%0 Journal Article %1 Bhosle_2015 %A Bhosle, Shrikant %A Khanale, Dr. Prakash %D 2015 %I Auricle Technologies, Pvt., Ltd. %J International Journal on Recent and Innovation Trends in Computing and Communication %K Algorithm Analysis CBIR Distance Extraction Feature Features GLCM Method Metrics Statistical Texture %N 4 %P 1910--1917 %R 10.17762/ijritcc2321-8169.150434 %T Comparison of Different Distance Metrics to Find Similarity between Images In CBIR System %U http://dx.doi.org/10.17762/ijritcc2321-8169.150434 %V 3 %X Content based image retrieval use low level feature (color, shape, texture) of image for retrieving similar image from image database. This paper presents a novel system for texture feature extraction from grayscale images using gray level co-occurrence matrix (GLCM). It works on statistical texture feature of image. Texture feature of image is referred to as repeated homogenous pattern in an image. This texture feature is classified into three categories Statistical, structural and spectral. Among these we extract second order statistical texture feature from image using GLCM. These features are Energy, correlation, contrast, homogeneity, entropy. Different distance metrics are used to find the similarity between images. The experiment is conducted on own texture database. Accuracy of result and time complexity of design algorithm for CBIR system is calculated.

@article{Bhosle_2015, abstract = {Content based image retrieval use low level feature (color, shape, texture) of image for retrieving similar image from image database. This paper presents a novel system for texture feature extraction from grayscale images using gray level co-occurrence matrix (GLCM). It works on statistical texture feature of image. Texture feature of image is referred to as repeated homogenous pattern in an image. This texture feature is classified into three categories Statistical, structural and spectral. Among these we extract second order statistical texture feature from image using GLCM. These features are Energy, correlation, contrast, homogeneity, entropy. Different distance metrics are used to find the similarity between images. The experiment is conducted on own texture database. Accuracy of result and time complexity of design algorithm for CBIR system is calculated.}, added-at = {2015-08-19T06:32:30.000+0200}, author = {Bhosle, Shrikant and Khanale, Dr. Prakash}, biburl = {https://www.bibsonomy.org/bibtex/2593625bcf4175f23435fcf4ab42ce98e/ijritcc}, doi = {10.17762/ijritcc2321-8169.150434}, interhash = {d53ea0b7a817d555dd95b41e27ed66d9}, intrahash = {593625bcf4175f23435fcf4ab42ce98e}, journal = {International Journal on Recent and Innovation Trends in Computing and Communication}, keywords = {Algorithm Analysis CBIR Distance Extraction Feature Features GLCM Method Metrics Statistical Texture}, month = {april}, number = 4, pages = {1910--1917}, publisher = {Auricle Technologies, Pvt., Ltd.}, timestamp = {2015-08-19T06:32:30.000+0200}, title = {Comparison of Different Distance Metrics to Find Similarity between Images In {CBIR} System}, url = {http://dx.doi.org/10.17762/ijritcc2321-8169.150434}, volume = 3, year = 2015 }