Multimodel Local Terenary Patterns for Content Based Image Retrieval

Abstract

CBIR is the field of digital media that plays important role for extraction of relevant information from media dataset based on various contents. These contents are signals, shapes, and texture and colour compositions. Texture feature provide information about the background of the images and content of the images. LBP has been widely used for texture feature extraction. LBP has major drawback of sensitivity to noise and irregularity at edges. In this paper a novel approach has been utilized for texture feature extraction from the colour images. LTP approach has been used for feature extraction from the colour images so that effective information about the image regions has been computed. Texture features have been computed by decomposing image into various small regions and these features have been concatenated to a single vector. On the basis of proposed model performance we can analyse that proposed system provide better result than existing one.