Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enhancing Apple's Defect Classification: Insights from Visible Spectrum and Narrow Spectral Band Imaging

Omar Coello, Moisés Coronel, Darío Carpio, Boris Vintimilla, Luis Chuquimarca

TL;DR

An innovative approach is employed that integrates images from the visible spectrum and 660 nm spectral wavelength to enhance accuracy and efficiency in defect classification and highlights the potential to enhance the method by capturing images with specific spectral ranges using filters, enabling more effective network training for classification task.

Abstract

This study addresses the classification of defects in apples as a crucial measure to mitigate economic losses and optimize the food supply chain. An innovative approach is employed that integrates images from the visible spectrum and 660 nm spectral wavelength to enhance accuracy and efficiency in defect classification. The methodology is based on the use of Single-Input and Multi-Inputs convolutional neural networks (CNNs) to validate the proposed strategies. Steps include image acquisition and preprocessing, classification model training, and performance evaluation. Results demonstrate that defect classification using the 660 nm spectral wavelength reveals details not visible in the entire visible spectrum. It is seen that the use of the appropriate spectral range in the classification process is slightly superior to the entire visible spectrum. The MobileNetV1 model achieves an accuracy of 98.80\% on the validation dataset versus the 98.26\% achieved using the entire visible spectrum. Conclusions highlight the potential to enhance the method by capturing images with specific spectral ranges using filters, enabling more effective network training for classification task. These improvements could further enhance the system's capability to identify and classify defects in apples.

Enhancing Apple's Defect Classification: Insights from Visible Spectrum and Narrow Spectral Band Imaging

TL;DR

An innovative approach is employed that integrates images from the visible spectrum and 660 nm spectral wavelength to enhance accuracy and efficiency in defect classification and highlights the potential to enhance the method by capturing images with specific spectral ranges using filters, enabling more effective network training for classification task.

Abstract

This study addresses the classification of defects in apples as a crucial measure to mitigate economic losses and optimize the food supply chain. An innovative approach is employed that integrates images from the visible spectrum and 660 nm spectral wavelength to enhance accuracy and efficiency in defect classification. The methodology is based on the use of Single-Input and Multi-Inputs convolutional neural networks (CNNs) to validate the proposed strategies. Steps include image acquisition and preprocessing, classification model training, and performance evaluation. Results demonstrate that defect classification using the 660 nm spectral wavelength reveals details not visible in the entire visible spectrum. It is seen that the use of the appropriate spectral range in the classification process is slightly superior to the entire visible spectrum. The MobileNetV1 model achieves an accuracy of 98.80\% on the validation dataset versus the 98.26\% achieved using the entire visible spectrum. Conclusions highlight the potential to enhance the method by capturing images with specific spectral ranges using filters, enabling more effective network training for classification task. These improvements could further enhance the system's capability to identify and classify defects in apples.

Paper Structure

This paper contains 13 sections, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Proposed Approach
  4. Dataset Acquisition
  5. Image Registration
  6. Defects Segmentation
  7. Spectral Subrange Selection
  8. Feed Forward Classification Models
  9. Multi-Input Architecture with Segmentation Masks
  10. Experimental Results
  11. Feedforward method
  12. Multi-Input method
  13. Conclusions

Figures (5)

  • Figure 1: Image registration stage. The images in the first row show unregistered images while those in the second row show the resulting registered images.
  • Figure 2: Feed forward architecture for apple defects classification.
  • Figure 3: Multi-Input architecture for apple defects classification.
  • Figure 4: Comparison of validation accuracy for defects classification CNN models using visible spectrum dataset.
  • Figure 5: Comparison of validation accuracy for defects classification CNN models using 660 nm wavelength spectrum dataset.