KMITL Innovation Expo 2025 Logo

Automatic gemstone color sorting machine

Abstract

This research aims to develop an automatic gemstone color sorting machine to overcome the limitations of manual color sorting, which can be restricted by speed and accuracy. This study applies deep learning technology to analyze and classify gemstone colors precisely, developing an algorithm capable of accurately detecting and categorizing color shades. An automated conveyor system was also designed to efficiently transport gemstones through the color sorting process, allowing for continuous operation. The sorting machine works by capturing high-resolution images of the gemstones, processing them with software to classify color shades, and directing each gemstone to its designated position on the automated conveyor. Experimental results demonstrate that the automated color sorting machine, integrated with the conveyor system, achieves high speed and accuracy, significantly reducing labor costs and enhancing the efficiency of gemstone color sorting.

Objective

ปัจจุบันการตรวจสอบเฉดสีของพลอยถือเป็นขั้นตอนสำคัญในการประเมินคุณภาพ ทั้งในกระบวนการผลิตและการค้าขาย อย่างไรก็ตามการตรวจสอบเฉดสีที่ดำเนินการโดยมนุษย์นั้นมีข้อจำกัดหลายประการ ซึ่งหนึ่งในนั้นเป็นเรื่องความสามารถในการแยกเฉดสีที่ซับซ้อน ซึ่งอาจทำให้การตรวจสอบใช้เวลานาน และมีความแม่นยำต่ำ จากปัญหาดังกล่าว จึงได้พัฒนาแนวคิดในการสร้างเครื่องคัดแยกเฉดสีพลอยอัตโนมัติ โดยใช้ระบบ Computer Vision ร่วมกับระบบอัตโนมัติในการวิเคราะห์เฉดสีของพลอย เพื่อลดข้อจำกัดของการตรวจสอบด้วยมนุษย์ เพิ่มความแม่นยำและประสิทธิภาพในการทำงาน รวมถึงทำให้กระบวนการตรวจสอบเป็นไปอย่างรวดเร็วและมีมาตรฐานของเฉดสี GIA (Gemological Institute of America)

Other Innovations

EcoGrow Pellets: Recycled Clay Pellets Enriched with Natural Calcium

คณะวิทยาศาสตร์

EcoGrow Pellets: Recycled Clay Pellets Enriched with Natural Calcium

Eco Grow Pellets are high-porosity plant-growing clay pellets made from ceramic industrial sediment, blended with ground chicken bone to enhance calcium and essential minerals, promoting strong and healthy plant growth. They are suitable for all types of plants, especially those requiring well-aerated soil with good water drainage. Eco Grow Pellets are an innovative clay-based growing medium designed to optimize plant cultivation efficiency. Their high porosity structure allows for excellent air and water circulation, reducing soil compaction and waterlogging—common causes of root rot and stunted growth. Additionally, the pellets are enriched with calcium and essential minerals from ground chicken bones, reinforcing plant structure and enhancing root strength, enabling better nutrient absorption. This product is made from 100% recycled ceramic industrial sediment, aligning with the principles of Zero Waste and the BCG Economy Model. It helps minimize industrial waste while transforming discarded materials into high-value, eco-friendly growing media. Eco Grow Pellets are ideal for vegetables, flowers, and potted plants, offering ease of use, cleanliness, and safety. They contribute to sustainable agriculture by improving both crop productivity and environmental health.

Read more
Evenly Distributed Temperature Controlled Medical Refrigerator

คณะบริหารธุรกิจ

Evenly Distributed Temperature Controlled Medical Refrigerator

Evenly Distributed Temperature Controlled Medical Refrigerator is the medical refrigerator which equipped with specialized control system to control the cold air distribution within the chamber to have the same temperature along the different height within the chamber.

Read more
Smart Jaundice Diagnostic System

คณะวิศวกรรมศาสตร์

Smart Jaundice Diagnostic System

Jaundice, a common condition in infants that results from high bilirubin levels in the blood, often requires early diagnosis and monitoring to prevent severe complications, especially in newborns. Traditional diagnostic methods can be time-consuming and subject to human error. This study proposes an approach for real-time jaundice detection using advanced image processing techniques and machine learning algorithms. By analyzing images captured in RGB color spaces, pixel values are extracted and processed through Otsu’s thresholding and morphological operations to detect color patterns indicative of jaundice. A classifier model is then trained to distinguish between normal and jaundiced conditions, offering an automated, accurate, and efficient diagnostic tool. The system’s potential to operate in real-time makes it particularly suited for clinical settings, providing healthcare professionals with timely insights to improve patient outcomes. The proposed method represents a significant innovation in healthcare, combining artificial intelligence and medical imaging to enhance the early detection and management of jaundice, reducing reliance on manual interventions and improving overall healthcare delivery.

Read more