Deep unsupervised hashing methods are gaining attention in the field of remote sensing (RS) image retrieval due to rapid growth volume unlabeled RS data. Most previous research used only natural image-based pre-trained models generate label matrices; however, this method cannot capture semantic information images well and limits accuracy retrieval. To solve problem, authors propose a deep weigh...

Multi-keyword query is widely supported in text search engines. However, an analogue in image retrieval systems, multi-object query, is rarely studied. Meanwhile, traditional object-based image retrieval methods often involve multiple steps separately. In this work, we propose a weakly-supervised Deep Multiple Instance Hashing (DMIH) framework for object-based image retrieval. DMIH integrates o...

Cross-modal hashing aims to map heterogeneous multimedia data into a common Hamming space, which can realize fast and flexible retrieval across different modalities. Unsupervised cross-modal hashing is more flexible and applicable than supervised methods, since no intensive labeling work is involved. However, existing unsupervised methods learn hashing functions by preserving inter and intra co...

WTA (Winner Take All) hashing has been successfully applied in many large scale vision applications. This hashing scheme was tailored to take advantage of the comparative reasoning (or order based information), which showed significant accuracy improvements. In this paper, we identify a subtle issue with WTA, which grows with the sparsity of the datasets. This issue limits the discriminative po...

We describe a hashing function from the elements of the finite field Fq into points on a Hessian curve. Our function features the uniform and smaller size for the cardinalities of almost all fibers compared with the other known hashing functions for elliptic curves. Moreover, a point on the image set of the function is uniquely given by its abscissa. For ordinary Hessian curves, the cardinality...

Steganography is the art and science of writing hidden messages in such a way that no one apart from the intended recipient knows of the existence of the message; this is in contrast to cryptography, where the existence of the message itself is not disguised, but the content is obscured. Medical information about the patient is very sensitive and security solutions are needed to make the inform...

Image searching, is an active approach to recover the effective results for image searched by the users with the help of queries. Which is used by the current required search engines likes Bing, Google, and Internet Explorer and so on. To improve image searching method there is use of hash code technique. In this paper, various image search techniques using different hashing methods are reviewe...

In this paper we present a Bayesian image zooming/super-resolution algorithm based on a patch based representation. We work on a patch based model with overlap and employ a Locally Linear Embedding (LLE) based approach as our data fidelity term in the Bayesian inference. The image prior imposes continuity constraints across the overlapping patches. We apply an error back-projection technique, w...