Localizing global descriptors for content-based image retrieval

Abstract

In this paper, we explore, extend and simplify the localization of the description ability of the well-established MPEG-7 (Scalable Colour Descriptor (SCD), Colour Layout Descriptor (CLD) and Edge Histogram Descriptor (EHD)) and MPEG-7-like (Color and Edge Directivity Descriptor (CEDD)) global descriptors, which we call the SIMPLE family of descriptors. Sixteen novel descriptors are introduced that utilize four different sampling strategies for the extraction of image patches to be used as points of interest. Designing with focused attention for content-based image retrieval tasks, we investigate, analyse and propose the preferred process for the definition of the parameters involved (point detection, description, codebook sizes and descriptors' weighting strategies). The experimental results conducted on four different image collections reveal an astonishing boost in the retrieval performance of the proposed descriptors compared to their performance in their original global form. Furthermore, they manage to outperform common SIFTand SURF-based approaches while they perform comparably, if not better, against recent state-of-the-art methods that base their success on much more complex data manipulation.

Robust Image Identification without Visible Information for JPEG Images

“…Note that T PR = 100[%] means that there are no false negative matches. The proposed scheme was compared with the stateof-art image hashing-based scheme [18], the SIMPLE descriptors-based scheme [27] and the fuzzy commitment scheme (FCS)-based scheme [14]. In the scheme [18], the hamming distances between the hash value of a query image and those of all images in each database are calculated, and then images that have the smallest distance are chosen as the images generated from the same original image as the query, after decompressing all images.…”

“…In the scheme [18], the hamming distances between the hash value of a query image and those of all images in each database are calculated, and then images that have the smallest distance are chosen as the images generated from the same original image as the query, after decompressing all images. In the scheme [27], after indexing all images in each database, image retrieval is performed by using a query image and the index, and then images that have the highest values are chosen as the images generated from the same original image as the query, where SURF(speeded up robust features) and CEDD(color and edge directivity descriptors) were used as local and global descriptors respectively in the simulations. The results in Tables 2 and 3 suggest the following points.…”

A Genesis of a Meticulous Fusion based Color Descriptor to Analyze the Supremacy between Machine Learning and Deep learning

“…Image segmentation is a process which is based on obtaining information from a specific part of an image and therefore be called as Region based image retrieval (RBIR). Edge-integrated minimum spanning tree (EI-MST) is an algorithm which can be used for RBIR and has been developed by Yang liu [12].Various global descriptors like color layout descriptor (CLD), Edge histogram descriptor (EHD), Color and edge directivity descriptor (CEDD), etc have been analyzed by lakovidou et al [13]. These descriptors have been tested to analyze their performance in CBIR systems.…”

Robust Image Identification with DC Coefficients for Double-Compressed JPEG Images

“…The conventional schemes for identifying images can be broadly classified into two types: compression-method-dependent and compression-methodindependent. Compression-method-independent schemes include image retrieval and image hashing-based ones [12]- [15]. These schemes generally extract features from resized or divided images after decoding images, and then the features are converted to other representations.…”