Feature extraction is essential for solving image classification by transforming low-level pixel values into high-level features. However, extracting effective features from images is challenging due to high variations across images in scale, rotation, illumination, and background. Existing methods often have a fixed model complexity and require domain expertise. Genetic programming (GP) with a flexible representation can find the best solution without the use of domain knowledge. This article proposes a new GP-based approach to automatically learning informative features for different image classification tasks. In the new approach, a number of image-related operators, including filters, pooling operators, and feature extraction methods, are employed as functions. A flexible program structure is developed to integrate different functions and terminals into a single tree/solution. The new approach can evolve solutions of variable depths to extract various numbers and types of features from the images. The new approach is examined on 12 different image classification tasks of varying difficulty and compared with a large number of effective algorithms. The results show that the new approach achieves better classification performance than most benchmark methods. The analysis of the evolved programs/solutions and the visualization of the learned features provide deep insights on the proposed approach.

中文翻译：

---

使用图像相关算子的遗传编程和灵活的程序结构，用于图像分类中的特征学习


特征提取对于通过将低级像素值转换为高级特征来解决图像分类至关重要。然而，由于图像之间的比例、旋转、照明和背景差异很大，从图像中提取有效特征具有挑战性。现有方法通常具有固定的模型复杂性，并且需要领域专业知识。具有灵活表示的遗传编程（GP）可以在不使用领域知识的情况下找到最佳解决方案。本文提出了一种新的基于 GP 的方法来自动学习不同图像分类任务的信息特征。在新方法中，许多与图像相关的算子，包括滤波器、池化算子和特征提取方法，都被用作函数。开发了灵活的程序结构，将不同的功能和终端集成到单个树/解决方案中。新方法可以演化出可变深度的解决方案，以从图像中提取各种数量和类型的特征。该新方法在 12 种不同难度的图像分类任务上进行了检验，并与大量有效算法进行了比较。结果表明，新方法比大多数基准方法取得了更好的分类性能。对演进的程序/解决方案的分析和学习特征的可视化为所提出的方法提供了深刻的见解。