scholarly journals Binary Image Classification: A Genetic Programming Approach to the Problem of Limited Training Instances

2016 ◽  
Vol 24 (1) ◽  
pp. 143-182 ◽  
Author(s):  
Harith Al-Sahaf ◽  
Mengjie Zhang ◽  
Mark Johnston
Keyword(s):  
Computer Vision ◽  
Pattern Recognition ◽  
Genetic Programming ◽  
Visual System ◽  
Image Classification ◽  
Human Visual System ◽  
Binary Classification ◽  
Programming Approach ◽  
Data Sets ◽  
New Class

In the computer vision and pattern recognition fields, image classification represents an important yet difficult task. It is a challenge to build effective computer models to replicate the remarkable ability of the human visual system, which relies on only one or a few instances to learn a completely new class or an object of a class. Recently we proposed two genetic programming (GP) methods, one-shot GP and compound-GP, that aim to evolve a program for the task of binary classification in images. The two methods are designed to use only one or a few instances per class to evolve the model. In this study, we investigate these two methods in terms of performance, robustness, and complexity of the evolved programs. We use ten data sets that vary in difficulty to evaluate these two methods. We also compare them with two other GP and six non-GP methods. The results show that one-shot GP and compound-GP outperform or achieve results comparable to competitor methods. Moreover, the features extracted by these two methods improve the performance of other classifiers with handcrafted features and those extracted by a recently developed GP-based method in most cases.

scholarly journals Binary image classification: A genetic programming approach to the problem of limited training instances

2020 ◽  
Author(s):  
Harith Al-Sahaf ◽  
Mengjie Zhang ◽  
M Johnston
Keyword(s):  
Pattern Recognition ◽  
Genetic Programming ◽  
Image Classification ◽  
Binary Classification ◽  
Programming Approach ◽  
Data Sets ◽  
Massachusetts Institute ◽  
Massachusetts Institute Of Technology ◽  
New Class ◽  
Institute Of Technology

© 2016 by the Massachusetts Institute of Technology. In the computer vision and pattern recognition fields, image classification represents an important yet difficult task. It is a challenge to build effective computer models to replicate the remarkable ability of the human visual system, which relies on only one or a few instances to learn a completely new class or an object of a class. Recently we proposed two genetic programming (GP) methods, one-shot GP and compound-GP, that aim to evolve a program for the task of binary classification in images. The two methods are designed to use only one or a few instances per class to evolve the model. In this study, we investigate these two methods in terms of performance, robustness, and complexity of the evolved programs. We use ten data sets that vary in difficulty to evaluate these two methods. We also compare them with two other GP and six non-GP methods. The results show that one-shot GP and compound-GP outperform or achieve results comparable to competitor methods. Moreover, the features extracted by these two methods improve the performance of other classifiers with handcrafted features and those extracted by a recently developed GP-based method in most cases.

scholarly journals Binary image classification: A genetic programming approach to the problem of limited training instances

2020 ◽  
Author(s):  
Harith Al-Sahaf ◽  
Mengjie Zhang ◽  
M Johnston
Keyword(s):  
Pattern Recognition ◽  
Genetic Programming ◽  
Image Classification ◽  
Binary Classification ◽  
Programming Approach ◽  
Data Sets ◽  
Massachusetts Institute ◽  
Massachusetts Institute Of Technology ◽  
New Class ◽  
Institute Of Technology

© 2016 by the Massachusetts Institute of Technology. In the computer vision and pattern recognition fields, image classification represents an important yet difficult task. It is a challenge to build effective computer models to replicate the remarkable ability of the human visual system, which relies on only one or a few instances to learn a completely new class or an object of a class. Recently we proposed two genetic programming (GP) methods, one-shot GP and compound-GP, that aim to evolve a program for the task of binary classification in images. The two methods are designed to use only one or a few instances per class to evolve the model. In this study, we investigate these two methods in terms of performance, robustness, and complexity of the evolved programs. We use ten data sets that vary in difficulty to evaluate these two methods. We also compare them with two other GP and six non-GP methods. The results show that one-shot GP and compound-GP outperform or achieve results comparable to competitor methods. Moreover, the features extracted by these two methods improve the performance of other classifiers with handcrafted features and those extracted by a recently developed GP-based method in most cases.

scholarly journals A One-shot Learning Approach to Image Classification using Genetic Programming

2020 ◽  
Author(s):  
Harith Al-Sahaf ◽  
Mengjie Zhang ◽  
M Johnston
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Genetic Programming ◽  
Image Classification ◽  
Local Binary Patterns ◽  
Support Vector ◽  
Learning Approach ◽  
Data Sets ◽  
Domain Specific ◽  
International Publishing

In machine learning, it is common to require a large number of instances to train a model for classification. In many cases, it is hard or expensive to acquire a large number of instances. In this paper, we propose a novel genetic programming (GP) based method to the problem of automatic image classification via adopting a one-shot learning approach. The proposed method relies on the combination of GP and Local Binary Patterns (LBP) techniques to detect a predefined number of informative regions that aim at maximising the between-class scatter and minimising the within-class scatter. Moreover, the proposed method uses only two instances of each class to evolve a classifier. To test the effectiveness of the proposed method, four different texture data sets are used and the performance is compared against two other GP-based methods namely Conventional GP and Two-tier GP. The experiments revealed that the proposed method outperforms these two methods on all the data sets. Moreover, a better performance has been achieved by Naïve Bayes, Support Vector Machine, and Decision Trees (J48) methods when extracted features by the proposed method have been used compared to the use of domain-specific and Two-tier GP extracted features. © Springer International Publishing 2013.

scholarly journals An Automatic Feature Extraction Approach to Image Classification Using Genetic Programming

2020 ◽  
Author(s):  
Ying Bi ◽  
Bing Xue ◽  
Mengjie Zhang
Keyword(s):  
Feature Extraction ◽  
Genetic Programming ◽  
Image Classification ◽  
Image Data ◽  
Data Sets ◽  
Automatic Feature Extraction ◽  
Terminal Set ◽  
Comparable Performance ◽  
International Publishing ◽  
High Level

© Springer International Publishing AG, part of Springer Nature 2018. Feature extraction is an essential process for image data dimensionality reduction and classification. However, feature extraction is very difficult and often requires human intervention. Genetic Programming (GP) can achieve automatic feature extraction and image classification but the majority of existing methods extract low-level features from raw images without any image-related operations. Furthermore, the work on the combination of image-related operators/descriptors in GP for feature extraction and image classification is limited. This paper proposes a multi-layer GP approach (MLGP) to performing automatic high-level feature extraction and classification. A new program structure, a new function set including a number of image operators/descriptors and two region detectors, and a new terminal set are designed in this approach. The performance of the proposed method is examined on six different data sets of varying difficulty and compared with five GP based methods and 42 traditional image classification methods. Experimental results show that the proposed method achieves better or comparable performance than these baseline methods. Further analysis on the example programs evolved by the proposed MLGP method reveals the good interpretability of MLGP and gives insight into how this method can effectively extract high-level features for image classification.

scholarly journals Biologically Inspired Visual System Architecture for Object Recognition in Autonomous Systems

Algorithms ◽  
2020 ◽  
Vol 13 (7) ◽  
pp. 167 ◽  
Author(s):  
Dan Malowany ◽  
Hugo Guterman
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Object Recognition ◽  
Visual System ◽  
Human Visual System ◽  
State Of The Art ◽  
Top Down ◽  
Feed Forward ◽  
Recognition Process ◽  
The World

Computer vision is currently one of the most exciting and rapidly evolving fields of science, which affects numerous industries. Research and development breakthroughs, mainly in the field of convolutional neural networks (CNNs), opened the way to unprecedented sensitivity and precision in object detection and recognition tasks. Nevertheless, the findings in recent years on the sensitivity of neural networks to additive noise, light conditions, and to the wholeness of the training dataset, indicate that this technology still lacks the robustness needed for the autonomous robotic industry. In an attempt to bring computer vision algorithms closer to the capabilities of a human operator, the mechanisms of the human visual system was analyzed in this work. Recent studies show that the mechanisms behind the recognition process in the human brain include continuous generation of predictions based on prior knowledge of the world. These predictions enable rapid generation of contextual hypotheses that bias the outcome of the recognition process. This mechanism is especially advantageous in situations of uncertainty, when visual input is ambiguous. In addition, the human visual system continuously updates its knowledge about the world based on the gaps between its prediction and the visual feedback. CNNs are feed forward in nature and lack such top-down contextual attenuation mechanisms. As a result, although they process massive amounts of visual information during their operation, the information is not transformed into knowledge that can be used to generate contextual predictions and improve their performance. In this work, an architecture was designed that aims to integrate the concepts behind the top-down prediction and learning processes of the human visual system with the state-of-the-art bottom-up object recognition models, e.g., deep CNNs. The work focuses on two mechanisms of the human visual system: anticipation-driven perception and reinforcement-driven learning. Imitating these top-down mechanisms, together with the state-of-the-art bottom-up feed-forward algorithms, resulted in an accurate, robust, and continuously improving target recognition model.

2D and 3D Visual Attention for Computer Vision

2016 ◽  
pp. 1-44
Author(s):  
Vincent Ricordel ◽  
Junle Wang ◽  
Matthieu Perreira Da Silva ◽  
Patrick Le Callet
Keyword(s):  
Computer Vision ◽  
Visual Perception ◽  
Visual Attention ◽  
Visual System ◽  
Computational Modeling ◽  
Depth Perception ◽  
Human Visual System ◽  
Visual Importance ◽  
2D And 3D ◽  
The Impact

Visual attention is one of the most important mechanisms deployed in the human visual system (HVS) to reduce the amount of information that our brain needs to process. An increasing amount of efforts has been dedicated to the study of visual attention, and this chapter proposes to clarify the advances achieved in computational modeling of visual attention. First the concepts of visual attention, including the links between visual salience and visual importance, are detailed. The main characteristics of the HVS involved in the process of visual perception are also explained. Next we focus on eye-tracking, because of its role in the evaluation of the performance of the models. A complete state of the art in computational modeling of visual attention is then presented. The research works that extend some visual attention models to 3D by taking into account of the impact of depth perception are finally explained and compared.

Technical Vision Model of the Visual Systems for Industry Application

2021 ◽  
pp. 288-310
Author(s):  
Oleg Sytnik ◽  
Vladimir Kartashov
Keyword(s):  
Image Processing ◽  
Pattern Recognition ◽  
Visual System ◽  
Mathematical Models ◽  
Human Visual System ◽  
Vision System ◽  
Vision Systems ◽  
Industrial Systems ◽  
Visual Systems ◽  
Technical Vision

The problems of highlighting the main informational aspects of images and creating their adequate models are discussed in the chapter. Vision systems can receive information about an object in different frequency ranges and in a form that is not accessible to the human visual system. Vision systems distort the information contained in the image. Therefore, to create effective image processing and transmission systems, it is necessary to formulate mathematical models of signals and interference. The chapter discusses the features of perception by the human visual system and the issues of harmonizing the technical characteristics of industrial systems for receiving and transmitting images. Methods and algorithms of pattern recognition are discussed. The problem of conjugation of the characteristics of the technical vision system with the consumer of information is considered.

Is depth information and optical flow helpful for visual control?

2016 ◽  
Vol 12 (1) ◽  
Author(s):  
Johannes Hansen ◽  
Marc Ebner
Keyword(s):  
Genetic Programming ◽  
Visual System ◽  
Optical Flow ◽  
Human Visual System ◽  
Visual Control ◽  
Depth Information ◽  
Artificial Evolution ◽  
Natural Evolution ◽  
Color Depth

AbstractThe human visual system was shaped through natural evolution. We have used artificial evolution to investigate whether depth information and optical flow are helpful for visual control. Our experiments were carried out in simulation. The task was controlling a simulated racing car. We have used The Open Racing Car Simulator for our experiments. Genetic programming was used to evolve visual algorithms that transform input images (color, optical flow, or depth information) to control commands for a simulated racing car. We found that significantly better solutions were found when color, depth, and optical flow were available as input together compared with color, depth, or optical flow alone.

scholarly journals Garment smoothness appearance evaluation through computer vision

2011 ◽  
Vol 82 (3) ◽  
pp. 299-309 ◽  
Author(s):  
Javier Silvestre-Blanes ◽  
Joaquin Berenguer-Sebastiá ◽  
Rubén Pérez-Lloréns ◽  
Ignacio Miralles ◽  
Jorge Moreno
Keyword(s):  
Computer Vision ◽  
Visual System ◽  
Human Visual System ◽  
Evaluation System ◽  
Human Perception ◽  
Measurement And Evaluation ◽  
Different Parts ◽  
Textile Products

The measurement and evaluation of the appearance of wrinkling in textile products after domestic washing and drying is performed currently by the comparison of the fabric with the replicas. This kind of evaluation has certain drawbacks, the most significant of which are its subjectivity and its limitations when used with garments. In this paper, we present an automated wrinkling evaluation system. The system developed can process fabrics as well as any type of garment, independent of size or pattern on the material. The system allows us to label different parts of the garment. Thus, as different garment parts have different influence on human perception, this labeling enables the use of weighting, to improve the correlation with the human visual system. The system has been tested with different garments showing good performance and correlation with human perception.

Sign in / Sign up

Export Citation Format

Share Document