K-means segmentation based-on lab color space for embryo detection in incubated egg

TL;DR

This paper presents a method for detecting embryos in eggs using K-means segmentation on Lab color space images, enabling non-destructive embryo detection to improve hatchery efficiency.

Contribution

It introduces a novel application of K-means clustering on Lab color images for embryo detection in eggs, combining color segmentation with grayscale processing.

Findings

Segmentation effectively separates background, eggs, and yolk.

High similarity index (MSSIM=0.9979) indicates accurate embryo detection.

Method supports non-destructive embryo analysis in poultry production.

Abstract

The quality of the hatching process influences the success of the hatch rate besides the inherent egg factors. Eliminating infertile or dead eggs and monitoring embryonic growth are very important factors in efficient hatchery practices. This process aims to sort eggs that only have embryos to remain in the incubator until the end of the hatching process. This process aims to sort eggs with embryos to remain hatched until the end. Maximum checking is done the first week in the hatching period. This study aims to detect the presence of embryos in eggs and processed by segmentation. Egg images are segmented using the K-means algorithm based on Lab color images. The results of the image acquisition are converted into Lab color space images. The results of Lab color space images are processed using K-means for each color. The K-means process uses cluster k=3 and divides into three parts: background, eggs, and yolk. Egg yolks are part of eggs that have embryonic characteristics. This study applies the concept of color in the initial segmentation and grayscale in the final stages. The initial phase results show that the image segmentation results using k-means clustering based on Lab color space provide a grouping of three parts. At the grayscale image processing stage, the results of color image segmentation are processed with grayscaling, image enhancement, and morphology. Thus, it seems clear that the yolk segmented shows the presence of egg embryos. Based on this results, the initial stages of the embryo detection process used K-means segmentation based on Lab color space. The evaluation uses MSE and MSSIM, with values of 0.0486 and 0.9979; this can be used to reference that the results obtained can detect embryos in egg yolk. This protocol could be used in a non-destructive quantitative study on embryos and their morphology in a precision poultry production system in the future.