arXiv subjects

Vasile Patrascu

Publications and source records attributed to Vasile Patrascu.

25 records · Page 2Linked to original sources

arXiv2014

Contour Detection Using Contrast Formulas in the Framework of Logarithmic Models

In this paper we use a new logarithmic model of image representation, developed in [1,2], for edge detection. In fact, in the framework of the new model we obtain the formulas for computing the "contrast of a pixel" and the "contrast" image is just the "contour" or edge image. In our setting the range of values is preserved and the quality of the contour is good for high as well as for low luminosity regions. We present the comparison of our results with the results using classical edge detection operators.

cs.CV↗

arXiv2014

Image enhancement using the mean dynamic range maximization with logarithmic operations

In this paper we use a logarithmic model for gray level image enhancement. We begin with a short presentation of the model and then, we propose a new formula for the mean dynamic range. After that we present two image transforms: one performs an optimal enhancement of the mean dynamic range using the logarithmic addition, and the other does the same for positive and negative values using the logarithmic scalar multiplication. We present the comparison of the results obtained by dynamic ranges optimization with the results obtained using classical image enhancement methods like gamma correction and histogram equalization.

cs.CV↗

arXiv2014

An Algebraical Model for Gray Level Images

In this paper we propose a new algebraical model for the gray level images. It can be used for digital image processing. The model adresses to those images which are generated in improper light conditions (very low or high level). The vector space structure is able to illustrate some features into the image using modified level of contrast and luminosity. Also, the defined structure could be used in image enhancement. The general approach is presented with experimental results to demonstrate image enhancement.

cs.CV↗

arXiv2014

Color Image Enhancement In the Framework of Logarithmic Models

In this paper, we propose a mathematical model for color image processing. It is a logarithmical one. We consider the cube (-1,1)x(-1,1)x(-1,1) as the set of values for the color space. We define two operations: addition <+> and real scalar multiplication . With these operations the space of colors becomes a real vector space. Then, defining the scalar product (.|.) and the norm || . ||, we obtain a (logarithmic) Euclidean space. We show how we can use this model for color image enhancement and we present some experimental results.

cs.CV↗

arXiv2014

A Mathematical Model for Logarithmic Image Processing

In this paper, we propose a new mathematical model for image processing. It is a logarithmical one. We consider the bounded interval (-1, 1) as the set of gray levels. Firstly, we define two operations: addition <+> and real scalar multiplication . With these operations, the set of gray levels becomes a real vector space. Then, defining the scalar product (.|.) and the norm || . ||, we obtain an Euclidean space of the gray levels. Secondly, we extend these operations and functions for color images. We finally show the effect of various simple operations on an image.

cs.CV↗

arXiv2014

The Affine Transforms for Image Enhancement in the Context of Logarithmic Models

The logarithmic model offers new tools for image processing. An efficient method for image enhancement is to use an affine transformation with the logarithmic operations: addition and scalar multiplication. We define some criteria for automatically determining the parameters of the processing and this is done via mean and variance computed by logarithmic operations.

cs.CV↗

arXiv2014

Neutrosophic information in the framework of multi-valued representation

The paper presents some steps for multi-valued representation of neutrosophic information. These steps are provided in the framework of multi-valued logics using the following logical value: true, false, neutral, unknown and saturated. Also, this approach provides some calculus formulae for the following neutrosophic features: truth, falsity, neutrality, ignorance, under-definedness, over-definedness, saturation and entropy. In addition, it was defined net truth, definedness and neutrosophic score.

cs.AI↗