Visual Schemas in Neural Networks for Object Recognition and Scene Analysis

Leow, Wee Kheng; Miikkulainen, Risto

doi:10.1080/095400997116676

Cited by 8 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These rules describe the characteristic properties of objects of different types. Some examples of such work include SCHEMA vision system by Draper et al [12], region-based scene analysis by Ohta [34], and VISOR connectionist system for scene analysis [28]. Although these approaches have shown reasonable results, a significant amount of computational effort is required even for simple scenes.…”

mentioning

confidence: 99%

Neural network analysis of MINERVA scene image benchmark

Markou

Singh

2005

Neural Comput & Applic

View full text Add to dashboard Cite

Scene analysis is an important area of research with the aim of identifying objects and their relationships in natural scenes. MINERVA benchmark has been recently introduced in this area for testing different image processing and classification schemes. In this paper we present results on the classification of eight natural objects in the complete set of 448 natural images using neural networks. An exhaustive set of experiments with this benchmark has been conducted using four different segmentation methods and five texture-based feature extraction methods. The results in this paper show the performance of a neural network classifier on a tenfold cross-validation task. On the basis of the results produced, we are able to rank how well different image segmentation algorithms are suited to the task of region of interest identification in these images, and we also see how well texture extraction algorithms rank on the basis of classification results. Scene analysisOutdoor scene analysis is a complex problem. A number of different approaches have been used for recognising different objects in such scenes. In early experiments on scene analysis, simple problems were tackled. For example, Brice and Fennema [7] defined the procedure to interpret simple objects in images such as wedges, cubes, wall and floor. Model-based approaches, such as the one proposed by Brooks [8], have met with some success, provided that objects can be defined with geometric primitives. These approaches have problems with recognising natural objects such as trees, for example, where such primitives are hard to define. Another approach is based on the use of a knowledge-based scheme where hand-coded rules are used for object recognition. These rules describe the characteristic properties of objects of different types. Some examples of such work include SCHEMA vision system by Draper et al. [12], region-based scene analysis by Ohta [34], and VISOR connectionist system for scene analysis [28]. Although these approaches have shown reasonable results, a significant amount of computational effort is required even for simple scenes. More recently, far more complex problems are being solved using texture-based image analysis. The thesis of Becalick [5] and MacKeown [30] provides an excellent review treatment of other studies in this area and summarise the progress made. In particular, Becalick reviews important studies based on knowledge-based approaches in scene analysis, Autonomous Ground Vehicle (AGV) research, and image database and multimedia search.Batlle et al.[4] review a number of studies in the area of scene analysis for urban and natural scene classification. Campani et al. [9], and Parodi and Piccioli [35] have used colour information in the classification of natural objects including road boundaries, road signs, vehicles, buildings and trees. Colour information has also been used by the following authors: Draper et al. [12], and Hanson and Riseman [15] for the discrimination of objects (road scenes) including sky,

show abstract

mentioning

confidence: 99%

Neural network analysis of MINERVA scene image benchmark

Markou

Singh

2005

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…The pre-processing module (also present in biological vision systems [6]) executes a series of transformations in the image, so that the subsequent module (Characteristics Extractor) may extract its intrinsic characteristics. The input to the pre-processing module is a matrix of pixels (also called "raw image"), obtained through methods that transform captured light signals into electrical signals.…”

Section: Systemmentioning

confidence: 99%

Classification of bidimensional images using artificial intelligence techniques

Perelmuter

Pereira²,

Vellasco³

et al.

Proceedings II Workshop on Cybernetic Vision

View full text Add to dashboard Cite

This article presents the structure of an "intelligent classifier" composed of three modules: the preprocessor, responsible for the transformation of the raw image; the characteristics extractor, implemented by a genetic algorithm, which is responsible for the selection of the most relevant coefficients; and the classifier, implemented by a neural network. Genetic algorithms have been used as a search technique for large sets of data and neural networks, due to their ability to extract information from complex sets of data, have been largely applied in comp,uter vision for pattern classification. The complete image classification system is invariant to translation, rotation and sizing of the analysed object.

show abstract

Computational Maps in the Visual Cortex

Miikkulainen¹,

Bednar

Choe

et al. 2005

View full text Add to dashboard Cite

Visual Schemas in Neural Networks for Object Recognition and Scene Analysis

Cited by 8 publications

References 39 publications

Neural network analysis of MINERVA scene image benchmark

Neural network analysis of MINERVA scene image benchmark

Classification of bidimensional images using artificial intelligence techniques

Computational Maps in the Visual Cortex

Contact Info

Product

Resources

About