The YOLOv8 is a deep learning model used for real-time object detection, classification, and segmentation known for its high speed and accuracy. The performance of the model is evaluated using metrics such as precision, recall, and mean Average Precision (mAP). The dataset used for training consists of images of crop and weed from sesame crop field. The dataset also contains the labels for images which helps the model for crop-weed detection. The dataset is trained using yolov8n model and then tested on unseen data. The evaluated accuracy from the performance metrics is 97.96%. Weeds are a major threat to agricultural productivity. They are the unwanted plants that grow along with the crops. The traditional weed control methods, such as the use of harmful pesticides or removal of weed manually, have proven to be inefficient, costly, and harmful to the environment. To overcome this challenge, this study explores the application of machine learning for crop-weed detection, in which weed can be detected and helpful measures can be taken to get rid of it. This application help farmer to target weed which minimizes the use of pesticides and herbicides and also reduces manual labor. For image detection, machine learning offers various algorithms such as K-Nearest Neighbors (KNN), Support Vector Machines (SVM) and many more. Deep learning is sub-branch of machine learning, which deals with real-world application, also offers various algorithms such as Convolutional Neural Networks (CNNs), Faster Region-Convolutional Neural Networks (R-CNN), and YOLO. In this study, You Only Look Once, version 8(YOLOv8) object detection framework is used to train the dataset.