The usage of algorythm based on color descriptor in the laparoscopic images classification

Abstract

The classification of laparoscopic images in correspondence to certain pathological state of the abdominal organs assumes the exploration of characteristic of color descriptor of abdominal structures which are suspected for the pathology presence. Sparse publications which were devoted to computer automatic diagnostics (CAD) in the laparoscopic surgery till the recent time have not been dealt with the color descriptors as an informative one for diagnostics. That is why the aim of the work is to investigate the effectiveness of the usage of algorithm of the objects classification, when cascade classifier is learned with color descriptors. The general scheme of CAD was based on the realization of algorithm which supposed to capture video frame with the next gamma-correction and conversion of the color scale from RGB to HSV, extraction and selection of descriptors with the final classification of images. The uttermost was performed with the usage of database of proper images and technologies of learning in accordance to cascade classifier learning principles. The gained data revealed that created CAD was able to gain most pronounced true positive diagnoses in cases of liver cysts and liver metastasis which were registered in 84,0 % and 68,0 % of all cases correspondently.

Authors and Affiliations

A. V. Liashenko, L. S. Hodlevskyi, D. M. Baiazitov, A. B. Buzynovskyi

Keywords

Related Articles

Discrete mathematical model of extruder with varied power capacities of heaters and dynamic of polymer phase distribution

Constant growth and development of society contribute to increasing consumption, which leads to the development of production, but also increases competition and product requirements. High-quality goods can only be obtai...

On the issue of automation the road objects visibility distance determining during road accident technical expertise

The problems of traffic accidents occurrence during the nighttime, problems determine the road subject visibility distance of under uncertainty and uncertainty of baseline data on existing methods are analyzed. The techn...

Study of the state of forest resources of zhytomyr region

The state of forest fund is studied; the volume of forest use and reforestation in the region was analyzed, resources of Zhytomyr region is investigated in this work; the structure of the forest, the main reasons for uns...

Mathematical model of heat exchange in the turnover of the surface grinding machine

A mathematical model of the heat transfer process in the coolant tank of a circular grinding machine is proposed. The sequence and dependencies for calculating the coolant temperature at the inlet to the pump of the cool...

Modern methods of high-pressure fuel pump common rail power system diagnostics

We've considered high pressure fuel pumps design features and equipment for their diagnosis. It was noted that the reliability of the fuel elements Common Rail system primarily provide precision parts of the fuel equipme...

Download PDF file
  • EP ID EP254975
  • DOI -
  • Views 95
  • Downloads 0

How To Cite

A. V. Liashenko, L. S. Hodlevskyi, D. M. Baiazitov, A. B. Buzynovskyi (2017). The usage of algorythm based on color descriptor in the laparoscopic images classification. Вісник Житомирського державного технологічного університету. Серія: Технічні науки, 79(1), 128-133. https://europub.co.uk/articles/-A-254975