Multi-Objective Genetic Programming for object detection

Liddle, Thomas; Johnston, Mark; Zhang, Mengjie

doi:10.1109/cec.2010.5586072

Cited by 20 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Watchareeruetai et al [38] have also adopted the MOGP for automatic construction of feature extractor. Liddle et al [39] have proposed a MOGP approach for the task of providing a decision-maker with a diverse set of alternative object detection programs that balance between high detection rate and low false-alarm rate. In addition, Olague and Trujillo [40] developed an MOGP approach for automated synthesis of operators that detect interest points.…”

Section: Related Workmentioning

confidence: 99%

Feature Learning for Image Classification Via Multiobjective Genetic Programming

Shao

Liu

2014

IEEE Trans. Neural Netw. Learning Syst.

288

224

View full text Add to dashboard Cite

Feature extraction is the first and most critical step in image classification. Most existing image classification methods use hand-crafted features, which are not adaptive for different image domains. In this paper, we develop an evolutionary learning methodology to automatically generate domain-adaptive global feature descriptors for image classification using multiobjective genetic programming (MOGP). In our architecture, a set of primitive 2-D operators are randomly combined to construct feature descriptors through the MOGP evolving and then evaluated by two objective fitness criteria, i.e., the classification error and the tree complexity. After the entire evolution procedure finishes, the best-so-far solution selected by the MOGP is regarded as the (near-)optimal feature descriptor obtained. To evaluate its performance, the proposed approach is systematically tested on the Caltech-101, the MIT urban and nature scene, the CMU PIE, and Jochen Triesch Static Hand Posture II data sets, respectively. Experimental results verify that our method significantly outperforms many state-of-the-art hand-designed features and two feature learning techniques in terms of classification accuracy

show abstract

Section: Related Workmentioning

confidence: 99%

Feature Learning for Image Classification Via Multiobjective Genetic Programming

Shao

Liu

2014

IEEE Trans. Neural Netw. Learning Syst.

288

224

View full text Add to dashboard Cite

show abstract

“…As future work, one promising approach can be to explicitly express the GP framework as multi-objective, as has been done in previous works [55][56][57][58][59][60][61]; this way, the relative importance between inter-class and intra-class distance of the examples can also be optimized, and novel objectives (e.g., precision and recall) can be considered.…”

Section: Discussionmentioning

confidence: 99%

A Soft Computing Approach for Selecting and Combining Spectral Bands

et al. 2020

View full text Add to dashboard Cite

We introduce a soft computing approach for automatically selecting and combining indices from remote sensing multispectral images that can be used for classification tasks. The proposed approach is based on a Genetic-Programming (GP) framework, a technique successfully used in a wide variety of optimization problems. Through GP, it is possible to learn indices that maximize the separability of samples from two different classes. Once the indices specialized for all the pairs of classes are obtained, they are used in pixelwise classification tasks. We used the GP-based solution to evaluate complex classification problems, such as those that are related to the discrimination of vegetation types within and between tropical biomes. Using time series defined in terms of the learned spectral indices, we show that the GP framework leads to superior results than other indices that are used to discriminate and classify tropical biomes.

show abstract

“…GP aims at automatically exploring the solution space in order to evolve a computer program (solution) for a user-defined problem (Koza, 1992). GP has been widely used to tackle the problems of image classification (Smart and Zhang, 2003;Zhang and Smart, 2004;Zhang and Johnston, 2009;Downey and Zhang, 2009;Atkins et al, 2011;Abdulhamid et al, 2011;Al-Sahaf et al, 2014b,a), object detection (Zhang and Ciesielski, 1999;Liddle et al, 2010), edge detection (Fu et al, 2011(Fu et al, , 2012, and image descriptor (Perez and Olague, 2009;Hindmarsh et al, 2012;Olague and Trujillo, 2011;Albukhanajer et al, 2014). A large number of the GP-based methods operate in two stages where feature detection and extraction is performed first, and evolving a classifier takes place second.…”

Section: Introductionmentioning

confidence: 99%

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

Al-Sahaf

Zhang

Johnston

2016

Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Multi-Objective Genetic Programming for object detection

Cited by 20 publications

References 20 publications

Feature Learning for Image Classification Via Multiobjective Genetic Programming

Feature Learning for Image Classification Via Multiobjective Genetic Programming

A Soft Computing Approach for Selecting and Combining Spectral Bands

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

Contact Info

Product

Resources

About