Image registration is the process of establishing point by point correspondence between images obtained from a same scene. This process is very useful in remote sensing, medicine, cartography, computer vision, etc. Then, the task of registration is to place the data into a common reference frame by estimating the transformations between the data sets. In this work, we develop a rigid point regi...

We present here, a novel network architecture called MergeNet for discovering small obstacles for on-road scenes in the context of autonomous driving. The basis of the architecture rests on the central consideration of training with less amount of data since the physical setup and the annotation process for small obstacles is hard to scale. For making effective use of the limited data, we propo...

Digitized pathology images typically have very high resolution, making it difficult to display in their entirety on the computer screen and inefficient to transmit over the network for educational purposes. Progressive zooming of pathology images is desirable despite the availability of inexpensive networking bandwidth. An efficient progressive image resolution refining system for on-line distr...

We develop a new method for visualizing and refining the invariances of learned representations. Given two reference images (typically, differing by some transformation), we synthesize a sequence of images lying on a path between them that is of minimal length in the space of a representation (a “representational geodesic”). If the transformation relating the two reference images is an invarian...

We propose a methodology for comparing and refining perceptual image quality metrics based on synthetic images that are optimized to best differentiate two candidate quality metrics. We start from an initial distorted image and iteratively search for the best/worst images in terms of one metric while constraining the value of the other to remain fixed. We then repeat this, reversing the roles o...

Oil refining is an inevitable step in production of edible and industrial oil. Bleaching is the most important process among the refining processes. Bleaching adsorption is the most common method and clay is the most widely used adsorbent in this method. Disposal of bleaching clay, as a waste from re-refining plants, makes many environmental problems and economic losses. In the current study, t...

Watermarking technology.play a central role in the digital right management for multimedia data. Especially a video watermarking is a real challenge, because of very high compression ratio (about 1:200). Normally the watermarks can barely survive such massive attacks, despite very sophisticated embedding strategies. It can only work with a sufficient error correcting code method. In this paper,...

in this paper the issue of evaluating iranian oil refineries performance has been discussed. the research is based on math modelling by operational research techniques. to do so, of the proposed scenarios and different math programming models, a model is made by combining dea with goal programming techniques that compared with the old classical dea models which measures the efficiency and produ...