Image classification using low-level features is always a challenging research in computer vision. Recent years, content-based image retrieval has emerged as an important area in computer vision and multimedia computing. In this project, I'm going to introduce and implement an approach [1] that can better represent the image using low-level features and then I apply this method in image classif...

We have observed the central 45 region of the Galaxy at 620 MHz band of the Giant Metrewave Radio Telescope (GMRT) in radio continuum, and measured the polarisation properties of 64 small diameter background extragalactic sources seen through the −6< l <6, −2< b <2 region with the Australia Telescope Compact Array (ATCA) and the Very Large Array (VLA). Our 620 MHz observations show that Sgr A* ...

Saliency prediction is a well studied problem in computer vision. Early saliency models were based on low-level hand-crafted feature derived from insights gained in neuroscience and psychophysics. In the wake of deep learning breakthrough, a new cohort of models were proposed based on neural network architectures, allowing significantly higher gaze prediction than previous shallow models, on al...

A family of proximity graphs, called Empty Region Graphs (ERG) is presented. The vertices of an ERG are points in the plane, and two points are connected if their neighborhood, defined by a region, does not contain any other point. The region defining the neighborhood of two points is a parameter of the graph. This way of defining graphs is not new, and ERGs include several known proximity grap...

In this paper, we propose a novel method for comparing the shape of similar objects. From the viewpoint of linear algebra, we turn this identifiable region detection problem into a low-rank submatrices searching process, and solve it with biclustering. Comparing with traditional cluster analysis, our method looks for structural information on both object index and local shape dimensions, which ...

We report here on an investigation of high frequency oscillations in active regions, carried out using high cadence observations of O V 629 Å, Mg IX 368 Å and Fe XVI 335 Å with the Coronal Diagnostic Spectrometer (CDS) on SOHO. Using the techniques of wavelet analysis on various temporal series datasets, we find that certain oscillation frequencies are favoured for each line. We find furthermor...

The pseudoautosomal region (PAR) is a unique segment of sequence homology between differentiated sex chromosomes where recombination occurs during meiosis. Molecular and functional properties of the PAR are distinctive from the autosomes and the remaining regions of the sex chromosomes. These include a higher rate of recombination than genome average, bias towards GC-substitutions and increased...

The region counting distances, introduced by Demaine, Iacono and Langerman [5], associate to any pair of points p, q the number of items of a dataset S contained in a region R(p, q) surrounding p, q. We define region counting disks and circles, and study the complexity of these objects. In particular, we prove that for some wide class of regions R(p, q), the complexity of a region counting circ...

We introduce a novel method for embedding and detecting a chaotic watermark in the digital spatial image domain, based on segmenting the image and locating regions that are robust to several image manipulations. The robustness of the method is confirmed by experimental results that display the immunity of the embedded watermark to several kinds of attacks, such as compression, filtering, scalin...

This paper is an essay in axiomatic foundations for discrete geometry intended, in principle, to be suitable for digital image processing and (more speculatively) for spatial reasoning and description as in AI and GIS. Only the geometry of convexity and linearity is treated here. A digital image is considered as a nite collection of regions; regions are primitive entities (they are not sets of ...