Marcin Macias
supervisor: Przemysław Rokita
In this poster I have collected all the motivation and the information related to my current research. The main goal of my PhD thesis is to improve existing algorithms or propose new ones that can be used in the problem of automatic detection and comprehension of small objects in the RGB images. The real life examples of such classes that I currently focus on involves labels used in the retail stores that contain price information about the presented product. Those labels can be treated as anomalies on the initial image, if we compare their size with rest of the image. This data is usually easily noticeable by a human eye and is highly important for the later analysis. Nowadays this price tag detection is quite important due to high inflation worldwide. My task requires usage of different image analysis, segmentation and processing techniques and each of those methods has some known drawbacks and minor imperfections that I hope to improve. After the complex research of state-of-the-art literature, I have focused my efforts on the implementation of such processing flow and collection of benchmark dataset from the real life examples. I am currently finishing the implementation phase and moving to experiments and validation of my work.