what is the best way to detect visible defects on peaches

Introduction

Detecting visible defects on peaches is crucial for maintaining fruit quality, reducing economic losses, and ensuring food safety. Various advanced imaging and sensing technologies have been explored to address the challenges posed by the high variability in peach skin color and the similarity between defects and other features like stems.

Key Insights

Hyperspectral Imaging and Multispectral Analysis:
- Hyperspectral imaging combined with multivariate analysis and band math can effectively detect both artificial and non-artificial defects on peaches, achieving an overall classification accuracy of 93.3%.
- Multispectral detection using visible-near infrared (vis-NIR) hyperspectral imaging, coupled with principal component analysis (PCA) and a band ratio algorithm, can differentiate defects from normal surfaces with an accuracy of 96.6%.
- Short-wave near infrared (SW-NIR) hyperspectral imaging, combined with an improved watershed segmentation algorithm, is effective for detecting early bruises on peaches, with detection accuracies of 96.5% for bruised and 97.5% for sound peaches.
Artificial Neural Networks (ANN) and Machine Learning:
- Hyperspectral reflectance imaging combined with an artificial neural network (ANN) model can detect cold injury in peaches with an accuracy of 95.8%.
- Structured-illumination reflectance imaging (SIRI) coupled with convolutional neural networks (CNN) can detect early fungal infections in peaches with a detection rate of 98.6%.
Optical and Reflectance Techniques:
- Spatially-resolved diffuse reflectance techniques can assess the optical properties of peaches and correlate them with tissue structural and biochemical properties, aiding in early disease detection.
- Laser Doppler detection can remotely sense changes in fruit texture and detect internal disorders, offering a non-destructive method for evaluating fruit firmness and maturation.
Electronic Nose (E-nose) Technology:
- E-nose technology, based on volatile organic compounds (VOCs), can non-destructively predict compression damage levels in yellow peaches, with a correct identification rate of 93.33%.
Rotating Hyperspectral Imaging:
- A rotating hyperspectral imaging system can detect decay caused by Rhizopus stolonifera in peaches, achieving 100% classification accuracy for sound and rotten peaches.

Conclusion

The best methods for detecting visible defects on peaches involve advanced imaging technologies such as hyperspectral and multispectral imaging, combined with machine learning algorithms like ANN and CNN. These methods provide high accuracy in identifying various types of defects, including bruises, cold injuries, and fungal infections. Additionally, optical techniques and e-nose technology offer promising non-destructive alternatives for assessing fruit quality and detecting internal disorders.

What is the best way to detect visible defects on peaches

Summary

Introduction

Key Insights

Conclusion

Sources and full results

Multispectral detection of skin defects of bi-colored peaches based on vis–NIR hyperspectral imaging

The proposed multispectral algorithm effectively differentiates normal and defective bi-colored peaches using visible-near infrared (vis-NIR) hyperspectral imaging, with a 96.6% accuracy.

Hyperspectral imaging combined with multivariate analysis and band math for detection of common defects on peaches (Prunus persica)

Hyperspectral imaging combined with multivariate analysis and band math effectively detects common defects on peaches, with an overall classification accuracy of 93.3%.

Detection of cold injury in peaches by hyperspectral reflectance imaging and artificial neural network.

Hyperspectral reflectance imaging and artificial neural networks effectively detect cold injury in peaches, with a 95.8% classification accuracy for cold-stored samples.

Assessment of the optical properties of peaches with fungal infection using spatially-resolved diffuse reflectance technique and their relationships with tissue structural and biochemical properties.

Optical absorption and reduced scattering properties in peaches can be used to detect early disease detection, with their correlations to structural and biochemical parameters aiding in early disease detection.

Detection of early bruises on peaches (Amygdalus persica L.) using hyperspectral imaging coupled with improved watershed segmentation algorithm

SW-NIR hyperspectral imaging coupled with the improved watershed segmentation algorithm effectively detects early bruises on peaches, reducing quality loss and enhancing fruit safety.

PEACH DEFECT DETECTION WITH MACHINE VISION

The machine vision system accurately detects andidentifies surface defects on fresh market peaches, with 31% error rate for near-infrared systems and 40% for color systems.

Detecting decayed peach using a rotating hyperspectral imaging testbed.

The hyperspectral imaging method effectively detects decayed peaches, with potential for automatic detection of fungal infections in peaches.

Detection of early decay in peaches by structured-illumination reflectance imaging

SIRI, coupled with an appropriate image classification method, effectively detects early fungal infection in peaches, reducing economic loss for the industry.

Rapid and Non-Destructive Detection of Compression Damage of Yellow Peach Using an Electronic Nose and Chemometrics

Electronic nose technology effectively detects compression damage in yellow peaches without causing damage, enabling rapid monitoring and optimization of freshness preservation strategies.

Evaluation of fruit tissue texture and internal disorders by laser Doppler detection

Laser Doppler detection of fruit vibration signals can effectively evaluate tissue firmness, maturation, and detect concealed internal defects, making it a versatile remote sensing tool for fruit evaluation.

Try another search