NeuroNomixer logoNeuroNomixer
  • Home
  • Blog
  • Visual Guides
  • Authors
  • Contact
Sign InSign Up
NeuroNomixer logo
HomeBlogAuthorsContactPrivacy Policy

© 2026 NeuroNomixer — Built with Next.js & Tailwind CSS

Visual Guides/CNNs: See What Filters See
Deep Learning

CNNs: See What Filters See

Watch convolutional filters slide across images and produce feature maps. Explore edge detection, sharpening, and blur kernels: the same operations that power image recognition models.

Exploration Progress1/3 filters explored  · 0/1 hierarchy viewed

Sign in to save progress

1

Select a Sample Image

2

Choose a Filter

1/6 explored

These are classic hand-crafted kernels, chosen so you can see the mechanics of convolution. In a real CNN the filter values are learned from data during training; nobody writes them by hand. Early layers usually converge to edge-like detectors resembling these; deeper layers combine them into texture and object-part detectors.

Filter Kernel

3×3 weight matrix applied at each position

-1
-1
-1
0
0
0
1
1
1

Horizontal lines & edges

Detects horizontal boundaries where pixel brightness changes top-to-bottom.

Positive
Negative
Zero
3

Watch the Convolution

Convolution Visualizer

1 / 36

Input (8×8): Checkerboard

Orange box = current 3×3 patch. Stride = 1, no padding, which is why the 8×8 input shrinks to a 6×6 output.

→

Output (6×6): Horizontal Edge

0

Green border = current output cell

Computation at position (0,0)

Patch (÷255)

1.00
0.00
1.00
0.00
1.00
0.00
1.00
0.00
1.00
⊙

Kernel

-1
-1
-1
0
0
0
1
1
1
=

Sum

0.000

→ Display (0–255)

0

Element-wise multiply → sum → the whole output map is then min-max rescaled to 0–255 purely for display.

Run convolution to see feature map

4

How Layers Stack

How Layers Stack

Click each layer to see what it detects. Each layer builds on the previous.

Input8×8Layer 1Early LayerEdges & linesclick to exploreLayer 2Mid LayerShapes & texturesclick to exploreLayer 3+Deep LayerObjects & conceptsclick to exploreOutputPrediction

Click a layer above to complete this section

Key Insight

Real CNNs stack 10–100+ of these layers. Early layers detect edges, middle layers detect shapes, and deep layers detect complex features like faces or cars. Each layer's output becomes the next layer's input, building from simple to abstract.

← Previous GuideNext Guide →