Conquering knowledge from images: improving image mining with region-based analysis and associated information
Mirela T. Cazzolato · 2019
The popularization of social media, combined with the widespread use of smartphones and the use of advanced equipment in hospitals and medical centers has generated sequences of complex data, including images of high quality and in large quantity. Providing appropriate tools to extract meaningful knowledge from such data is a big challenge. While many potential techniques have been proposed to analyze images, most of the processing performed by image mining techniques consider the entire image. Thus, regions that are not of interest are considered in the analysis step, without proper distinction and consequently damaging most tasks. This doctorate research focused on the thesis that by taking advantage of small representations of images we can improve the overall results of different image analysis tasks. Then, we employed classification, clustering, and temporal data analysis algorithms, according to the application. We evaluate this thesis in three application scenarios. In the first scenario, we analyzed regions of images from emergencies, gathered from social media and which depict smoke regions. We were able to segment smoke regions and improve the classification of smoke images by up to 23%, compared to global approaches. In the second scenario, we worked with images from the medical context, containing Interstitial Lung Diseases (ILD). We classified the images considering the uncertainty of each lung region to contain different abnormalities, representing the obtained results with a heat map visualization. Our approach outperformed its competitors in the classification of lung regions by up to four of five classes of abnormalities. In the third scenario, we dealt with sequences of microscopic images depicting embryos being developed over time. Using regionbased information of images, we were able to track and predict cells over time and build their motion vector. Our approaches showed an improvement of up to 57% in quality, and a speed-up of the tracking pipeline by up to 81.9%. Therefore, this doctorate research contributed to the state-of-the-art by introducing methods of region-based image analysis for the three application scenarios mentioned above.