Wyniki wyszukiwania - BazTech

1

An Enhanced Approach for Image Edge Detection Using Histogram Equalization (BBHE) and Bacterial Foraging Optimization (BFO)

Kumar Praveen, Jindal Tanvi, Raj Balwinder

International Journal of Electronics and Telecommunications

|

2022

|

Vol. 68. No. 4

875--880

EN

The Edge detection is a customarily task. Edge detection is the main task to perform as it gives clear information about the images. It is a tremendous device in photograph processing gadgets and computer imaginative and prescient. Previous research has been done on moving window approach and genetic algorithms. In this research paper new technique, Bacterial Foraging Optimization (BFO) is applied which is galvanized through the social foraging conduct of Escherichia coli (E.coli). The Bacterial Foraging Optimization (BFO) has been practice by analysts for clarifying real world optimization problems arising in different areas of engineering and application domains, due to its efficiency. The Brightness preserving bi-histogram equalization (BHEE) is another technique that is used for edge enhancement. The BFO is applied on the low level characteristics on the images to find the pixels of natural images and the values of F-measures, recall(r) and precision (p) are calculated and compared with the previous technique. The enhancement technique i.e. BBHE is carried out to improve the information about the pictures.

2

Wykrywanie wad termokompresji w strukturach tyrystorów dużej mocy za pomocą termografii impulsowej

Suszyński Z., Bednarek M.

Pomiary Automatyka Kontrola

|

2011

|

R. 57, nr 10

1202-1205

PL

W artykule przedstawiono możliwość wykorzystania funkcji korelacji do przetwarzaniu sekwencji obrazów kontrastowych uzyskanych metodą termografii impulsowej. Metoda pozwala na wyodrębnienie obszarów powierzchni badanego elementu znajdujących się nad niejednorodnością cieplną występującą w strukturze. Badania wykonano na elementach warstwowych stosowanych do produkcji tyrystorów dużej mocy. Niejednorodność występująca w takich elementach związana jest z występowaniem defektów w obszarze przejściowym pomiędzy krzemem i molibdenem powstałych w trakcie termokompresji.

EN

Active thermography with pulse excitation is a diagnostic method enabling fast visualisation of thermal heterogeneity present in the volume of layered structures of semiconductor components. To improve the results obtained, when simultaneously increasing the detectability of heterogeneities related to structure defects, it is necessary to apply image processing methods. The studies were carried out for components used to manufacture high power thyristors. The test stand is composed of a set of 6 high power flash lamps, spectral filters and high speed infrared camera. The measurements consisted in recording a sequence of thermograms during the excitation of the tested object with an optical impulse derived from six flash lamps. The differences between the maximum temperature contrast on the surface of the tested component and various times of its occurrence for various defects (Fig. 6) are inconvenience in diagnostic process. While determining the location and area of the thermal heterogeneities in such structures as the tested components, it is of minor importance to determine thermal and geometrical properties of the defect precisely. The proposed method (Fig. 7) helps to generate an image depicting adjustment of contrast changing curve in time to the assumed reference function. Use of the linear correlation function to generate correlation images helps to increase the detectability of heterogeneous of thermal properties (Fig. 12).

3

Fast reduction of large dataset for nearest neighbor classifier

Raniszewski M.

Journal of Medical Informatics & Technologies

|

2010

|

Vol. 16

111--116

EN

Accurate and fast classification of large data obtained from medical images is very important. Proper images (data) processing results to construct a classifier, which supports the work of doctors and can solve many medical problems. Unfortunately, Nearest Neighbor classifiers become inefficient and slow for large datasets. A dataset reduction is one of the most popular solution to this problem, but the large size of a dataset causes long time of a reduction phase for reduction algorithms. A simple method to overcome the large dataset reduction problem is a dataset division into smaller subsets. In this paper five different methods of large dataset division are considered. The received subsets are reduced by using an algorithm based on representative measure. The reduced subsets are combined to form the reduced dataset. The experiments were performed on a large (almost 82 000 samples) two–class dataset dating from ultrasound images of certain 3D objects found in a human body.

4

Koncepcja technologii przetwarzania zdjęć fotogrametrycznych z wykorzystaniem lokalnych i rozległych sieci komputerowych

Janowski R., Paszotta Z., Szulwic J.

Archiwum Fotogrametrii, Kartografii i Teledetekcji

|

2001

|

Vol. 11

3-19--3-24

PL

Autorzy artykułu próbują wskazać jeden z kierunków rozwoju fotogrametrii cyfrowej, który wynika z możliwości wykorzystania technologii wspartej na możliwościach udostępnianych przez nowoczesne sieci komputerowe. W treści artykułu opisują założenia technologii systemu przetwarzania zdjęć fotogrametrycznych opartego na relacji klient-serwer jako formę odejścia od stanowiskowego rozwiązywania zagadnień fotogrametrii cyfrowej na rzecz rozwiązań sieciowych wspartych na silnej i bezpiecznej jednostce centralnej.