Image segmentation technique to support automatic marking of objects in endoscopic images

Author(s):  
R.R. Akhmetvaleev ◽  
I.A. Lackman ◽  
D.V. Popov ◽  
M.V. Krasnoperov

The aim of this study is to develop a method for visual segmentation of various objects of endoscopic images based on a collection of endoscopic images. The method was developed on the basis of a collection of images obtained by ENVD LLC on a contractual basis with medical organizations of the Republic of Bashkortostan, Russia. The collection consists of 70 endoscopic images recording clinical cases diagnosed in accordance with the Paris Tumor Classification of Gastrointestinal Diseases. A number of machine vision operations were carried out, including image preprocessing, image sampling, and subsequent clustering for the purpose of image segmentation. Results: A technique for the analysis of endoscopic images was developed, which makes it possible to obtain the contours of objects of interest to a specialist performing endoscopy. Conclusion. The developed solution allows to speed up and improve the procedure for marking endoscopic images, which in turn prepares a platform for further processing of endoscopic images, for example, nosological classification of neoplasms.

2013 ◽  
Vol 373-375 ◽  
pp. 521-524
Author(s):  
Bao Jun Wang ◽  
Guang Yan Yang

This paper presents a medical bottle detecting system based on machine vision, and completing the tightness detection task for the installation of vial and cap. The first step is experimental platform building; secondly, using MATLAB software for operations such as histogram equalization, image enhancement, image segmentation and boundary signature; finally, finalizing the design of the system software with MATLAB GUI. The systems can significantly reduce testing cost, improve detection quality, speed up the system efficiency and realize non-contact real-time detection in industrial field.


ÈKOBIOTEH ◽  
2020 ◽  
Vol 3 (3) ◽  
pp. 497-504
Author(s):  
I.G. Bikbaev ◽  
◽  
V.B. Martynenko ◽  

In the Bashkir Fore-Ural, 284 forested mires were studied. The total area of the investigated mires was more than 29 thousand hectares. Classification of mire vegetation was performed using Braun-Blanquet approach. The vegetation of forested mires of Bashkir Fore-Ural is characterized by low diversity and belongs to four associations of three alliances, three orders and two classes of vegetation, i.e. Alnetea glutinosae and Oxycocco-Sphagnetea. The brief description and geographical distribution of plant communities of associations are provided. It was shown that the communities of the alliance Alnion glutinosae have a wide distribution across in the Bashkir Fore-Ural by comparison with other types of forested mires. The forested mires with the predominance of pine and sphagnum mosses belonging to the alliance Vaccinii uliginosi-Pinion are most seldom type of vegetation occurring only in the northern part of the Republic of Bashkortostan.


Author(s):  
V. P. Toporkov ◽  
A. I. Kologorov ◽  
N. A. Ossina ◽  
T. V. Bugorkova ◽  
S. A. Scherbakova ◽  
...  

The detailed description of imported cholera cases in Beloretshk, the Republic of Bashkortostan, in 2008 is presented. The cases were associated with pilgrimage in India. The similar case of cholera importation was registered in Beloretsk in 2004. Special attention should be paid to the persons returned from religious trips to India as their long stay in cholera endemic country increases the risk of infection. Should there appear gastrointestinal diseases in persons returned from cholera-endemic countries it is advisable to carry out their examination on cholera using bacteriological and serological methods.


Author(s):  
F. Verkholantsev ◽  
R. Diagilev ◽  
I. Golubeva ◽  
N. Guseva

The article provides macroseismic data on the earthquake 20.05.2014 18h26mUTC ML=2.8, that had a local but relatively strong macroseismic effect (I0=4–5) in the Chishminsky district of the Republic of Bashkortostan. After the event, macroseismic data were collected in 27 settlements in the epicentral zone. This data allowed to determine the macroseismic epicenter, which is close to the instrumental one. The events in the same area during the historical period were considered in detail and modern seismic records were revised. The data allowed to identify a series of similar seismic events with less magnitudes in 2014. The classification of these activities into two groups has been justified there. There are tectonic and natural events induced by Alkinskoye oil deposit exploration.


2016 ◽  
pp. 13-27 ◽  
Author(s):  
L. M. Abramova ◽  
Ya. M. Golovanon

The Republic of Bashkortostan is located between 51°34′ –56 °10′ N and 53°10′ — 59°59′ E, its length from the north to the south — 550 km, from the west to the east — 450 km. The territory of Bashkortostan consists of three main natural regions (provinces): the Bashkir Cis-Urals (about 65 % of the area), the South Urals (29 %) and the Bashkir Trans-Urals (6 %). These areas differ not only by the natural conditions (topography, climate, soil, vegetation, etc.), but also by their level of economic development. Currently, an expansion and naturalization of a number of North American alien species of the family Asteraceae Dumort. of the genera Ambrosia L., Xanthium L., Bidens L., Galinsoga Ruiz & Pav., Cyclachaena Fresen. etc. (Abramova, 2011, 2012, 2014, 2015) are observed in the Republic of Bashkortostan. Since 1990th of XX century we conduct a geobotanical research of communities with alien species. The article represents the third part of series of publications devoted to the classification of communities with alien species in the South Urals. The results of vegetation classification of communities with species from the gene­ra Ambrosia L., Cyclachaena (Nutt.) Fresen and Xanthium L. were published earlier (Abramova, 2011, 2015). In this article the communities with participation of three aggressive alien species such as: Bidens frondosa L., Hordeum jubatum L. and Urtica cannabina L. are presented. Two of them— Bidens frondosa and Hordeum jubatum — are included in “The black book of flora of the Central Russia” (Vinogradova, et al., 2010), and they are invasive species of many regions of Russia, and the third – Urtica cannabina — an invasive species of the South Urals (Abramova, 2014). As a result of the carried-out classification a Prodrome of communities is made, the synoptic table of syntaxa is given.


2013 ◽  
Vol 664 ◽  
pp. 1093-1097 ◽  
Author(s):  
Min Hao Cao ◽  
Fei Zhong

In order to meet the online testing requirements in current manufacturing automated production of car foam,the paper proposes a method for detecting the mould that products the foam by using machine vision and introduces the overall solutions of the system. The detection arithmetic mainly includes the image preprocessing、image template matching, interesting region acquisition and the blob detection of image segmentation. The arithmetic is developed in VS2010.Through a series of experiments, the result shows that the arithmetic meets the requirements of inspecting various moulds on the production line.


Author(s):  
Victorov V. V. ◽  
◽  
Sharafutdinov M. A. ◽  
Mukhamadeeva O. R. ◽  
Pavlova M. Yu. ◽  
...  

2020 ◽  
Vol 0 (6) ◽  
pp. 13-19
Author(s):  
Guzel Gumerova ◽  
Georgiy Gulyuk ◽  
Dmitry Kucher ◽  
Anatoly Shuravilin ◽  
Elena Piven

Data of long-term researches (2015–2018) in southern forest-steppe zone of the Republic of Bashkortostan, is justified theoretically and experimentally the mode of irrigation of potatoes on leached chernozems of unsatisfactory, satisfactory and good ameliorative condition of irrigated lands. For the growing periods of potatoes with different heat and moisture supply, the number of watering, the timing of their implementation, irrigation and irrigation norms are established. On lands with unsatisfactory meliorative state the number of irrigation depending on weather conditions of potato vegetation period varied from 0 to 3 (1.5 on average) with average irrigation norm – 990 m3/ha. With satisfactory meliorative state of lands the number of irrigation on average increased from 0 to 4 (2.3 on average) with irrigation norm – 1305 m3/ha. On lands with good meliorative state the number of irrigation was the highest – from 1 to 5 (3 on average) with average irrigation irrigation norm is 1653 m3/ha. It was noted that in the dry periods of potato vegetation the greatest number of watering was carried out (3–5 watering), and in the wet periods (2017) watering was not carried out except for the area with a good reclamation state, where only one irrigation was carried out by the norm of 550 m3/ha. Water consumption of potato was studied in dynamics as a whole during the growing season and the months of the growing season depending on weather conditions of vegetation period and land reclamation condition of irrigated lands, as well as in the control (without irrigation). The lowest total water consumption was in the area without irrigation and averaged 226.8 mm. In irrigated areas, its values increased to 319-353.4 mm. The average daily water consumption varied from 2.12 to 3.3 mm. The highest rates of potato water consumption were observed in June and July, and the lowest – in May and August. In the total water consumption of potatoes on the site without irrigation, the largest share was occupied by atmospheric precipitation and in addition to them the arrival of moisture from the soil. Irrigation water was used in irrigated areas along with precipitation, the share of which was 30.2–46.1 %.


Sign in / Sign up

Export Citation Format

Share Document