Admissions Open for JANUARY Batch

UPMENTA COURSES IMAGES (11)

Explore image processing math – convolution, pooling, and feature extraction.

Days : Tue & Thu

Duration : 3 Hours

Timings: 8 - 10 PM IST

Try Risk-free, 15 Days Money Back Guarantee

3 Hours

9 - 10 PM IST

Tue & Thu

Maths for Computer Vision

Explore image processing math – convolution, pooling, and feature extraction.

Online Live Instructor-Led Learning

3 Hours

8 - 10 PM IST

Tue & Thu

By end of this course

Get stronger in

Convolution and feature map calculation

Pooling and dimensionality reduction

Get familier with

Edge detection filters

Image classification math concepts

New Batch Starts : jan 2026

Limited seats only 15 students per batch

Who Should Enroll?

This course is for learners interested in understanding the mathematical foundations of computer vision, including convolution operations, pooling, and feature extraction ideal for those pursuing expertise in image processing and vision AI

Prerequisites

Knowledge of matrix operations and CNN basics.

Experience our course risk-free

We offer a 15-day money back guarantee

Prerequisite

Knowledge of matrix operations and CNN basics.

Who Should Enroll?

This course is for learners interested in understanding the mathematical foundations of computer vision, including convolution operations, pooling, and feature extraction ideal for those pursuing expertise in image processing and vision AI

By end of this course

Get Stronger in

  • Convolution and feature map calculation
  • Pooling and dimensionality reduction

Get Familiar in

  • Edge detection filters
  • Image classification math concepts

Course Contents

Day 1 - Convolutional Operations

Topics

  • Convolution as linear operator
  • Kernel math and feature extraction
  • Padding, stride, dilation effects

Key Outcomes

Derive and interpret convolution layers

Day 2 - Feature Maps & Receptive Fields

Topics

  • Mathematical definition of feature maps
  • Receptive field calculation
  • Hierarchical feature extraction math

Key Outcomes

Understand CNN spatial transformations

Day 3 - Pooling & Feature Pyramids

Topics

  • Pooling as down sampling operator
  • Max vs average pooling derivation
  • Feature pyramid network (FPN) formulation

Key Outcomes

Design and optimize vision architectures

Day 1 - Convolutional Operations

Topics

  • Convolution as linear operator
  • Kernel math and feature extraction
  • Padding, stride, dilation effects

Key Outcomes

Derive and interpret convolution layers

Day 2 - Feature Maps & Receptive Fields

Topics

  • Mathematical definition of feature maps
  • Receptive field calculation
  • Hierarchical feature extraction math

Key Outcomes

Understand CNN spatial transformations

Day 3 - Pooling & Feature Pyramids

Topics

  • Pooling as down sampling operator
  • Max vs average pooling derivation
  • Feature pyramid network (FPN) formulation

Key Outcomes

Design and optimize vision architectures