You are on page 1of 14

Digit recognition based on

using template matching


Presented By:
Anik Deb Nath
ID: 1803510201673
Dept. of CSE, PUC
01 Objective

02 Motivation

03 Applications

Contents 04 Methodology

05 Processing Example

06 Conclusion
07 Appendix
01 Objectives
• Recognition digit for given image using template matching .

(a)

Matching similarity by NCC

(b)
g

(c)

Figure for Processing Example : (a) Template & candidate image (b)
Template matching algoithm (c) Recognize digit image
02 Motivation

Traditional methods often struggle to handle various fonts, styles, and


01 handwriting.

02 To minimize human error, inefficiencies and inaccuracies.

03 Ensuring accurate digit extraction and interpretation,


03 Applications
• Numeric entries in forms filled up by hand
• Processing bank check amounts
• Room Number
04 Methodology
Template
Input image normalize by size
Candidate(digit)

Convert images to grayscale.

Convert to binary using Otsu's thresholds

Complement Binary Images

Calculate Candidate Mean

NCC Loop

Find Best Match

Visualize result by rectangle box


05 Process Example - 1

Fig 1: Read RGB image and convert Fig 2: Convert gray to binary and Fig 3: Display the current template,
to grayscale image take the complement of binary candidate and best match
image
06 Process Example -2

Fig 1: Read RGB image and convert Fig 2: Convert gray to binary and Fig 3: Display the current template,
to grayscale image take the complement of binary candidate and best match
image
07 Conclusion

In conclusion, the code demonstrates a basic implementation of digit recognition using the NCC
technique.

Merits of NCC: Demerits of NCC:


• Easy to understand and implement. • Can be slow for large images.
• Effective for finding patterns. • Only good for exact or near-exact matches.
• Affected by similar patterns in the background.
• Clear interpretation of results.
• Challenging to set accurate thresholds.
• Doesn't need extensive training.
• Struggles with noise, and variations.
08 Appendix
09 Appendix
10 Appendix
11 Appendix
Thank You

You might also like