Assessing The Impact of CNN Auto Encoder-Based Image Denoising on Image Classification Tasks

TL;DR

This paper demonstrates that integrating CNN autoencoder-based denoising techniques with classification models significantly improves defect detection accuracy in noisy industrial images, especially in casting product inspection.

Contribution

The study introduces a novel pipeline combining noise detection, denoising, and classification using deep learning models, achieving high accuracy in industrial defect detection tasks.

Findings

VGG16 achieved over 99% accuracy in noise type classification.

Denoising improved defect detection accuracy from 94.6% to 97.0%.

The approach is effective for real-world industrial applications.

Abstract

Images captured from the real world are often affected by different types of noise, which can significantly impact the performance of Computer Vision systems and the quality of visual data. This study presents a novel approach for defect detection in casting product noisy images, specifically focusing on submersible pump impellers. The methodology involves utilizing deep learning models such as VGG16, InceptionV3, and other models in both the spatial and frequency domains to identify noise types and defect status. The research process begins with preprocessing images, followed by applying denoising techniques tailored to specific noise categories. The goal is to enhance the accuracy and robustness of defect detection by integrating noise detection and denoising into the classification pipeline. The study achieved remarkable results using VGG16 for noise type classification in the frequency domain, achieving an accuracy of over 99%. Removal of salt and pepper noise resulted in an average SSIM of 87.9, while Gaussian noise removal had an average SSIM of 64.0, and periodic noise removal yielded an average SSIM of 81.6. This comprehensive approach showcases the effectiveness of the deep AutoEncoder model and median filter, for denoising strategies in real-world industrial applications. Finally, our study reports significant improvements in binary classification accuracy for defect detection compared to previous methods. For the VGG16 classifier, accuracy increased from 94.6% to 97.0%, demonstrating the effectiveness of the proposed noise detection and denoising approach. Similarly, for the InceptionV3 classifier, accuracy improved from 84.7% to 90.0%, further validating the benefits of integrating noise analysis into the classification pipeline.