Computer Vision, a dynamic field within Deep Learning, intersects various disciplines such as computer science, mathematics, and cognitive science, and is seen as a pathway to Artificial General Intelligence due to its cross-domain expertise. The article explores major computer vision techniques, highlighting the use of Convolutional Neural Networks (CNNs) in tasks like image classification, object detection, and semantic segmentation. Image classification involves predicting categories for test images, while object detection focuses on identifying and labeling objects within images using techniques like Faster R-CNN and YOLO. Semantic segmentation goes further by classifying each pixel in an image, a task facilitated by Fully Convolutional Networks (FCNs) and Mask R-CNN. Object tracking and segmentation are also addressed, emphasizing the role of CNNs in extracting, analyzing, and understanding visual data. The article concludes by encouraging further exploration of the field through courses, tutorials, and resources, citing Stanford's CS231n as an excellent starting point.