overall
writing style.

Issued this th day of ___________, [year], [address].

___________
[Affiliation/Position]
[Company/Organization]
Disclaimer:
“This Capstone Project is submitted to the Department of Information Technology,
College of Engineering, in partial fulfillment of the requirements for the degree Bachelor
of Science in Information Technology at the Central Luzon State University, Science City
of Muñoz, Nueva Ecija. It is a product of our own work except where indicated in the
text. The project report or any portion thereof including the source code or any section
may be freely copied and distributed provided that the source is acknowledged.”
 TABLE OF CONTENTS
Title Page ……………………………………………………….………….………….… i

Approval Sheet ……………………………………….………………………….……… ii

Certification of Manuscript Proofreading …………………………………….…….…... iii

Disclaimer……………………………………………...….…….…………………….… vi

CHAPTER I - INTRODUCTION ………………………..…………………………… 1

Problem Statement …………………………………………………………………….… 2

Objectives ……………………………….…………………….……….…………………2

Scope and Limitation …………………………………………………………….……… 3

Significance of the Study……………………………………...….……………………… 4

CHAPTER II - REVIEW OF RELATED LITERATURE AND EXISTING

ALTERNATIVES ………………………………………..……………….....………….. 6

A. Review of Related Literature ………………………………………………………… 6

B. Review of Existing Alternatives ………………………………...…………………… 8

Portable Tilapia Fingerlings Counter using Digital Image Processing System ..... 8

An Automated Fish Counting Algorithm in Aquaculture Based on Image

Processing …………………………………………...….….…………...……….. 8

Nonintrusive methods for biomass estimation in aquaculture with emphasis on

fish : a review……………………………………………………………………. 9
 Google Play Store Application: Count Things ……....………………………….. 9

Design and Development of an Automated Fry Counter……..…………………. 9

Using image processing technology to create a novel fry counting algorithm … 10

Automatic live fingerlings counting using computer vision ………........……… 10

Automatic Fish Population Counting by Machine Vision and a Hybrid Deep

Neural Network Model ………………………………………………………… 11

Synthesis ……………………………………...………….…………………………… 13

CHAPTER III - METHODOLOGY ………...........……………...….…………….… 15

A. Requirements and Definition …….……………..……………………………………15

a. Data Gathering ………………………....………………..……………………16

b. Gantt Chart …………..………………....………………..……………………17

c. Feasibility Study ………...……………...………………..……………………17

B. System Design …..………………………...………………………………………… 18

a. Hardware Requirements .……………...………………..……………………. 19

b. Software Requirements .……………...………………..…………………….. 20

C. Implementation …………….….….….….….….….….….…...………………………21

D. Integration and Testing ……………………………………...……………………… 21

E. Operation and Maintenance …………………………………………………………. 22

REFERENCES ……………………….….…………………….………….…….….…. 24

APPENDICES ………………………………………………………………………… 28

A. Prototype ….…………….…………….…………….…………….…………….……27

Mobile App User Interface………….…………….…….…………….…………27

Scan Module ….….………….………….…....……….…………...………….…28

History Module ...……….…….………….…….……...…….…….………….…29

Fingerlings Module ....…….…….…….….….…….…….…….…….…….…….30

Exit Module ...…..……..……..……..……..…...…..……..……..……..……..…31

B. ISO 9126 Evaluation Tool …………….…………….…………….…………….……32

LIST OF FIGURES

Figure 1: SDLC Waterfall Model ……..........................….……….…...…….……….…15

Figure 2: Mobile App User Interface ……….…….……….…….………..…….……….34

Figure 3: Scan Module ……….………….…………..…......….….……….………….…35

Figure 4: History Module ………………………………………………………..………36

Figure 5: Fingerlings Module ……..………..………..………..………………..……….37

Figure 6: Exit Module ….……….….…......…….….…….……….……….……….……38

Figure 7: ISO 9126 Model ……….……….…...….……….………...……….……….…39

 LIST OF TABLES

Table 1: Comparison Between Existing Alternatives and the Proposed System in Terms

of Features and Functionalities ……….……….…………….………...……………….. 12

Table 2: Hardware Requirements ………………………..….……….……….…….……18

Table 3: Software Requirements ………………………..…..……….……….…….……19

Table 4: Size Chart of Tilapia Fingerlings .……………..…..……….……….…….……23

 CHAPTER I

INTRODUCTION

Fish production continues to change with the help of technology. In aquaculture,

traditional farming such as natural ponds is used to produce fish. Open-air earthen ponds

are widely popular and used by local farmers for they have wide farmlands that contain

water reservoirs like dams and irrigation. Using this method, it is also possible to produce

invasive species like tilapia.

Tilapia is the second most important farmed species in the Philippines with a total

production of 281,111 metric tonnes in 2021 (ISPs, 2022). This industry provides

valuable income and an affordable source of animal protein for the growing population,

particularly those that depend on agriculture and fishing for livelihood (Mirasol, 2021).

In Freshwater Aquaculture (FAC) at Central Luzon State University, they produced

tilapia, and tilapia fingerlings then sold to a nearby town. Fingerlings were lighter to sell

in mass produce than the grown tilapia. Traditional methods of counting using straining

tools and manually hand-counting the population of fingerlings was implemented for

more than a decade in Aquaculture. Too many assumptions on population could cost

oversold tilapia fingerlings in production.

As the traditional method of counting is designed to know the exact population of

fingerlings in production, it is important to count and weigh this in the most efficient way

possible. An Application for CLSU Freshwater Aquaculture can be a substantial help to

1
lessen the time and effort of the people in the Freshwater Aquaculture Center. The time

they’ve consumed before in manual counting and weighing can now be spent on other

activities.

This automated counting and weighing aim to count the population of fingerlings in

the most practical way. The application will record the fingerling’s size and weight on a

database.

PROBLEM STATEMENT

During the harvest season, hatchery production managers manually count the sample

population of tilapia fingerlings by this traditional step. They use a strainer tool such as a

skimmer to transfer the fingerlings from the pond and place it in a plastic bag. They

weigh each batch by batch equally to the first batch for reference and count the first batch

of tilapia fingerlings manually. Assuming that the total population of the fingerlings in

the first batch is the same as the rest of the batch. After getting the assumed number of

tilapia fingerlings, this process will be repeated. Hatchery production managers track the

records of the tilapia fingerlings every harvesting season by writing down their product

by size and the total population of tilapia fingerlings every time there are buyers. This

traditional step consumes a lot of labor and may lead to human errors when counting.

OBJECTIVES OF THE STUDY

The general objective of the study is to develop and implement an Automated

Counting and Weighing Application for tilapia fingerlings that can be used by the Tilapia

farmers at the Central Luzon State University Freshwater Aquaculture.

2
This study's specific objectives are as follows:

● To determine the number of tilapia fingerlings.

● To determine the weight of tilapia fingerlings.

● To generate reports of the total number of tilapia fingerlings.

● To lessen the amount of labor used when counting and weighing tilapia

fingerlings.

SCOPE AND LIMITATION

The application to be developed specifically features counting, weighing, and generating

tilapia fingerlings’ data only. It can be used for any type of Tilapia fingerlings only and it

is not applicable to other fish like milkfish. The study uses tilapia fingerlings for

implementation and testing. The implementation and testing were conducted at the

Central Luzon State University Fresh Aquaculture Center.

The interface of the application has four modules: the Scan Module, History Module,

Fingerlings Module, and the Exit Module.

Scan Module

The Scan module is the scanner of the application. When the button is clicked, it will

directly open the camera. It has a Capture button at the bottom and is now ready to

capture fingerlings.

History Module

The History module will show the previous data gathered from the scanner. History will

include the date and the records of the previous image taken such as the total number and

the size of the tilapia fingerlings. Users can also delete and save data into the application.

3
Fingerlings Module

The Fingerlings module will show the standard size chart of the tilapia fingerlings. It will

also include some facts about the tilapia fingerlings that the user may need.

Exit Module

The Exit module will show the exit option if the user wants to exit the application.

SIGNIFICANCE OF THE STUDY

This application aims to provide accurate and effective Automated Counting and

Weighing Application, to count and provide the weight of Tilapia Fingerlings for the

hatchery production managers at the Freshwater Aquaculture Center. In today’s

generation, developers are engaging in Android-based applications to aim and enhance

individual lifestyles, especially for hatchery production managers who count fingerlings

manually. This application will be helpful because it can optimize the counting method

with the precise number of fingerlings in a short period of time.

To the BSIT Students: This project will provide additional knowledge on the

new technology and enhance the skills of the Information Technology and Fisheries

Students at the CLSU.

To the Teachers: This project will assist the teachers in imparting knowledge to

the students/learners and in showing them how to utilize advanced technology that can be

used in counting and weighing tilapia fingerlings.

To the Fish Farmers: This project will help them count and weigh fingerlings

accurately and faster than the traditional method.

4
 To the Researchers: This project will help the researchers improve their

programming skills even on offline applications. This project may also let them innovate

more and enhance their logical thinking skills in solving problems by using advanced

technology.

To the future Researchers: This project can inspire future researchers to learn

more and to innovate more advanced technology that can be used in the future.

5
 CHAPTER II

REVIEW OF RELATED LITERATURE AND EXISTING ALTERNATIVES

A. REVIEW OF RELATED LITERATURE

Tilapia Cultured: The Basics

Several studies have been explored to determine the content of the Tilapia. One of

these is the study conducted by Eguia, et al. (2020). They conclude that among the most

important aquaculture commodities in the world is a fast-growing and prolific tilapia. In

the Philippines, tilapia is second only to milkfish in terms of the fish production volume

from aquaculture. Based on data from the Bureau of Fisheries and Aquatic Resources

(BFAR), the country produced a total of 277,006 metric tons of tilapia in 2018. That year,

this comprised 33.5% of the volume of all non-seaweed production in Philippine

aquaculture.

Tilapia Fingerlings

Fingerling is a young or small fish, a broad term applied to a juvenile fish that is

about the size of a finger. The definition of what length classifies a fish as a fingerling

varies between species, but the Food and Agriculture Organization (FAO) generally

defines a fingerling as ranging in length from 10 to 15 centimeters (Abby, 2019).

Fingerling availability is a critical element in the development of the tilapia farming

industry in the United States. Farms are widely dispersed among the states and territories

and no region has enough output for any one farm to specialize in the production of

advanced fingerlings (40-50 g) for sale to nearby grow-out operations. Fisheries is a

6
rapidly growing food-producing industry in the world. Aquaculture provides 44.14% of

the world’s fish production for human consumption.

Digital Image Processing

Digital image processing, also known as computer image processing, refers to the

process of converting an image signal into a digital signal and processing it with a

computer. This process includes image enhancement, noise reduction, segmentation,

restoration, encoding, compression, and extraction of features. Image processing

technology cannot be developed without the development of computers, the development

of mathematics, and the growth of application requirements in various industries. In the

1960s, image processing technology began to be applied more scientifically, and people

used this technology to perform idealized processing of output images. After years of

development, the current electronic image processing technology has the following

characteristics: better reproducibility: Compared with traditional analog image

processing, digital image processing will not be due to storage, copying, or transmission

in image processing. Causes the change of image quality; The occupied frequency band is

wider: this is relative to the language information, the image information is several orders

of magnitude larger than the frequency band of the language information, so the image

information is more difficult in the process of operation; Applicable width: data sources

can be obtained from various sources (Luo,2018).

Digital Images Processing is an integral part of our digital life. Digital images are

used in every aspect of our daily life. Digital image processing is concerned with

7
techniques to perform processing on an image, to get an enhanced image, or to extract

some useful information from it to make some decisions based on it (Tyagi, 2018).

B. REVIEW OF EXISTING ALTERNATIVES

Portable Tilapia Fingerlings Counter using Digital Image Processing System

This research by Sulit, J. R. et al. (2019) demonstrates a portable tilapia

fingerlings counter that operates through the use of digital image processing. Using the

Blob detection and Haar cascade techniques. An image of the pool of fingerlings captured

inside the counting chamber specially designed for this project will undergo grey-scaling

and dilation and several image processing to count the fingerlings. Sub-images containing

the image of the fingerlings are set to be the XML file, which will then match the subject

image for the Haar method for dead fingerlings and deduct it from the counted fingerlings

using Blob detection.

An Automated Fish Counting Algorithm in Aquaculture Based on Image Processing

A study by Le, J., & Xu, L. (2017) discusses a new algorithm based on the

endpoints of the skeleton to efficiently get the number of fish in this paper. Considering

the complexity of the underwater environment like the lack of light, this paper presents

an improved adaptive thresholding method to segment the fish image better. In addition,

the object of our research is free-swimming fish. The overlapped fish in the image makes

the counting result inaccurate often. So after segmentation and morphological processing,

this paper adopts the image thinning method to extract the skeleton of fish. After that, we

get the fish number according to the number of corresponding endpoints in the image.

8
The experimental results show that the method can accurately count the fish population

even under high overlapped degrees.

Nonintrusive methods for biomass estimation in aquaculture with emphasis on fish:

a review

According to Li, D. et al. (2020) fish biomass estimation is one of the most

common and important practices in aquaculture. The regular acquisition of fish biomass

information has been identified as an urgent need for managers to optimize daily feeding,

control stocking densities, and ultimately determine the optimal time for harvesting.

However, it is difficult to estimate fish biomass without human intervention because

fishes are sensitive and move freely in an environment where visibility, lighting, and

stability are uncontrollable.

Google Play Store Application: CountThings

An in-app purchase by Dynamic Ventures, Inc. d/b/a (2017) is to automate your

counting. Manual counting takes too long and creates too many errors. Switch to

automatic counting, it is fast and accurate and used in many industries. The app uses

Counting Templates to identify objects that need to be counted in an image. The

Counting Template tells the app what to count.

Design and Development of an Automated Fry Counter

Developed by Bagasbas (2020) designed, constructed, and evaluated the

performance of an automated fry counter in terms of accuracy, capacity, and mortality

9
rate of the fry. His result shows that as the initial number of fry weighed increases, the

more accurate the fry count is. The machine's mean capacity is 52 fry per minute with a

counting accuracy of 98% and a mortality rate of 0%. He concluded that the constructed

automated fry counter is advantageous and profitable for economic analysis resulting in

0.284 years of the payback period.

Using image processing technology to create a novel fry counting algorithm

Study by Zhang, et al. (2022), uses image processing technology as a useful

method for creating a fish counting algorithm. Quantitative counting of fry is required for

multiple reasons, including breeding, transportation, and sales. The thinning and the

connected area algorithms were then independently adopted to count the fish fry within

the image. The advantages and the disadvantages of the two algorithms under different

densities were also compared, revealing that the fish fry pictures with a clear contrast

between the foreground and background resulted in higher accuracy. Their main purpose

was to solve the problem of fry counting in the case of high density and high overlap.

Automatic live fingerlings counting using computer vision

Conducted by Albuquerque, et al. (2019), proposes a new technique for fish

counting and presents a new image dataset to evaluate fish counting systems that provide

low-cost solutions. They describe a computer-vision-based system that counts fish by

combining information from blob detection, a mixture of Gaussians, and a Kalman filter.

The dataset is composed of a series of videos partially annotated at the frame level, which

include approximately a thousand fish in high-resolution images. Their work shows that

10
the proposed method is a feasible approach for automatic fish counting, reducing costs

and boosting production, as it increases labor availability. Their approach is efficient for

fingerlings counting, with an average precision of 97.47%, recall of 97.61%, and

F-measure of 97.52% in the provided dataset.

Automatic Fish Population Counting by Machine Vision and a Hybrid Deep Neural

Network Model

study by Zhang, et al. (2020), propose an automatic fish counting method based

on a hybrid neural network model to realize the real-time, accurate, objective, and

lossless counting of fish population in far offshore salmon mariculture. They use a

multi-column convolutional neural network (MCNN) as the front end to capture the

feature information of different receptive fields. They used convolution kernels of

different sizes to adapt to the changes in angle, shape, and size caused by the motion of

fish. Simultaneously, a wider and deeper dilated convolution neural network (DCNN) is

used as the back end to reduce the loss of spatial structure information during network

transmission. Finally, a hybrid neural network model is constructed. Their experimental

results show that the counting accuracy of the proposed hybrid neural network model is

up to 95.06%, and the Pearson correlation coefficient between the estimation and the

ground truth is 0.99. Compared with CNN- and MCNN-based methods, the accuracy, and

other evaluation indices are also improved. Therefore, the proposed method can provide

an essential reference for feeding and other breeding operations.

11
 Features
Digital Ligh Edge Biom Comput Mobile Data Online Offline
Image ting Detecti ass er Applica base with
Processing on Program tion Payment

Portable Tilapia ✓ ✓ ✓ ✓
Fingerlings
Counter using
Digital Image
Processing
System

An Automated ✓ ✓ ✓
Fish Counting
Algorithm in
Aquaculture
Based on Image
Processing

Nonintrusive ✓ ✓ ✓
methods for
biomass
estimation in
aquaculture with
emphasis on fish:
a review

CountThings ✓ ✓ ✓ ✓

Automated Tilapia ✓ ✓ ✓ ✓
Fingerlings
Counter and
Weighing
Application for
CLSU Freshwater
Aquaculture
Table 1: Comparison Between Existing Alternatives and the Proposed System in Terms
of Features and Functionalities

12
Synthesis

The existing alternatives included in this chapter allow the developer to express a

simple and portable application such studies included a bulky desktop system into

portable creating an idea for the developer to make a comfortable usage of technology in

the fishing industry.

Previous studies on possible ways of fish counting include electrical system

materials that are connected to digital weighing machines. The microcontroller will serve

as the brain of the automated fry counter. The counter will be constructed after getting the

average weight of the fry to its size. (Bagasbas, 2020). Other existing project designs

consist of light yet durable materials that enable the user to carry the machine from the

hatchery to the farm where the fingerlings will be delivered (Sulit, 2019). Some projects

provide a quick, affordable, and non-invasive method. Environmental DNA, acoustics,

machine vision, and resistivity counters all provide the potential to create non-intrusive,

faster, and less expensive techniques for the situational assessment of fish biomass (Li et

al., 2019). However, these machines can be bulky and can be operated by only one

person.

This application’s main advantage against the existing alternatives is that it is a

software application that can be installed on any android mobile phone and it has an

offline feature used in off-data areas, especially in the FAC. This application can be used

by not only one user as long as the user has an android phone. It can be carried out to

13
other places, unlike other bulky devices that are settled in one place. This application is

also applicable to any tilapia fingerlings as long as it is recognizable as tilapia fingerlings.

In addition, for hatchery production managers who have experience putting a lot

of effort into counting and weighing tilapia fingerlings, this application will make them

count, weigh and generate data accurately without human errors, unlike manual counting.

In conclusion, instead of using a computer and bulky machines, developers use

computer programming Java and the software Android Studio to create an application

that will provide counting, weighing, and generating records of the tilapia fingerlings to

the hatchery production managers of Freshwater Aquaculture in Central Luzon State

University.

14
 CHAPTER III

METHODOLOGY

This chapter covers the project's construction methods and plans using the SDLC

waterfall model. Starting with the Requirement Definition and analysis, System Design,

Implementation, Integration and Testing, Deployment of the system, and Maintenance.

A. Requirements Definition

Figure 1. SDLC Waterfall Model

The developers must specify the project requirements during this phase. It is a

planning step that emphasizes a contractual document which includes a description,

specification, requirements and details. Goals, expectations, timeframes, and budgets are

all included.

15
 a. Data Gathering

The data collected by the developers from the Freshwater Aquaculture (FAC)

from Dr. Hazel Monica Peralta will serve as the framework or projection for the creation

of the application.

The following questions will be asked to the person in charge of monitoring the

tilapia fingerlings:

1. What method do you use for counting tilapia fingerlings?

● This question identifies the technique they employ to count tilapia

fingerlings in order to quickly identify opportunities to improve that

method.

2. What are the factors you need to consider when counting tilapia fingerlings?

● This inquiry identifies the factors to take into consideration when counting

tilapia fingerlings in order to avoid as much stress as possible during

testing and implementation.

3. What process or method do you use when weighing fingerlings?

● This question identifies the technique they employ to weigh tilapia

fingerlings in order to quickly identify opportunities to improve that

method.

4. How many pieces of fingerlings do you count in a container?

16
 ● This question estimates the population of fingerlings in each container. To

establish how many fingerlings we can place in a container to minimize

stress for the fingerlings.

5. What is the purpose of counting fingerlings?

● The importance of counting and weighing fingerlings is determined by this

query.

The developers must record the vital data after gathering it to complete the

project's functionality. The developers must also create a Gantt chart to keep track

of the timetable that will be used for the entire project.

b. Gantt Chart

The developers will create a Gantt chart to illustrate work completed over

a period of time in relation to the time planned for the job. Work should be

planned around deadlines. It will help the development team stay on track by

depicting the relationship between task start and end dates, milestones, and

dependent tasks, among other things.

c. Feasibility Study

Researchers will conduct a feasibility study to analyze and consider all

relevant factors for the project, including economic, technical, and operational

feasibility.

Economic Feasibility

17
 Researchers will conduct an economic feasibility study to

determine the costs and benefits of the proposed system. Tangible and

intangible project means will be included to demonstrate that the desired

project will meet the cost of investment.

Technical Feasibility

Researchers will conduct a technical feasibility study to determine

whether the client has the necessary tools and equipment for the proposed

project.

Operational Feasibility

Researchers will conduct an operational feasibility study to

determine whether the project has addressed the issues raised by the FAC.

It will also determine how easily the application will be used by the client

or user.

B. System Design

Java will be used by the developers in an Android Studio with image processing.

The goal is to construct an application that uses image processing to weigh and count

tilapia fingerlings. The fingerlings will be detected in an aquarium or basin provided by

the university using object detection. An android phone must be used to capture the

necessary images of the fingerlings. To test the system and determine which camera angle

18
is best for spotting the fingerlings, many angles from which to take the photos must be

used.

The application has image processing that teaches the program to learn the

structure of the fingerlings. At first, photos on the website will be gathered to teach the

program about tilapia fingerlings. This information will be put on the program to

recognize an individual and count as a singular fingerling. This is the result of the

counting of each fingerling inside the program.

After defining the requirements is complete, the system must be trained to

recognize the fingerlings. After detecting the fingerlings, the developers will write a

program that counts the fingerlings using the images captured during sampling.

a. Hardware Requirements

Item Specification Quantity Price

1. Glass 40 cm long and 30 cm wide 1 P600.00

Aquarium (provided by the
FAC)

2. Mobile Must be an android phone 1 P3,000.00

Phone with at least 4 GB RAM (provided by the
More than 8MP camera developers)
Android 5.1 (SDK 22)
minimum android version.

3. Laptop with at least 8 GB RAM, 1 P30,000

64-bit, and Windows 10 OS (provided by the
developers)
Table 2. Hardware Requirements

19
 The glass aquarium (40 cm long and 30 cm wide) will serve as the background;

whereas the foreground objects to be extracted are tilapia fingerlings. The mobile phone

will be placed 35 cm above the container to capture images of the tilapia fingerlings. A

batch of tilapia fingerlings provided by the FAC is placed inside the container, which has

a shallow water level of 2.5 cm to reduce overlaps between fishes, which can lead to

occlusion. The images will be processed on an Android phone with the app installed.

b. Software Requirements

Software Specification

1. Android Studio 2021.3 version

Application Program Platform

2. Java Programming Language

3. SQLite Database Engine Version 3.40.1

4. YoloV5 V7.0 by Ultralytics

Object detection algorithm

Table 3. Software Requirements

Android Studio will be used as a platform to make an application on android

devices, with a Java language that programs a command on each part of the module.

Since the application was offline, data stored in the application will be placed in SQLite

which builds to all mobile devices. YoloV5 is an algorithm created by Ultralytics that is

composed of three convolution layers that predict the location of the bounding boxes (x,y,

height, width), the scores, and the objects classes. This helps the application recognize

the fingerlings faster and more accurately up to 91%.

20
 C. Implementation

In this phase, application coding and turning the system design into a functional

model all take place. Clients will provide detailed feedback during this phase, offering

adjustments, modifications, or fresh concepts to address issues as they arise. Following

testing at the CLSU FAC, developers must compile all client input and suggestions before

moving on to the implementation phase.

D. Integration and Testing

There will be two sets of testing that developers will test. The first test will be in

an aquarium. Developers will put the tilapia fingerlings in an aquarium containing 2.5 cm

of water to avoid the overlapping of the fingerlings. The aquarium will be placed at a spot

where there is enough balanced lighting. The place must be flat and settled so the water

will balance. After the aquarium is settled, developers will scan the fingerlings on top of

the aquarium using an android phone where there is an installed application at an exact

angle to scan the whole corners of it.

The second test will be on the basin. The basin will also contain 2.5 cm of water,

the same as the aquarium. The same lighting and the same white flat tile beneath the

plastic bag. The camera that will be used will be put on the same angle as the aquarium.

After the first and second testing, developers will compare each test to see what is the

best and clear testing set for the application.

21
 E. Operation and Maintenance

Developers may now move on to finalizing and executing the application after

submitting a prototype. Developers will install the application on an android phone and

use it for tilapia production at the FAC during the implementation phase so that any

necessary extensive testing or training may be conducted.

The application will count and estimate the weight of the tilapia fingerlings

accurately. The photos that the developers will gather from the FAC will be used as data

to teach the application about the fingerling's structure. This illustrates the data of each

fingerling from the FAC indicating the size, resulting in the accurate population and

weight of a batch of fingerlings in a short time.

STANDARD AGE WEIGHT PRICE/pc

LENGTH (cm) (days) (g)

0.8 - 1.0 3-5 0.009 - 0.01 P0.07

Post-Fry 7 - 10 0.02 - 0.06 P0.10

1.1 - 1.3

Size 32 11 - 14 0.07 - 0.20 P0.20

1.4 - 1.6

Size 24 15 - 19 0.21 - 0.40 P0.30

1.7 - 2.2

Size 22 20 - 25 0.41 - 0.60 P0.35

2.3 - 2.6

Size 20 26 - 30 0.61 - 1.0 P0.40

2.7 - 3.2
Table 4. Size Chart of Tilapia Fingerlings

22
 This table shown above is the standard sizes of the tilapia fingerlings from the fish

farmers at the FAC including their standard length in centimeters, age in days, weight in

grams, and price per piece. The size of the fingerlings is based on how many days the

fingerlings are.

To get the total population of tilapia fingerlings, the application will capture the

fingerlings from the two testing sets that are given. After capturing it, the application will

process the image once it detected the tilapia fingerlings. The application will count the

detected fingerlings one by one until it gets the total number of them.

To get the total population weight of tilapia fingerlings, after getting the total

number of the fingerlings, the application will multiply the population or the total number

to its size as given in the formula below.

total population weight = weight (based on size chart) x total population

To generate the reports of the tilapia fingerlings, the application will have the

history of previous data gathered for documentation purposes. After the application gets

the total number and total population weight of fingerlings, the data will be saved to the

history. The facts about the fingerlings for the user to understand some of the information

about the tilapia. Before confidently providing the FAC with a finished product,

developers create extensive documentation and conduct maintenance chores. After

completing all of these steps, the FAC is now able to use the finished product or

application that is suitable for the fishing industry at the CLSU FAC.

23
References:

Abby, (2019). Fishionary. https://fishionary.fisheries.org/fingerling/.

ACTION, I. (2020). World Fisheries and Aquaculture.

https://www.fao.org/3/ca9229en/ca9229en.pdf

AL-JUBOURI, Q, AL-NUAIMY, W, AL-TAEE, M, YOUNG, I. (2017). An automated

vision system for measurement of zebrafish length using low-cost orthogonal web

cameras. Aquacultural Engineering 75: 156-162.

Bagasbas, J. (2020, February 2). Design and Development of an Automated Fry

Counter. citefactor.org.

COSTA, C., SCARDI, M., VITALINI, V., CATAUDELLA, S. (2009). A dual camera

system for counting and sizing Northern Bluefin Tuna (Thunnus thynnus;

Linnaeus, 1758) stock, during transfer to aquaculture cages, with a semiautomatic

Artificial Neural Network tool. Aquaculture 291: 161-167.

Divino, A. M. (2021, June 24). Volume of Fisheries Production in Central Luzon First

Quarter 2021.

http://rsso03.psa.gov.ph/article/volume-fisheries-production-central-luzon-first-qu

arter-2021

DUAN, Y., STIEN, L., THORSEN, A., KARLSEN, Ø., SANDLUND, N. (2015). An

automatic counting system for transparent pelagic fish eggs based on computer

vision. Aquacultural Engineering 67: 8- 13.

24
Dynamic Ventures, Inc. d/b/a (2017). CountThings.

FAN, L., LIU, Y. (2013). Automate fry counting using computer vision and multi-class

least squares support vector machine. Aquaculture 380-383: 91- 98.

Guerrero, R.D. III, "Eco-Friendly Fish Farm Management and Production of Safe

Aquaculture Foods in the Philippines", Philippine Council for Aquatic and Marine

Research and Development. Retrieved January 26, 2011, from Food and Fertilizer

Technology Center

http://www.agnet.org/library/bc/55003/

Industry Strategic Science and Technology Plans (ISPs) Platform. (n.d.). Retrieved

November 28, 2022, from

https://ispweb.pcaarrd.dost.gov.ph/tilapia-2/#:~:text=Tilapia%20Industry%20Prof

ile,MT%20total%20production%20in%202021.

Jiang H F, Xu Y. Research Advances on Security Problems of Underwater Sensor

Networks [J]. Advanced Materials Research, 2011, 317-319:1002-1006.

Le, J., & Xu, L. (2017, March). An automated fish counting algorithm in aquaculture

based on image processing. In 2016 international forum on mechanical, control,

and automation (IFMCA 2016) (pp. 358-366). Atlantis Press.

Li, D., Hao, Y., & Duan, Y. (2019). Nonintrusive methods for biomass estimation in

aquaculture with emphasis on fish: a review. Reviews in Aquaculture, 12(3),

1390-1411.

25
Mirasol, P. B. (2021, January 21). Tilapia is the ideal pandemic food — DoST.

BusinessWorld. Retrieved January 21, 2021, from

https://www.bworldonline.com/agribusiness/2021/01/21/340199/tilapia-is-the-ide

al-pandemic-food-dost/

Sulit, J. R., Flores, G. A., Asuncion, J. A. B., & Atilio, J. M. D. (2019) Portable Tilapia

Fingerlings Counter using Digital Image Processing System. Red, 53, 74-4681.

Sulit, J. (2019, April). Fingerlings Counter Using Image Processing. researchgate.net.

https://www.researchgate.net/publication/343205745_Fingerlings_Counter_Using

_Image_Processing

Tyagi, V. (2018). Understanding digital image processing. CRC Press.

https://www.researchgate.net/profile/Vipin-Tyagi-2/publication/328120952_Unde

rstanding_Digital_Image_Processing/links/5bda76c092851c6b279dc5a8/Understa

nding-Digital-Image-Processing.pdf

PCAARRD Writer. (2021, May 19). Automatic Fry Counter.

https://ispweb.pcaarrd.dost.gov.ph/.

26
APPENDICES

A. Prototype

Figure 4. Mobile App User Interface

27
Figure 3. Scan Module

28
Figure 3. History Module

29
Figure 3. Fingerlings Module

30
Figure 3. Exit Module

31
 B. Evaluation Tool
Evaluation Tool for User Acceptability (IT Experts)
(Adapted from ISO 25010)

Automated Tilapia Fingerlings Counter and Weighing Application for CLSU

Freshwater Aquaculture

Respondent’s Profile:

Name: _____________________________________________

Position: _____________________________________________

Company: _____________________________________________

Years in Service: _____________________________________________

Highest Educational Attainment: _____________________________________________

QUESTIONNAIRE

Please indicate a check mark (√) under the column that best describes your responses for each
item about the Automated Tilapia Fingerlings Counter and Weighing Application for CLSU
Freshwater Aquaculture.

Please use the rating below:

5 – Beyond Acceptable
4 – Acceptable
3 – Slightly Acceptable
2 – Slightly Unacceptable
1 – Unacceptable

Please start answering here:

32
 Rating
Criteria 5 4 3 2 1
FUNCTIONAL SUITABILITY
Functional Completeness - Functionality covers the
required tasks
Functional Correctness - System provides the appropriate
results with accuracy
Functional Appropriateness – System functions
accomplishes the desired tasks and objectives

PERFORMANCE EFFICIENCY
Time Behavior - Response and processing time is at
acceptable rate when performing specific functionality
Resource Utilization - Amounts and types of resources
used by the system, when performing its functions, meet
requirements of the user
Capacity – Limitations like internet speed, size of database
and processing time do not affect the overall performance
of the system
COMPATIBILITY
Co-existence – The system performs its required functions
efficiently while sharing a common environment and
resources with other products, without detrimental impact
on any other product
Interoperability – System works well when exchanging
information with different units of the organization
USABILITY
Appropriateness Recognizability – Usefulness of the
software/hardware to the intended users. Presence of the
basic or expected functions of the system
Learnability – Use of the system is easily learned by the
intended users
Operability – Functions of system are designed to be
easily adaptable for users
User Error Protection - System protects users against
making errors

33
 Rating
Criteria 5 4 3 2 1
User Interface Aesthetics – User interface like its colors
and icons enables pleasing and satisfying interaction for the
users
Accessibility – System can be used by people with the
widest range of characteristics and capabilities to achieve a
specified goal in a specified context of use.
RELIABILITY
Maturity – System component meet the needs for
reliability under normal operation
Availability – System component is operational and
accessible when required for use
Fault Tolerance – System component operates as intended
despite the presence of hardware or software faults
Recoverability - In the event of an interruption or a failure,
the system can recover the data directly affected and
re-establish its normal state
SECURITY
Confidentiality – System ensures that data are accessible
only to those authorized users
Integrity – System prevents unauthorized access to, or
modification of, computer programs or data
MAINTAINABILITY
Modularity – System failure of one component has
minimal impact to another part of the computer program
Reusability – Data from another part of the system are
easily shared with other units or entities
Analyzability – Errors or failures of the system is easily
diagnosed and mechanism to determine cause of failures is
easily identified.
Modifiability – System can be effectively and efficiently
modified without introducing defects or degrading existing
quality
Testability – Effectiveness and efficiency with which test
criteria can be established for the system and tests can be
performed to determine whether those criteria have been
met
PORTABILITY

34
 Rating
Criteria 5 4 3 2 1
Adaptability – Appropriate interface for novice/ new user.
Appropriate interface for the user’s device display or
screen. System was designed to perform even in mobile
devices.
Installability – Effectiveness and efficiency with which the
system can be successfully installed and/or uninstalled in a
specified environment
Replaceability – System can replace another software for
the same purpose in the same environment

________________________________________
Signature over printed name of Respondent

____________________
Date

35