Open Access Open Access  Restricted Access Subscription Access

A Survey of Content Based Image Retrieval Using Color and Texture Features


Affiliations
1 Assistant Professor, Department of Computer Science and Engineering, Modern Institute of Technology & Research Center, Alwar, Rajasthan, India - 301028, India
2 Assistant Professor, Department of Computer Science and Engineering, Modern Institute of Technology & Research Center, Alwar, Rajasthan, India - 301028, India

   Subscribe/Renew Journal


Content based image retrieval (CBIR) system that works on the basis of low level image semantics cannot be directly related to the expressive semantics that is used by humans for deciding image similarities. The low-level semantic of the image consists of color, texture, and shape of the object inside an image. Nowadays, one type of feature extraction technique cannot provide complete result, so now a combination of different feature techniques like color, texture and shape features are being used. There is a generous increase in retrieval precision when combinations of these techniques are used in an effective way. In this paper, we propose a comparison of CBIR system using different feature extraction methods; three features based on color (i.e. HSV Histogram, Color Moment) and other two features computed by applying the texture feature using Gabor Wavelet and Wavelet Transform of the image. For similarity matching between the query image and database images, Manhattan distance or City Block or L1 distance is used. The experimental results on WANG database show higher retrieval efficiency in terms of precision when compared with existing methods using color and texture features.

Keywords

Content based image retrieval, HSV Histogram, Color Moment, Gabor wavelet and Wavelet Transform
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 313

PDF Views: 0




  • A Survey of Content Based Image Retrieval Using Color and Texture Features

Abstract Views: 313  |  PDF Views: 0

Authors

Beerbal Solanki
Assistant Professor, Department of Computer Science and Engineering, Modern Institute of Technology & Research Center, Alwar, Rajasthan, India - 301028, India
Manish Jain
Assistant Professor, Department of Computer Science and Engineering, Modern Institute of Technology & Research Center, Alwar, Rajasthan, India - 301028, India

Abstract


Content based image retrieval (CBIR) system that works on the basis of low level image semantics cannot be directly related to the expressive semantics that is used by humans for deciding image similarities. The low-level semantic of the image consists of color, texture, and shape of the object inside an image. Nowadays, one type of feature extraction technique cannot provide complete result, so now a combination of different feature techniques like color, texture and shape features are being used. There is a generous increase in retrieval precision when combinations of these techniques are used in an effective way. In this paper, we propose a comparison of CBIR system using different feature extraction methods; three features based on color (i.e. HSV Histogram, Color Moment) and other two features computed by applying the texture feature using Gabor Wavelet and Wavelet Transform of the image. For similarity matching between the query image and database images, Manhattan distance or City Block or L1 distance is used. The experimental results on WANG database show higher retrieval efficiency in terms of precision when compared with existing methods using color and texture features.

Keywords


Content based image retrieval, HSV Histogram, Color Moment, Gabor wavelet and Wavelet Transform



DOI: https://doi.org/10.17010/ijcs%2F2018%2Fv3%2Fi6%2F141444