Image Retrieval using Autocorrelation Based Chordiogram Image Descriptor and Support Vector Machine
Nowadays, evolving systems for indexing and organizing images is more important due to proliferation of images in all domains and it has made content-based image retrieval (CBIR) as significant research area. This paper uses autocorrelation based chordiogram image descriptor (ACID) for effective image representation and Support vector machine (SVM) for effective image classification. The ACID of images is computed from Haar wavelet based multiresolution domain and it exploits shape, texture and geometric details. The proposed combination of ACID and SVM is highly compatible and is comprehensively tested on benchmark datasets namely Gardens Point Walking and St. Lucia and experimental results prove that proposed combination outperforms significantly in terms of precision and recall