Trichoderma Classification System Based on Color Code Texture of Potato Dextrose Agar Solid Using Tensorflow with Prototype

Table of Contents

CHAPTER I Introduction

Background of the Study

Objective of the Study

Significance of the Study

Scope and Limitations of the Study

Definition of Terms

CHAPTER II Review of Related Study

Related Literatures

Review of Related Studies

System Design

Data and Data Gathering Procedure

Operational Framework

Respondents of the Study

Statistical tools Formula Used

CHAPTER III METHODOLOGY

Research Locale of the Study

CHAPTER IV RESULT AND DISCUSSION

Development of a prototype that has a remote control.

Development of a Camera that slides along the track, ensuring smooth and steady movement.

Development of the Capture image using controlled camera system.

Development a system that can determine the healthy Solid Trichoderma culture Ready to harvest.

Development of a system that can Classify difference of solid Trichoderma

Data Analysis

CHAPTER V RESULT AND DISCUSSION

SUMMARY

CONCLUSION

RECOMMENDATION

Research Objectives & Topics

The primary goal of this research is to develop an automated Trichoderma Classification System based on the color code texture of Potato Dextrose Agar Solid (PDA) using TensorFlow, aiming to enhance quality control in agricultural laboratories by reducing reliance on manual visual inspection.

• Automated classification of healthy vs. contaminated Trichoderma cultures.
• Development of a hardware prototype featuring a motorized camera dolly for controlled imaging.
• Implementation of TensorFlow-based image recognition for accurate Trichoderma status assessment.
• Performance evaluation of the system using statistical reliability and functionality metrics.

Excerpt from the Book

Summary of Chapters

CHAPTER I Introduction: This chapter introduces the importance of Trichoderma in agriculture and identifies the problem of manual inspection, proposing an automated classification system as a solution.

CHAPTER II Review of Related Study: This chapter reviews various existing image processing and machine learning techniques applied in agriculture for disease detection and fruit grading.

CHAPTER III METHODOLOGY: This chapter describes the waterfall model, research locale, and the hardware and software requirements necessary to build the proposed classification system.

CHAPTER IV RESULT AND DISCUSSION: This chapter presents the development of the hardware prototype and the software, along with the data analysis of testing results on classification accuracy and system reliability.

CHAPTER V RESULT AND DISCUSSION: This chapter provides a summary of the project development, draws conclusions based on evaluators' feedback, and offers recommendations for future system enhancements.

Keywords

Trichoderma, TensorFlow, Potato Dextrose Agar, Color Code Texture, Image Processing, Machine Learning, Automation, Quality Control, Agricultural Technology, Desktop Application, Prototype, Camera Dolly, Classification, Reliability, Functionality.

Frequently Asked Questions

What is the core purpose of this research?

The research focuses on automating the classification process of Trichoderma cultures to ensure efficient quality control in laboratories using image processing.

What are the primary fields covered in this study?

The study intersects fields such as agricultural biotechnology, computer vision, machine learning (specifically TensorFlow), and software systems engineering.

What is the main objective of the system?

The objective is to determine if a solid Trichoderma culture is healthy and ready for harvest or contaminated, based on its color and texture.

Which scientific methodology does the project employ?

The study utilizes the waterfall model for development, alongside survey research methodology (ISO Software Quality Model 9126) to evaluate functionality and reliability.

What is covered in the main body of the project?

The main body details the hardware design of the camera dolly, the software implementation using TensorFlow and Python, and the subsequent testing phases conducted over several days.

Which keywords define this research?

Key terms include Trichoderma, TensorFlow, automation, image classification, and quality control.

How does the camera dolly improve the system?

The motorized camera dolly ensures smooth and consistent camera movement to capture high-quality images of the Trichoderma samples for reliable processing.

What role does the Likert scale play in the study?

It is used as a statistical tool to quantify and interpret the feedback from respondents regarding the functionality and reliability of the developed system.

What were the main conclusions drawn by the proponent?

The system was found to be functional and effective for classification, though further improvements in camera resolution and automation via Arduino are recommended.