Multiscale Texture Analysis and Color Coherence Vector Based Feature Descriptor for Multispectral Image Retrieval

Abstract

Content Based Image Retrieval (CBIR) for remote sensing image data is a tedious process due to high resolution and complexity of image interpretation. Development of feature extraction technique is a major portion to represent the image content in an optimal way. In this paper, we propose a feature descriptor which combines the color coherent pixel information and GLCM texture features in multi scale domain. Curvelet transform is used to decompose the image into coarse and detail coefficients. Then Gabor magnitude is computed for each coefficient to improve the directional information. GLCM texture features are extracted from the Gabor magnitude response. The novel feature set by combining the CCV and GLCM using curvelet and Gabor filter is developed. Mahalanobis distance measure is used to find the similarity between query and feature database. Average Normalized Modified Retrieval Rate (ANMRR) is computed to evaluate the performance with the state of art methods.

Impact of Feature Representation on Remote Sensing Image Retrieval

“…Dataset description Retrieval Using Texture Features [38] Five images from two geographic regions, California and Nebraska of 384x384 pixels, 4 spectral bands Empirical Analysis of SIFT, Gabor and Fused Feature Classification Using SVM [39] Multispectral Landsat 8 satellite Image 105 images of Landsat 8 sensors data of 30 meter resolution Spectral Feature and Semantic Computing [40] 80 multispectral-images which are captured from UAV multispectral Sensor. Multiscale Texture Analysis and Color Coherence Vector Based Feature Descriptor [41] UCMerced having image size 256x256 with 21 classes and 10,000 total images An End-To-End Adversarial Hashing Method [42] EuroSAT having 10 land-use classes and have 13 bands with three different spatial resolutions of 10m, 20m and 60m per pixel. Each class contains 2000-3000 images.…”

Web-based remote sensing image retrieval using multiscale and multidirectional analysis based on Contourlet and Haralick texture features

“…The Histogram of Curvelet (HOC) has been used as a feature vector by Uslu and Albayrak (2013) to improve classification accuracy. Sudheer and Krishnan (2019) have analyzed texture features by extracting GLCM from the Curvelet coefficients and Color Coherence Vector (CCV) (Sudheer and Krishnan, 2019). Liu et al (2019a) were also used as a Curvelet-based feature vector using statistical co-occurrence features from the various scales of the SAR image to detect the sea ice (Liu et al , 2019a).…”