Genetic Programming for Automatically Synthesising Robust Image Descriptors with A Small Number of Instances

<p>Image classification is a core task in many applications of computer vision, including object detection and recognition. It aims at analysing the visual content and automatically categorising a set of images into different groups. Performing image classification can largely be affected by the features used to perform this task. Extracting features from images is a challenging task due to the large search space size and practical requirements such as domain knowledge and human intervention. Human intervention is usually needed to identify a good set of keypoints (regions of interest), design a set of features to be extracted from those keypoints such as lines and corners, and develop a way to extract those features. Automating these tasks has great potential to dramatically decrease the time and cost, and may potentially improve the performance of the classification task. There are two well-recognised approaches in the literature to automate the processes of identifying keypoints and extracting image features. Designing a set of domain-independent features is the first approach, where the focus is on dividing the image into a number of predefined regions and extracting features from those regions. The second approach is synthesising a function or a set of functions to form an image descriptor that aims at automatically detecting a set of keypoints such as lines and corners, and performing feature extraction. Although employing image descriptors is more effective and very popular in the literature, designing those descriptors is a difficult task that in most cases requires domain-expert intervention. The overall goal of this thesis is to develop a new domain independent Genetic Programming (GP) approach to image classification by utilising GP to evolve programs that are capable of automatically detecting diverse and informative keypoints, designing a set of features, and performing feature extraction using only a small number of training instances to facilitate image classification, and are robust to different image changes such as illumination and rotation. This thesis focuses on incorporating a variety of simple arithmetic operators and first-order statistics (mid-level features) into the evolutionary process and on representation of GP to evolve programs that are robust to image changes for image classification. This thesis proposes methods for domain-independent binary classification in images using GP to automatically identify regions within an image that have the potential to improve classification while considering the limitation of having a small training set. Experimental results show that in over 67% of cases the new methods significantly outperform the use of existing hand-crafted features and features automatically detected by other methods. This thesis proposes the first GP approach for automatically evolving an illumination-invariant dense image descriptor that detects automatically designed keypoints, and performs feature extraction using only a few instances of each class. The experimental results show improvement of 86% on average compared to two GP-based methods, and can significantly outperform domain-expert hand-crafted descriptors in more than 89% of the cases. This thesis also considers rotation variation of images and proposes a method for automatically evolving rotation-invariant image descriptors through integrating a set of first-order statistics as terminals. Compared to hand-crafted descriptors, the experimental results reveal that the proposed method has significantly better performance in more than 83% of the cases. This thesis proposes a new GP representation that allows the system to automatically choose the length of the feature vector side-by-side with evolving an image descriptor. Automatically determining the length of the feature vector helps to reduce the number of the parameters to be set. The results show that this method has evolved descriptors with a very small feature vector which yet still significantly outperform the competitive methods in more than 91% of the cases. This thesis proposes a method for transfer learning by model in GP, where an image descriptor evolved on instances of a related problem (source domain) is applied directly to solve a problem being tackled (target domain). The results show that the new method evolves image descriptors that have better generalisability compared to hand-crafted image descriptors. Those automatically evolved descriptors show positive influence on classifying the target domain datasets in more than 56% of the cases.</p>

Genetic Programming for Automatically Synthesising Robust Image Descriptors with A Small Number of Instances

<p>Image classification is a core task in many applications of computer vision, including object detection and recognition. It aims at analysing the visual content and automatically categorising a set of images into different groups. Performing image classification can largely be affected by the features used to perform this task. Extracting features from images is a challenging task due to the large search space size and practical requirements such as domain knowledge and human intervention. Human intervention is usually needed to identify a good set of keypoints (regions of interest), design a set of features to be extracted from those keypoints such as lines and corners, and develop a way to extract those features. Automating these tasks has great potential to dramatically decrease the time and cost, and may potentially improve the performance of the classification task. There are two well-recognised approaches in the literature to automate the processes of identifying keypoints and extracting image features. Designing a set of domain-independent features is the first approach, where the focus is on dividing the image into a number of predefined regions and extracting features from those regions. The second approach is synthesising a function or a set of functions to form an image descriptor that aims at automatically detecting a set of keypoints such as lines and corners, and performing feature extraction. Although employing image descriptors is more effective and very popular in the literature, designing those descriptors is a difficult task that in most cases requires domain-expert intervention. The overall goal of this thesis is to develop a new domain independent Genetic Programming (GP) approach to image classification by utilising GP to evolve programs that are capable of automatically detecting diverse and informative keypoints, designing a set of features, and performing feature extraction using only a small number of training instances to facilitate image classification, and are robust to different image changes such as illumination and rotation. This thesis focuses on incorporating a variety of simple arithmetic operators and first-order statistics (mid-level features) into the evolutionary process and on representation of GP to evolve programs that are robust to image changes for image classification. This thesis proposes methods for domain-independent binary classification in images using GP to automatically identify regions within an image that have the potential to improve classification while considering the limitation of having a small training set. Experimental results show that in over 67% of cases the new methods significantly outperform the use of existing hand-crafted features and features automatically detected by other methods. This thesis proposes the first GP approach for automatically evolving an illumination-invariant dense image descriptor that detects automatically designed keypoints, and performs feature extraction using only a few instances of each class. The experimental results show improvement of 86% on average compared to two GP-based methods, and can significantly outperform domain-expert hand-crafted descriptors in more than 89% of the cases. This thesis also considers rotation variation of images and proposes a method for automatically evolving rotation-invariant image descriptors through integrating a set of first-order statistics as terminals. Compared to hand-crafted descriptors, the experimental results reveal that the proposed method has significantly better performance in more than 83% of the cases. This thesis proposes a new GP representation that allows the system to automatically choose the length of the feature vector side-by-side with evolving an image descriptor. Automatically determining the length of the feature vector helps to reduce the number of the parameters to be set. The results show that this method has evolved descriptors with a very small feature vector which yet still significantly outperform the competitive methods in more than 91% of the cases. This thesis proposes a method for transfer learning by model in GP, where an image descriptor evolved on instances of a related problem (source domain) is applied directly to solve a problem being tackled (target domain). The results show that the new method evolves image descriptors that have better generalisability compared to hand-crafted image descriptors. Those automatically evolved descriptors show positive influence on classifying the target domain datasets in more than 56% of the cases.</p>

On the Effectiveness of Leukocytes Classification Methods in a Real Application Scenario

Automating the analysis of digital microscopic images to identify the cell sub-types or the presence of illness has assumed a great importance since it aids the laborious manual process of review and diagnosis. In this paper, we have focused on the analysis of white blood cells. They are the body’s main defence against infections and diseases and, therefore, their reliable classification is very important. Current systems for leukocyte analysis are mainly dedicated to: counting, sub-types classification, disease detection or classification. Although these tasks seem very different, they share many steps in the analysis process, especially those dedicated to the detection of cells in blood smears. A very accurate detection step gives accurate results in the classification of white blood cells. Conversely, when detection is not accurate, it can adversely affect classification performance. However, it is very common in real-world applications that work on inaccurate or non-accurate regions. Many problems can affect detection results. They can be related to the quality of the blood smear images, e.g., colour and lighting conditions, absence of standards, or even density and presence of overlapping cells. To this end, we performed an in-depth investigation of the above scenario, simulating the regions produced by detection-based systems. We exploit various image descriptors combined with different classifiers, including CNNs, in order to evaluate which is the most suitable in such a scenario, when performing two different tasks: Classification of WBC subtypes and Leukaemia detection. Experimental results have shown that Convolutional Neural Networks are very robust in such a scenario, outperforming common machine learning techniques combined with hand-crafted descriptors. However, when exploiting appropriate images for model training, even simpler approaches can lead to accurate results in both tasks.

Machine Learning-Based Facial Beauty Prediction and Analysis of Frontal Facial Images Using Facial Landmarks and Traditional Image Descriptors

The beauty industry has seen rapid growth in multiple countries and due to its applications in entertainment, the analysis and assessment of facial attractiveness have received attention from scientists, physicians, and artists because of digital media, plastic surgery, and cosmetics. An analysis of techniques is used in the assessment of facial beauty that considers facial ratios and facial qualities as elements to predict facial beauty. Here, the facial landmarks are extracted to calculate facial ratios according to Golden Ratios and Symmetry Ratios, and an ablation study is performed to find the best performing feature set from extracted ratios. Subsequently, Gray Level Covariance Matrix (GLCM), Hu’s Moments, and Color Histograms in the HSV space are extracted as texture, shape, and color features, respectively. Another ablation study is performed to find out which feature performs the best when concatenated with the facial landmarks. Experimental results show that the concatenation of primary facial characteristics with facial landmarks improved the prediction score of facial beauty. Four models are trained, K-Nearest Neighbors (KNN), Linear Regression (LR), Random Forest (RF), and Artificial Neural Network (ANN) on a dataset of 5500 frontal facial images, and amongst them, KNN performs the best for the concatenated features achieving a Pearson’s Correlation Coefficient of 0.7836 and a Mean Squared Error of 0.0963. Our analysis also provides us with insights into how different machine learning models can understand the concept of facial beauty.

Quaternion fractional-order color orthogonal moment-based image representation and recognition

Inspired by quaternion algebra and the idea of fractional-order transformation, we propose a new set of quaternion fractional-order generalized Laguerre orthogonal moments (QFr-GLMs) based on fractional-order generalized Laguerre polynomials. Firstly, the proposed QFr-GLMs are directly constructed in Cartesian coordinate space, avoiding the need for conversion between Cartesian and polar coordinates; therefore, they are better image descriptors than circularly orthogonal moments constructed in polar coordinates. Moreover, unlike the latest Zernike moments based on quaternion and fractional-order transformations, which extract only the global features from color images, our proposed QFr-GLMs can extract both the global and local color features. This paper also derives a new set of invariant color-image descriptors by QFr-GLMs, enabling geometric-invariant pattern recognition in color images. Finally, the performances of our proposed QFr-GLMs and moment invariants were evaluated in simulation experiments of correlated color images. Both theoretical analysis and experimental results demonstrate the value of the proposed QFr-GLMs and their geometric invariants in the representation and recognition of color images.