Genetic Programming With Image-Related Operators and a Flexible Program Structure for Feature Learning in Image Classification

Bi, Ying; Xue, Bing; Zhang, Mengjie

doi:10.1109/tevc.2020.3002229

Cited by 60 publications

(18 citation statements)

References 48 publications

(101 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, feature extraction methods based on GP have been successfully proposed and applied to different tasks, such as image classification [36]. Benefiting from the flexible representation of GP, many image-related operators, such as the convolution operator, histogram of orientated gradient, the mean filter, the Gaussian filter, the Gabor filter, and the Sobel filter, have been integrated into the GP programs as functions to extract/learn informative features from raw images [43], [47]. Atkins et al [48] proposed a three-tier GP method, where the mean, max, min, median, and standard deviation of image pixel values are extracted as features for image classification.…”

Section: B Gp For Feature Extraction and Constructionmentioning

confidence: 99%

Automatic Feature Extraction and Construction Using Genetic Programming for Rotating Machinery Fault Diagnosis

Peng

Wan

et al. 2021

IEEE Trans. Cybern.

Self Cite

View full text Add to dashboard Cite

Feature extraction is an essential process in the intelligent fault diagnosis of rotating machinery. Although existing feature extraction methods can obtain representative features from the original signal, domain knowledge and expert experience are often required. In this paper, a novel diagnosis approach based on evolutionary learning, namely automatic feature extraction and construction using genetic programming (AFECGP), is proposed to automatically generate informative and discriminative features from original vibration signals for identifying different fault types of rotating machinery. To achieve this, a new program structure, a new function set and a new terminal set are developed in AFECGP to allow it to detect important subband signals, extract and construct informative features, automatically and simultaneously. More importantly, AFECGP can produce a flexible number of features for classification. Having the generated features, k-Nearest Neighbors is employed to perform fault diagnosis. The performance of the AFECGP based fault diagnosis approach is evaluated on four fault diagnosis datasets of varying difficulty and compared with fourteen baseline methods. The results show that the proposed approach achieves better fault diagnosis accuracy on all the datasets than the competitive methods and can effectively identify different fault conditions of rolling bearing, gear, and rotor.

show abstract

Section: B Gp For Feature Extraction and Constructionmentioning

confidence: 99%

Automatic Feature Extraction and Construction Using Genetic Programming for Rotating Machinery Fault Diagnosis

Peng

Wan

et al. 2021

IEEE Trans. Cybern.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The implementation of the EFLGP approach is based on the DEAP (Distributed Evolutionary Algorithm in Python) [60] package, which is a popular evolutionary algorithm package in Python. The parameter settings for EFLGP are based on the commonly used parameter settings of the GP community [21]. The population size is 500 and the maximum number of generations is 50.…”

Section: Parameter Settingsmentioning

confidence: 99%

“…GP has a tree-based variablelength individual representation, which allows it to evolve solutions of variable depths to solve a problem. In feature learning, the flexible representation enables GP to employ image operators for feature extraction in many possible ways [16,21,22]. Specifically, GP may find shallow/simple solutions for easy tasks and deep/complex solutions for difficult tasks, which is a limitation of many other techniques including convolutional neural networks (CNNs).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Genetic Programming-Based Discriminative Feature Learning for Low-Quality Image Classification

Bi¹,

Xue²,

Zhang³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Being able to learn discriminative features from low-quality images has raised much attention recently due to their wide applications ranging from autonomous driving to safety surveillance. However, this task is difficult due to high variations across images, such as scale, rotation, illumination, and viewpoint, and distortions in images, such as blur, low contrast, and noise. Image preprocessing could improve the quality of the images, but it often requires human intervention and domain knowledge. Genetic programming (GP) with a flexible representation can automatically perform image preprocessing and feature extraction without human intervention. Therefore, this study proposes a new evolutionary learning approach using GP (EFLGP) to learn discriminative features from images with blur, low contrast, and noise for classification. In the proposed approach, we develop a new program structure (individual representation), a new function set, and a new terminal set. With these new designs, EFLGP can detect small regions from a large input low-quality image, select image operators to process the regions or detect features from the small regions, and output a flexible number of discriminative features. A set of commonly used image preprocessing operators is employed as functions in EFLGP to allow it to search for solutions that can effectively handle low-quality image data. The performance of EFLGP is comprehensively investigated on eight datasets of varying difficulty under the original (clean), blur, low contrast, and noise scenarios, and compared with a large number of benchmark methods using handcrafted features and deep features. The experimental results show that EFLGP achieves significantly better or similar results in most comparisons. The results also reveal that EFLGP is more invariant than the benchmark methods to blur, low contrast, and noise.

show abstract

“…Furthermore, the decision trees (J48) classification approach [74] although provides interpretable solutions, but does not perform well when there are complex interactions between features. Moreover, the recently developed classification methods using genetic programming (GP) [43,44] have mostly used only gray-scale pixel statistics, which may not capture all the information from skin cancer images where variation in color is an important distinguishing characteristic between classes, as evident from the results shown in [167,95,154]. GP has been mostly explored for general image classification [16,44] and object detection [213] problems, and its applicability to domain-specific applications still needs investigation.…”

Section: Problem Statementmentioning

confidence: 99%

Genetic Programming based Feature Manipulation for Skin Cancer Image Classification

Ain¹

View full text Add to dashboard Cite

<p>Skin image classification involves the development of computational methods for solving problems such as cancer detection in lesion images, and their use for biomedical research and clinical care. Such methods aim at extracting relevant information or knowledge from skin images that can significantly assist in the early detection of disease. Skin images are enormous, and come with various artifacts that hinder effective feature extraction leading to inaccurate classification. Feature selection and feature construction can significantly reduce the amount of data while improving classification performance by selecting prominent features and constructing high-level features. Existing approaches mostly rely on expert intervention and follow multiple stages for pre-processing, feature extraction, and classification, which decreases the reliability, and increases the computational complexity. Since good generalization accuracy is not always the primary objective, clinicians are also interested in analyzing specific features such as pigment network, streaks, and blobs responsible for developing the disease; interpretable methods are favored. In Evolutionary Computation, Genetic Programming (GP) can automatically evolve an interpretable model and address the curse of dimensionality (through feature selection and construction). GP has been successfully applied to many areas, but its potential for feature selection, feature construction, and classification in skin images has not been thoroughly investigated. The overall goal of this thesis is to develop a new GP approach to skin image classification by utilizing GP to evolve programs that are capable of automatically selecting prominent image features, constructing new high level features, interpreting useful image features which can help dermatologist to diagnose a type of cancer, and are robust to processing skin images captured from specialized instruments and standard cameras. This thesis focuses on utilizing a wide range of texture, color, frequency-based, local, and global image properties at the terminal nodes of GP to classify skin cancer images from multiple modalities effectively. This thesis develops new two-stage GP methods using embedded and wrapper feature selection and construction approaches to automatically generating a feature vector of selected and constructed features for classification. The results show that wrapper approach outperforms the embedded approach, the existing baseline GP and other machine learning methods, but the embedded approach is faster than the wrapper approach. This thesis develops a multi-tree GP based embedded feature selection approach for melanoma detection using domain specific and domain independent features. It explores suitable crossover and mutation operators to evolve GP classifiers effectively and further extends this approach using a weighted fitness function. The results show that these multi-tree approaches outperformed single tree GP and other classification methods. They identify that a specific feature extraction method extracts most suitable features for particular images taken from a specific optical instrument. This thesis develops the first GP method utilizing frequency-based wavelet features, where the wrapper based feature selection and construction methods automatically evolve useful constructed features to improve the classification performance. The results show the evidence of successful feature construction by significantly outperforming existing GP approaches, state-of-the-art CNN, and other classification methods. This thesis develops a GP approach to multiple feature construction for ensemble learning in classification. The results show that the ensemble method outperformed existing GP approaches, state-of-the-art skin image classification, and commonly used ensemble methods. Further analysis of the evolved constructed features identified important image features that can potentially help the dermatologist identify further medical procedures in real-world situations.</p>

show abstract

Genetic Programming With Image-Related Operators and a Flexible Program Structure for Feature Learning in Image Classification

Cited by 60 publications

References 48 publications

Automatic Feature Extraction and Construction Using Genetic Programming for Rotating Machinery Fault Diagnosis

Automatic Feature Extraction and Construction Using Genetic Programming for Rotating Machinery Fault Diagnosis

Genetic Programming-Based Discriminative Feature Learning for Low-Quality Image Classification

Genetic Programming based Feature Manipulation for Skin Cancer Image Classification

Contact Info

Product

Resources

About