A large number of people worldwide suffer from Gastrointestinal (GI) diseases each year, which can lead to hospitalization. These diseases cause bleeding in the GI tract, which can be detected by video capsule endoscopy (VCE). Manual analysis of VCE images is a time-consuming process that requires skilled clinicians; therefore, automation of this process is essential. In this work, a combined pipeline is proposed for the binary classification of VCE images into bleeding and non-bleeding, and the detection of the bleeding region enabled by the use of multilayered Convolutional Neural Network (CNN)-based model for classification along with a YOLOv8 model. The proposed model is evaluated using precision, recall, F1-Score, and accuracy for classification and mean average precision (mAP) and precision-recall curve for detection model. The proposed methodology has achieved an accuracy of 98.14% and mAP of 0.912 for the identification of the bleeding region, which outperforms the previously available state-of-the-art work.