About Event

Computer Vision technology has been evolving continuously for the past four decades and today it is dominated by Deep learning models. Nowadays many applications like image classification, face recognition, identifying objects in images, video analysis and classification, and image processing in robots and autonomous vehicles use the advanced methods from Deep learning. As many computer vision tasks require intelligent segmentation of an image, to understand what is in the image and enable easier analysis of each part, the medical image segmentation techniques use models of deep learning to understand and can learn patterns in visual inputs in order to learn object classes that make up an image.
The most commonly used deep learning architectures in the field of image understanding are AlexNet, VGG Net, Inception, ResNet and U-NET. Models of deep learning for computer vision are typically trained and executed on specialized graphics processing units (GPUs) to reduce computation time. Convolutional networks have many Hyper-parameters that could impact performance. It is necessary to determine the hyperparameters that provide the best performance for the problem what we are considering. This faculty development programme aims to explore the recent development and deep learning models in the field of medical image analysis. This will be an eye-opener to build the computational skills required to build deep learning models for medical images.