Color Detection & Segmentation based Invisible Cloak
0 likes75 views
This document summarizes a student project that aims to create an invisible cloak using color detection and segmentation techniques in image processing. The objectives are to capture background images, detect colored objects in the frame using HSV color space, generate a mask to segment out the colored object, and combine the processed frames to create the effect of invisibility. The methodology involves capturing images using a webcam, processing them with OpenCV libraries, and testing the cloak in real-time. So far the team has completed capturing background images and detecting and segmenting colored objects, and is working on combining the frames. Accuracy and precision metrics will be used to evaluate the model's performance.
![Faculty of Electronics Engineering (ECE),UNSIET, VBSPU
PROJECT ROGRESS REVISED REPORT- I
PROJECTTITLE: Color Detection & Segmentation based Invisible Cloak
AREAOF WORK:Digital Image Processing
TYPE OF MODEL:Software [Python 3.11 (64bit)]
MODULES USED IN PYTHON: Open CV, NumPy, PIL, Socket, Tkinter
PROJECTAIM & OBJECTIVES:
AIM: This project aims to creates a magical experience by using an Image Processing
technique called Color Detection & Segmentation resulting in false sense of Invisibility in the
frame.
PROJECT OBJECTIVES: The main objective of the invisibility cloak project is to develop
a cloak or material that can render objects invisible to the human eye.
Objective#1: Initializing, Capturing & storing the background frame through a digital camera.
Objective#2: Detect the cloth using Color Detection by choosing appropriate HSV color space.
Objective#3: Segment out the colored cloth by generating a mask.
Objective#4: Applying Mask on frame & Combine mask frames together.
PROPOSED DESIGN METHODOLOGY: Overall, the Proposed Design
methodology involves capturing images, processing them using Image Processing operations
and testing the Invisibility Cloak in real-time using digital web camera. Proposed Design is
depicted in the Fig.1.
PROGRESS IN WORK: During this course of time Objective#1, Objective# 2 and
Objective#3 are completed & Objective#4 is under progress as detailed below,](https://image.slidesharecdn.com/reviewreport-230910083250-64bce5e4/85/Color-Detection-Segmentation-based-Invisible-Cloak-1-320.jpg)
More Related Content
Similar to Color Detection & Segmentation based Invisible Cloak (20)
More from Aviral Chaurasia (11)
Recently uploaded (20)
Color Detection & Segmentation based Invisible Cloak
- 1. Faculty of Electronics Engineering (ECE),UNSIET, VBSPU PROJECT ROGRESS REVISED REPORT- I PROJECTTITLE: Color Detection & Segmentation based Invisible Cloak AREAOF WORK:Digital Image Processing TYPE OF MODEL:Software [Python 3.11 (64bit)] MODULES USED IN PYTHON: Open CV, NumPy, PIL, Socket, Tkinter PROJECTAIM & OBJECTIVES: AIM: This project aims to creates a magical experience by using an Image Processing technique called Color Detection & Segmentation resulting in false sense of Invisibility in the frame. PROJECT OBJECTIVES: The main objective of the invisibility cloak project is to develop a cloak or material that can render objects invisible to the human eye. Objective#1: Initializing, Capturing & storing the background frame through a digital camera. Objective#2: Detect the cloth using Color Detection by choosing appropriate HSV color space. Objective#3: Segment out the colored cloth by generating a mask. Objective#4: Applying Mask on frame & Combine mask frames together. PROPOSED DESIGN METHODOLOGY: Overall, the Proposed Design methodology involves capturing images, processing them using Image Processing operations and testing the Invisibility Cloak in real-time using digital web camera. Proposed Design is depicted in the Fig.1. PROGRESS IN WORK: During this course of time Objective#1, Objective# 2 and Objective#3 are completed & Objective#4 is under progress as detailed below,
- 2. Faculty of Electronics Engineering (ECE),UNSIET, VBSPU a) We need to capture the background image of the scene without the object you want to hide. This can be done using a camera or by selecting an image of the background. b) Using OpenCV, generate a mask that will separate the object from the background. This can be done by applying image thresholding, (segmentation) that will allow you to isolate the object. c) Once we have generated a mask, you can apply image processing techniques to the object such as morphological transformations. This will make the object appear invisible. d) Once the processing is complete, test the invisibility cloak in real-time. This can be done using a webcam. e) Redefine the Design:Make any necessary modifications to the design to improve its overall performance, such as implementing on GUI for smooth interface. PROPOSED DESIGN EVALUATION METRICS we can utilize several evaluation metrics to measure the quality of our color detection and segmentation techniques. We will evaluate Accuracy & Precision for our proposed model. Accuracy is a widely used evaluation metric, especially in classification tasks, to assess the overall performance of a model or system. To measure accuracy, you compare the number of correct predictions made by your system to the total number of predictions made. Here's the formula for calculating accuracy: Accuracy = (Number of Correct Predictions) / (Total Number of Predictions) Precision measures the proportion of correctly detected colors among all detected colors, indicating how precise our system is in identifying the person and background colors. Calculate the true positives (TP), which are the colors correctly detected as belonging to the person's clothing & calculate the false positives (FP), which are the colors incorrectly detected as belonging to the person's clothing. Precision = TP / (TP + FP) Segment out the defined colored part bygenerating mask & applying it on frame Capture & Storebackground frame using Image Acquisition by Store a single frame before startingthe infinite loop. Generatethe finaloutput to create a magical effect by combining frames together, & remove the unnecessarynoise from masks. Detect the definedcolor using color detection & segmentation algorithm Using HSV Model
- 3. Faculty of Electronics Engineering (ECE),UNSIET, VBSPU COMPARATIVE ANALYSIS FUNCTIONALITYOF THE SYSTEM Correct Predictions Total Processed Frame Accuracy Precision 85 100 0.85 0.83 98 100 0.98 0.96 89 100 0.89 0.86 93 100 0.93 0.91 81 100 0.81 0.82 93 100 0.93 0.92 Choose Webcam: Stream Web Cam: If you want to connect with System Webcam (Inbuilt or Connected Directly To System) 0 for your inbuilt webcam in system and goes like 1,2,3.... according to webcam connected. 1 for webcam connected externally to your system. To connect to CCTV, Android Camera or to any other camera having IP Address IP Address: IP Address of Your Camera (Example: 192.168.43.1) Port: Port of Connection (Example: 1111) Refresh: To Refresh the page to show valid options (always refresh when you change the source) Connect: To Connect to Camera Change Background: Show Background: To Change The background (This Background is used to create the invisibility) To Show Current using Background Calibrate To Set HSV Values (Keep in Mind: The White Part In calibrating window will become invisible) Start Magic: To Start the Magic (That Make You Invisible) Stop Magic: To Stop Magic Disconnect Exit: To Disconnect from current Source To Exit the Program
- 4. Faculty of Electronics Engineering (ECE),UNSIET, VBSPU EVALUATION REMARKS BYPROJECTCOORDINATOR(S): PROJECTREPORTED: NAME & SIGNATURE OF TEAM MEMBERS: Aviral Chaurasia (195209) Ayush Singh (195206) Prashant Rai(195231) (APPROVED/NOT-APPROVED) ______________________________ NAME & SIGNATURE OF PROJECT SUPERVISOR (With Date) Mr. PC Yadav (Assistant Professor) Department of Electronics Engineering, UNSIET, VBSPU. 100%