Wyniki wyszukiwania - BazTech

1

Digital image restoration using SURF algorithm

Tammineni Shanmukhaprasanthi, Rayavarapu Swarajya Madhuri, Gottapu Sasibhushana Rao, Goswami Raj Kumar

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2024

|

T. 14, nr 1

37--40

EN

In contemporary times, the preservation of scientific and creative endeavours often relies on the utilization of film and image archives, hence emphasizing the significance of image processing as a critical undertaking. Image inpainting refers to the process of digitally altering an image in a manner that renders the adjustments imperceptible to a viewer lacking knowledge of the original image. Image inpainting is a technique mostly employed to restore damaged regions within an image by utilizing information obtained from matching characteristics in relevant images. This process involves filling in the damaged areas and removing undesired objects. The SURF (Speeded Up Robust Feature) algorithm under consideration is partitioned into three primary phases. Firstly, the essential characteristics of the impaired image and the pertinent image are identified. In the second stage, the relationship between the damaged image and the relevant image is determined in terms of translation, scaling, and rotation. Ultimately, the destroyed area is reconstructed through the application of the inverse transformation. The quality assessment of inpainted images can be evaluated using metrics such as Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR), and Mean Squared Error (MSE). The experimental findings provide evidence that the suggested inpainting technique is effective in terms of both speed and quality.

PL

We współczesnych czasach utrwalanie dorobku naukowego i twórczego często opiera się na wykorzystaniu archiwów filmowych i obrazowych, co podkreśla znaczenie przetwarzania obrazu jako przedsięwzięcia krytycznego. Inpainting odnosi się do procesu cyfrowej zmiany obrazu w sposób, który sprawia, że korekty są niezauważalne dla widza nie znającego oryginalnego obrazu. Inpainting to technika stosowana najczęściej w celu przywracania uszkodzonych obszarów obrazu poprzez wykorzystanie informacji uzyskanych na podstawie dopasowania cech odpowiednich obrazów. Proces ten polega na wypełnieniu uszkodzonych obszarów i usunięciu niepożądanych obiektów. Rozważany algorytm SURF (Speeded Up Robust Feature) dzieli się na trzy główne fazy. Po pierwsze, identyfikowane są podstawowe cechy obrazu zaburzonego i obrazu istotnego. W drugim etapie określa się relację pomiędzy obrazem uszkodzonym a obrazem odpowiednim pod względem translacji, skalowania i rotacji. Ostatecznie zniszczony obszar rekonstruuje się poprzez zastosowanie transformacji odwrotnej. Ocenę jakości renowacji obrazów można ocenić za pomocą wskaźników, takich jak wskaźnik podobieństwa strukturalnego (SSIM), szczytowy stosunek sygnału do szumu (PSNR) i błąd średniokwadratowy (MSE). Wyniki eksperymentów dostarczają dowodów na to, że sugerowana technika renowacji jest skuteczna zarówno pod względem szybkości, jak i jakości.

2

Optimization of soft-sensing model for ash content prediction of flotation tailings by image features tailings based on GA-SVMR

Wang Guanghui, He Ting, Kuang Yali, Lin Zhe

Physicochemical Problems of Mineral Processing

|

2020

|

Vol. 56, iss. 4

590--598

EN

Ash content is one of the most important properties of coal quality and the ash prediction of coal slurry in floatation is urgent and important for automation of the floatation process. The aim of this paper is to propose a method of ash content prediction for flotation tailings by the use of image analysis. The mean gray value, energy, skewness and coal slurry concentration are highly correlated with coal slurry ash content by correlation analysis based on experiments while the particles’ size has little effect on the ash. Single variable linear prediction model between coal ash content and mean gray value was developed by the LS and its prediction errors were below 7%. For improving the prediction results, an ash prediction model based on GA-SVMR was established with additional three input parameters: energy, skewness, coal slurry concentration. This model has a higher accuracy with predictive errors all below 5% and 80% of them less than 3%. Results indicate that GA-SVMR model has a higher precision compared with LS model and PSO-SVMR model and soft-sensing model based on image features of the slurry can be used as a new method for ash detection of floatation tailings in automatic control process of coal flotation.

3

New optical character recognition method based on Hu invariant moments and weighted voting

Kmieć M.

Journal of Applied Computer Science

|

2011

|

Vol. 19, nr 1

33-50

EN

Optical character recognition is an important image processing task. Its aim is to enable computers to recognise graphic characters without human supervision. The process of optical symbol recognition is divided into two stages. First, certain features of the character undergoing recognition are extracted, and second, a match to them is searched for in the library of models. This paper looks at Hu invariant moments, a well established set of image features, and discusses their performance in optical character recognition. One approach to using Hu invariant moments in pattern recognition is using a metric function to find the pattern in the library of models, that is of the same class as the pattern considered. In this paper a new classification method is proposed that performs better than the classic method of metric function.

4

Badania własności wybranych cech dyskryminacyjnych obrazów tekstur

Rudnicki Z.

Automatyka / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie

|

2009

|

T. 13, z. 3/1

959-969

PL

Przedstawiono wyniki badań kilkudziesięciu cech stosowanych dla rozróżniania klas badanych obrazów typu teksturowego. Uwzględniono cechy wyznaczane na podstawie takich charakterystyk jak: histogram, macierz gradientu, macierz przejść tonalnych, macierz długości pasm oraz model autoregresji. W szczególności badano wrażliwość poszczególnych cech na zmiany: jasności, kontrastu i rozmycia obrazów oraz uporządkowania struktury. Dokonano selekcji najlepszych cech dyskryminacyjnych.

EN

The paper presents the results of investigation of many image features commonly used in discrimination of texture image classes. The features calculated from: histogram, gradient matrix, co-occurrence matrix, run-length matrix and autoregression model were taken into consideration. The sensivity of these features on the changes of brightness, contrast, blurring and structure arrangement were investigated and the best discriminators were selected.

5

Computer analysis and disturbance compensation of sliding friction surface images.

Rudnicki Z., Figiel W.

Zagadnienia Eksploatacji Maszyn

|

2006

|

Vol. 41, nr 2

171-183

EN

In the paper, some methods of analysis of microscopic image sequences of steel countersample disk are presented. These images were recorded during sliding of the samples of PTFE composites in pin-on-disk tribotester. The sequences show variations of thin layer of transferred composite material - "transfer film", important in sliding friction process. The applied methods of noise evaluation and filtration and the method of binarization threshold calculation - based on image percentiles are described. Binary image features - showing transfer film changes - are defined and extracted. The approximation functions of experimental data are made. Conclusions and postulations of further research are formulated.

PL

W artykule przedstawiono metody analizy sekwencji obrazów mikroskopowych powierzchni stalowej tarczy, rejestrowanych w procesie tarcia ślizgowego próbek kompozytów PTFE w tribotesterze typu trzpień-tarcza. Przedstawiono zastosowane metody oceny i filtracji szumu, wyznaczania progu binaryzacji na podstawie percentyli obrazów oraz wyznaczono cechy obrazów binarnych pozwalające odzwierciedlić charakter zmian filmu transferowego. Zdefiniowano funkcję opisującą otrzymane przebiegi. Sformułowano wnioski co do dalszych badań.

6

Application of neural networks to microstructure classification with the use of image features

Pamuła T.

Journal of Medical Informatics & Technologies

|

2001

|

Vol. 2, Part. 2

SN39--SN43

EN

The paper presents further results of research carried out on the application of neural networks to microstructure analysis. As presented in [1] the aim is to classify microstructures. The current approach differs in that, the inputs of neural networks are not image pixel values but image features calculated over patches of the whole image. In the course of research a set of 7 features was named, which enabled effective analysis. Appropriate training sets were prepared and different net structures tested. The results may be applied in examining the quality of metal implants used in medicine.