Computer Vision (CV)

Computer Vision (CV) is a subfield of Artificial Intelligence (AI) that uses Digital Image Processing (DIP) and Machine Learning (ML) techniques to develop new theories and methods that extract and use information from digital images and videos for automated interpretation and understanding of the visual world. Despite being a seemingly simple task for human beings, interpreting images using computers is a very complex problem and is far from being solved, which provides several research opportunities into the problem of detection, tracking and classification of objects in images. In particular, the study and application of Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) are currently important research topics in the area. CV applications are present in several scenarios, such as optical character recognition (OCR), security, autonomous driving, inspection of industrial parts, medical imaging, robotics, biometrics (face recognition and fingerprint), among others. Because of important recent advances in the field, there is a great demand for computer vision professionals with knowledge in processing and recognition of digital images and videos, and the trend is that this demand will explode in the coming years. Among the various topics studied by professors from the VC line at PPGCC-UFSCar, we can mention: analysis of 2D and 3D biological and medical images (microscopy, magnetic resonance, X-rays, mammography, tomography, among others) aimed at aiding diagnosis of diseases and frontier research in biology, pest control and monitoring using agricultural imagery and statistical techniques for pattern recognition. The methodologies studied by professors in the area are not limited to the problems listed above, and can be used in any application of Computer Vision.