Computer Vision
University of Lincoln Assessment Framework
Assessment Briefing Template 2021-2022
| Module Code & Title: CMP9135M Computer Vision |
| Contribution to Final Module Mark: 100% |
| Description of Assessment Task and Purpose: Requirements: This assessment comprises three assessed tasks, as detailed in the following page. 1. Image segmentation and detection. Weight: 40% of this component 2. Feature calculation. Weight: 30% of this component 3. Object tracking. Weight: 30% of this component Task 1: Image Segmentation and Detection Download and unzip the file ‘skin lesion dataset.zip’ from Blackboard. You should obtain a set of 120 images. Among those images, there are 60 skin lesion colour images and 60 corresponding binary masks (ground-truth segmentation). Please use image processing techniques to implement the following tasks. Please note that you are encouraged to develop one model with same parameter settings for all the images. Task 1: Object segmentation. For each skin lesion image, please use image processing techniques to automatically segment lesion object. Examples of the lesion image (Fig.1(a) and the segmented lesion (Fig.1(b)) are shown in Figure 1. Task 2: Segmentation evaluation. For each skin lesion image, calculate the Dice Similarity Score (DS) which is defined in Equation 1; where M is the segmented lesion mask obtained from Task 1, and S is the corresponding ground-truth binary mask. DS = 2| |
AssignmentTutorOnline