Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: sharpness

Sortuj według:

Ogranicz wyniki do:

High-level and Low-level Feature Set for Image Caption Generation with Optimized Convolutional Neural Network

100%

Padate R. , Jain A. , Kalla M. , Sharma A.

tom nr 4

67--74

Automatic creation of image descriptions, i.e. cap- tioning of images, is an important topic in artificial intelligence (AI) that bridges the gap between computer vision (CV) and natural language processing (NLP). Currently, neural networks are becoming increasingly popular in captioning images and researchers are looking for more efficient models for CV and sequence-sequence systems. This study focuses on a new image caption generation model that is divided into two stages. Ini- tially, low-level features, such as contrast, sharpness, color and their high-level counterparts, such as motion and facial impact score, are extracted. Then, an optimized convolutional neural network (CNN) is harnessed to generate the captions from im- ages. To enhance the accuracy of the process, the weights of CNN are optimally tuned via spider monkey optimization with sine chaotic map evaluation (SMO-SCME). The development of the proposed method is evaluated with a diversity of metrics.

Improving Image Sharpness by Surface Recognition

86%

Zerbino D.

tom Vol. 8, No 2

39--44

The article proposes a rule for improving image sharpness and analyzes its implementation by means of the cellular automata formalism and neural networks. It has been proved, that the previously known contrasting algorithm, which uses a template and 3x3 pixels, can be improved considerably by repeatedly applying the iterative process over templates 2x2 with the rule "anti - blur" ( C 11 = C 11 x F - ( C 12 + C 21 + C 22) x S ) and gradient color correction at each step after the "anti - blur". Colors of images in the template are presented as real numbers (R, G, B). To correct the gradient (C11 < C12, C11 < C21, C11

Approximation of functions and their conjugates in Lp and uniform metric by Euler means

58%

Volosivets S. S. , Tyuleneva A. A.

2018

tom Vol. 51, nr 1

141--150

For 2π-periodic functions from Lp (where 1 < p < ∞) we prove an estimate of approximation by Euler means in Lp metric generalizing a result of L. Rempuska and K. Tomczak. Furthermore, we show that this estimate is sharp in a certain sense. We study the uniform approximation of functions by Euler means in terms of their best approximations in p-variational metric and also prove the sharpness of this estimate under some conditions. Similar problems are treated for conjugate functions.