An Innovative Method for Retrieving Relevant Images by Getting the Top-ranked Images First Using Interactive Genetic Algorithm
| Autor: | K. Jaya Sudha, K. Valli Madhavi, R. Tamilkodi |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Color histogram
Similarity (geometry) Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Wavelet Transform 02 engineering and technology Interacrive Genetic algorithm 0202 electrical engineering electronic engineering information engineering False positive paradox Computer vision Texture Spatial analysis Image retrieval General Environmental Science CBIR business.industry Cognitive neuroscience of visual object recognition Wavelet transform 020207 software engineering Pattern recognition General Earth and Planetary Sciences 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | Procedia Computer Science. 79:254-261 |
| ISSN: | 1877-0509 |
| DOI: | 10.1016/j.procs.2016.03.033 |
| Popis: | The prime goal of the CBIR system is to construct meaningful descriptions of physical attributes from images. Physical features and mathematical features are two such typical descriptions. Many research efforts have been made to extract physical features such as color, texture, edge, structure or a combination of two or more. The majority of the proposed solutions are variations of the color histogram initially proposed for object recognition. Since color histogram lacked spatial information these methods were liable to produce false positives especially when the database was large. We proposed a method called image retrieval using interactive genetic algorithm (IRIGA) for computing a very large number of highly selective features and comparing these features for some relevant images and using only those selected features which capture similarity in the given relevant images for image retrieval. Experiments on a collection of 10 000 general-purpose images demonstrate the effectiveness of the proposed framework. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|