Scribd
Upload
40 views32 pages

Indian Sign Language Recognition Using Fuzzy Logic

This document summarizes an Indian Sign Language recognition project using image processing and fuzzy logic. It discusses preprocessing video frames into images, segmenting the hand region using edge detection techniques, extracting features, and recognizing the signs using a fuzzy logic approach. Future work includes improving feature extraction and implementing pattern recognition algorithms.

Uploaded by

p.tirumalarao
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
40 views32 pages

Indian Sign Language Recognition Using Fuzzy Logic

This document summarizes an Indian Sign Language recognition project using image processing and fuzzy logic. It discusses preprocessing video frames into images, segmenting the hand region using edge detection techniques, extracting features, and recognizing the signs using a fuzzy logic approach. Future work includes improving feature extraction and implementing pattern recognition algorithms.

Uploaded by

p.tirumalarao
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 32

Indian Sign Language

Recognition Using Fuzzy


Logic
ECE

BATCH NO. 23

H.O.D: B.L.Prakash Sir Guide:


Co-ordinator: Srinivas Sir P.V.V.Kishore sir

Prakash -06L31A0464
Kaneez Fathima -06L31A0480
Ram Prathap -06L31A0453
Raju -07L31A0402
Objective

INSLR A
Literature Review
•A Static Gesture Recognition using Discrete Cosine Transform and NN:

 Kishore sir and Rajesh sir proposed system for recognizing


gestures of Indian Sign Language from images of gestures using NN

•Edge Detection using Dicrete Wavelet Transform and Image Fusion :

by P.V.V.Kishore,D.Prakash Babu ,Gneneshwarnath


Sathapathi, National Conference on Signal Processing and
Communication Systems

•Image Classification using Fuzzy Logic:

 Nedeljkovic
Overview

Introduction
Introduction to Image processing
 Image Preprocessing
Image Segmentation
Feature Extraction
Fuzzy logic for image recognition
Future Work
Introduction

Sign Language

Sign Language Recognition

Indian Sign Language Recognition =

Digital Image processing + Fuzzy logic


Image processing task of our
project

Capture the Video of the Find Edges in Image


Signer

Convert Video Frames into


Extract Elliptical Fourier Descriptors
Images

Preprocessing each Image Applying PCA to get feature vector


for entire video
Frame work of our Project

Preprocessing Preprocessing

Segmentation
Segmentation

Feature Extraction
Feature Extraction

Data Base

Fuzzy Logic

Play Corresponding Speech


Signal
Image Preprocessing

Resize of Image
RGB to Grayscale
Applying filter
Image Preprocessing

Fig: Average filter


Image Preprocessing

Original Video Preprocessed Video


Image Segmentation

 Edge Detection

 Image Fusing
Image Segmentation

Algorithm :

Step 1: Convert a multispectral RGB image into gray scale image.

Step 2: Perform the dilation operation and erosion operations using the same
structuring elements .Subtract Eroded Image from the Dilated Image.

Step 3: Perform the Canny Edge Detection on the original gray scale Image.

Step 4:Decompose the Morphological gradient image and Canny operated Image
into level2 wavelets consisting of approximate, Horizontal, and Vertical and
Diagonal details using DWT.

Step 5: Fuse the Approximate coefficients of both images by the max fusing and the
detail coefficients using min fusing .

Step 6: Reconstruct all the coefficients using IDWT


Edge Detection

Fig: Morphological Gradient


Edge Detection

Fig: Morphological Gradient and Canny operated Decomposition


Edge Detection

Fig: Wavelet Transform


Edge Detection-Image Fusion

Fig: Morphological Gradient and Canny operated Decomposition


Edge Detection

Fig: Sobel Edge Detector


Edge Detection

Fig: Robert Edge Detector


Edge Detection

Fig: Prewitt Edge Detector


Edge Detection

Fig: Canny Edge Detector


Edge Detection

Original video Video after Edge Detection


Morphological Operations

 These are image processing operations done on binary images


based on certain morphologies or shapes.

 Erosion
 Dilation
Erosion and Dilation

Fig: Dilation
Erosion and Dilation

Fig: Erosion
Edge Detection

Segmented Hand sign


Feature Extraction

 Representation

 Object description

 Dimensionality Reduction
Techniques
Fuzzy Logic

 Fuzzy Logic (FL) is a multivalued logic, that allows


intermediate values to be defined between
conventional evaluations like true/false, yes/no,
high/low, etc.
Why Use Fuzzy Logic ?
 Fuzzy logic is conceptually easy to understand.

 Fuzzy logic is flexible.

 Fuzzy logic is tolerant of imprecise data.

 Fuzzy logic is based on natural language.


Future Work

Feature Extraction
Pattern Recognition
THANK
YOU
ANY
SUGGESTIONS

You might also like