Blurring and smoothing (Gaussian, median, bilateral) in Computer Vision - Model Pipeline Trace

Model Pipeline - Blurring and smoothing (Gaussian, median, bilateral)

This pipeline shows how an image is processed to reduce noise and details using three common blurring techniques: Gaussian blur, median blur, and bilateral filter. These methods help improve image quality for tasks like object detection or recognition by smoothing the image while preserving important features.

Data Flow - 4 Stages

1Input Image

1 image x 256 height x 256 width x 3 channels→Load a color image with RGB channels→1 image x 256 height x 256 width x 3 channels

A photo of a cat with some noise and sharp edges

↓

2Gaussian Blur

1 image x 256 x 256 x 3→Apply Gaussian filter with kernel size 5x5 to smooth image by averaging pixels with Gaussian weights→1 image x 256 x 256 x 3

Image looks softer with edges slightly blurred, noise reduced

↓

3Median Blur

1 image x 256 x 256 x 3→Apply median filter with kernel size 5 replacing each pixel with median of neighbors to remove salt-and-pepper noise→1 image x 256 x 256 x 3

Image has less noise, edges preserved better than Gaussian blur

↓

4Bilateral Filter

1 image x 256 x 256 x 3→Apply bilateral filter with diameter 9, sigmaColor 75, sigmaSpace 75 to smooth image while preserving edges→1 image x 256 x 256 x 3

Image is smooth but edges remain sharp, noise reduced

Training Trace - Epoch by Epoch

Loss
0.5 |****
0.4 |****
0.3 |***
0.2 |**
0.1 |*
    +------------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.45	0.60	Initial smoothing reduces noise, improving model accuracy
2	0.35	0.72	Gaussian blur helps model learn better features
3	0.30	0.78	Median blur further reduces noise, accuracy improves
4	0.25	0.83	Bilateral filter preserves edges, leading to best accuracy
5	0.22	0.86	Model converges with smooth, edge-preserved images

Prediction Trace - 4 Layers

Layer 1: Input Image

Layer 2: Gaussian Blur

Layer 3: Median Blur

Layer 4: Bilateral Filter

Model Quiz - 3 Questions

Which blurring method best preserves edges while reducing noise?

A Bilateral filter

B Gaussian blur

C Median blur

D No blur

Key Insight

Blurring and smoothing techniques reduce noise in images, helping models learn better. Gaussian blur smooths softly but can blur edges. Median blur removes salt-and-pepper noise well. Bilateral filter smooths while keeping edges sharp, often improving model accuracy the most.