Sparse Modelling for Feature Learning in High Dimensional Data

TL;DR

This paper introduces a sparse modeling framework combining Lasso, proximal gradient methods, and pre-trained models like VGG19 for effective feature extraction and defect detection in high-dimensional wood surface datasets.

Contribution

It presents a novel integration of sparse modeling with deep pre-trained features and anomaly detection techniques for improved defect classification.

Findings

Enhanced accuracy and F1 scores in defect detection

Effective feature selection with interpretable models

Successful application of sparse modeling in high-dimensional data

Abstract

This paper presents an innovative approach to dimensionality reduction and feature extraction in high-dimensional datasets, with a specific application focus on wood surface defect detection. The proposed framework integrates sparse modeling techniques, particularly Lasso and proximal gradient methods, into a comprehensive pipeline for efficient and interpretable feature selection. Leveraging pre-trained models such as VGG19 and incorporating anomaly detection methods like Isolation Forest and Local Outlier Factor, our methodology addresses the challenge of extracting meaningful features from complex datasets. Evaluation metrics such as accuracy and F1 score, alongside visualizations, are employed to assess the performance of the sparse modeling techniques. Through this work, we aim to advance the understanding and application of sparse modeling in machine learning, particularly in the context of wood surface defect detection.