Scribd
Upload
28 views3 pages

New_CV_Syllabus (1)

The document outlines a Computer Vision course (CSBB 314) covering theory and practical applications across various units, including image processing, machine learning, and deep learning techniques. It includes a list of experiments for hands-on learning, reference books, and assessment methods. The course aims to equip students with advanced knowledge and skills in computer vision and machine learning for real-world applications.

Uploaded by

Arya Verma
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
28 views3 pages

New_CV_Syllabus (1)

The document outlines a Computer Vision course (CSBB 314) covering theory and practical applications across various units, including image processing, machine learning, and deep learning techniques. It includes a list of experiments for hands-on learning, reference books, and assessment methods. The course aims to equip students with advanced knowledge and skills in computer vision and machine learning for real-world applications.

Uploaded by

Arya Verma
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

COMPUTER VISION (CSBB 314)

Theory:

Unit I: Introduction to computer vision (4 Hours)

Overview of Computer Vision, Applications of Computer Vision in Robotics, Healthcare, and


Autonomous Vehicles, Basic Image Formation and Representation, Image Filtering:
Smoothing, Sharpening, and Histogram Equalization.

Unit II: Image Processing and Feature Detection Fundamentals (8 Hours)

Grayscale and Color Image Processing, Image Transformations: Fourier Transform, Discrete
Cosine Transform (DCT), Edge Detection: Sobel, Canny, and Laplacian, Corner and Blob
Detection (Harris Corner Detector, FAST, SIFT, and SURF), Image Matching and
Transformation: Homography and RANSAC, Keypoint Descriptors

Unit III: Machine Learning for Computer Vision Tasks (8 Hours)

Classification: SVMs, KNN, Decision Trees, Introduction to Neural Networks and


Convolutional Neural Networks (CNNs), Deep Learning Architectures for Vision (AlexNet,
ResNet, VGG), Anomaly Detection in Images (e.g., Autoencoders), Applications: Face
Recognition, Gesture Recognition, and Scene Understanding

Unit IV: Convention computer vision and algorithms (10 Hours)

Object detection and segmentation e.g. Edge, texture, region, detection of sliding windows:
Feature extraction, e.g. linear binary pattern, principal component analysis, Gabor filters, bags
of features, Matching and recognition e.g. Bayesian classifier, support vector machine, fusion,
Image alignment and stitching. Principal Component Analysis (PCA)

Unit V: Deep learning and Neural Networks for computer vision (6 Hours)

Key components and basic architecture of deep neural network , Convolution neural network,
Object detection using R-CNN, Segmentation using image-to image neural network, Temporal
processing and recurrent neural network.
List of Experiment:
1. To implement data visualization techniques such as box plot, scatter plot, and Q plot for
comprehensive analysis of a given dataset.
2. To apply Gaussian, Median, and Bilateral filters to reduce noise in images while preserving
important structural details.
3. To enhance and detect edges in images by applying Sobel, Prewitt, and Laplacian filters,
emphasizing significant transitions in pixel intensity.
4. To classify images using a Support Vector Machine (SVM) model and assess performance
through cross-validation and key metrics such as accuracy and confusion matrix.
5. To apply Convolutional Neural Networks (CNNs) for image classification and evaluate the
model's performance using standard metrics such as accuracy and confusion matrix.
6. To implement K-Nearest Neighbors (KNN) for image classification and evaluate its
effectiveness through cross-validation and performance metrics such as accuracy.
7. To apply the Fast Fourier Transform (FFT) to convert images into the frequency domain
and filter out high-frequency noise, enhancing image quality.
8. To apply Principal Component Analysis (PCA) for reducing the dimensionality of image
datasets while retaining the most significant features.
9. To extract texture features from images using Gabor filters, enhancing the understanding
of surface patterns and texture-related information.
10. To perform object detection by leveraging Region-based Convolutional Neural Networks
(R-CNN) for detecting and classifying objects in images.
11. To implement Long Short-Term Memory (LSTM) networks for sequential image
classification and evaluate the model’s performance using cross-validation and accuracy
metrics.
12. To classify images using a Decision Tree model and evaluate its performance using cross-
validation and metrics such as accuracy, precision, and recall.

Reference Books:

1. Computer Vision: Algorithms and Applications


Author: Richard Szeliski
Publisher: Springer

2. Computer Vision: a Modern Approach


Author: David Forsyth and Jean Ponce
Publisher: Pearson

3. Multiple View Geometry in Computer Vision


Author : Richard Hartley and Andrew Zisserman
Publisher: Cambridge University Press
Course Assessment:

• Continuous Evaluation 25%

• Mid Semester 25%

• End Semester 50%

Course Objectives and Outcomes:

Provide students with advanced knowledge of


Computer Vision, and Machine Learning, enabling
them to design, implement, and apply various models.

CO No. Course Outcome Level


CO1 Understand foundational concepts including neural L1, L2, L3
networks, training methods, and optimization
techniques.
CO2 Develop and evaluate convolutional neural networks L4, L5, L6
(CNNs) for image classification and object
detection.
CO3 Design recurrent neural networks (RNNs) and L4, L5, L6
Transformer models for NLP and time-series
analysis.
CO4 Implement advanced techniques for generative L4, L5, L6
modeling, speech recognition, and gesture
recognition.

PO No. Program Outcome


PO1 Apply concepts to design efficient computational solutions for real-world
problems.
PO2 Utilize modern tools and frameworks to develop and optimize models.
PO3 Analyze and interpret data for applications in computer vision
and NLP.
PO4 Engage in continuous learning to adapt to evolving technologies
in AI.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy