Image filtering: compute function of local neighborhood at each position

1. Image filters in spatial domain

– Filter is a mathematical operation of a grid of numbers

– Smoothing, sharpening, measuring texture

1. Image filters in the frequency domain

– Filtering is a way to modify the frequencies of images

– Denoising, sampling, image compression

– Enhance images

• Denoise, resize, increase contrast, etc.

– Extract information from images

• Texture, edges, distinctive points, etc.

– Detect patterns

• Template matching

– Deep Convolutional Networks

Box Filter:

• Replaces each pixel with an average of its neighborhood
• Achieve smoothing effect(remove sharp features)