Feature Extraction Statistical Feature ExtractionTexture Geometry Feature ExtractionFingerprint

  • Slides: 29
Download presentation
嵌入式視覺 Feature Extraction • Statistical Feature Extraction(Texture) • Geometry Feature Extraction(Fingerprint)

嵌入式視覺 Feature Extraction • Statistical Feature Extraction(Texture) • Geometry Feature Extraction(Fingerprint)

Texture Feature Extraction Texture is a description of the spatial arrangement of color or

Texture Feature Extraction Texture is a description of the spatial arrangement of color or intensities in an image or a selected region of an image.

Natural Textures grass leaves

Natural Textures grass leaves

Texture as Statistical Feature • Segmenting out texels is difficult or impossible in real

Texture as Statistical Feature • Segmenting out texels is difficult or impossible in real images. • Numeric quantities or statistics that describe a texture can be computed from the gray tones (or colors) alone. • This approach is less intuitive, but is computationally efficient. • It can be used for both classification and segmentation.

Simple Statistical Texture Measures 1. Edge Density and Direction • Use an edge detector

Simple Statistical Texture Measures 1. Edge Density and Direction • Use an edge detector as the first step in texture analysis. • The number of edge pixels in a fixed-size region tells us how busy that region is. • The directions of the edges also help characterize the texture

Two Edge-based Texture Measures 1. edgeness per unit area Fedgeness = |{ p |

Two Edge-based Texture Measures 1. edgeness per unit area Fedgeness = |{ p | gradient_magnitude(p) threshold}| / N where N is the size of the unit area 2. edge magnitude and direction histograms Fmagdir = ( Hmagnitude, Hdirection ) where these are the normalized histograms of gradient magnitudes and gradient directions, respectively.

Example Original Image Frei-Chen Edge Image Thresholded Edge Image

Example Original Image Frei-Chen Edge Image Thresholded Edge Image

Local Binary Pattern • For each pixel p, create an 8 -bit number b

Local Binary Pattern • For each pixel p, create an 8 -bit number b 1 b 2 b 3 b 4 b 5 b 6 b 7 b 8, where bi = 0 if neighbor i has value less than or equal to p’s value and 1 otherwise. • Represent the texture in the image (or a region) by the histogram of these numbers. 1 8 2 3 100 101 103 40 50 80 50 60 90 7 6 11111100 4 5

Co-occurrence Matrix Features A co-occurrence matrix is a 2 D array C in which

Co-occurrence Matrix Features A co-occurrence matrix is a 2 D array C in which • Both the rows and columns represent a set of possible image values. • Cd (i, j) indicates how many times value i co-occurs with value j in a particular spatial relationship d. • The spatial relationship is specified by a vector d = (dr, dc).

Co-occurrence Matrix gray-tone image 1 1 0 0 0 2 2 2 2 d

Co-occurrence Matrix gray-tone image 1 1 0 0 0 2 2 2 2 d = (3, 1) 1 012 i 3 j 0 1 2 103 202 001 co-occurrence matrix Cd From Cd we can compute Nd, the normalized co-occurrence matrix, where each value is divided by the sum of all the values.

Co-occurrence Features

Co-occurrence Features

Laws’ Texture Energy Features The Laws Algorithm : • Filter the input image using

Laws’ Texture Energy Features The Laws Algorithm : • Filter the input image using texture filters. • Compute texture energy by summing the absolute value of filtering results in local neighborhoods around each pixel. • Combine features to achieve rotational invariance.

Law’s texture masks (1)

Law’s texture masks (1)

Law’s texture masks (2) Creation of 2 D Masks E 5 L 5 E

Law’s texture masks (2) Creation of 2 D Masks E 5 L 5 E 5 L 5

9 D feature vector for pixel • Subtract mean neighborhood intensity from (center) pixel

9 D feature vector for pixel • Subtract mean neighborhood intensity from (center) pixel • Apply 16 5 x 5 masks to get 16 filtered images Fk , k=1 to 16 • Produce 16 texture energy maps using 15 x 15 windows Ek[r, c] = ∑ |Fk[i, j]| • Replace each distinct pair with its average map: • 9 features (9 filtered images) defined as follows:

Laws Filters

Laws Filters

Example: Using Laws Features to Cluster water tiger fence flag grass small flowers big

Example: Using Laws Features to Cluster water tiger fence flag grass small flowers big flowers

Features from sample images

Features from sample images

Autocorrelation function • Autocorrelation function can detect repetitive patterns • Also defines fineness/coarseness of

Autocorrelation function • Autocorrelation function can detect repetitive patterns • Also defines fineness/coarseness of the texture • Compare the dot product (energy) of non shifted image with a shifted image

Interpreting autocorrelation • • Coarse texture function drops off slowly Fine texture function drops

Interpreting autocorrelation • • Coarse texture function drops off slowly Fine texture function drops off rapidly Can drop differently for r and c Regular textures function will have peaks and valleys; peaks can repeat far away from [0, 0] • Random textures only peak at [0, 0]; breadth of peak gives the size of the texture

Fourier power spectrum • High frequency power fine texture • Concentrated power regularity •

Fourier power spectrum • High frequency power fine texture • Concentrated power regularity • Directionality directional texture

Feature Extraction Process • Input: image • Output: pixel features – Color features –

Feature Extraction Process • Input: image • Output: pixel features – Color features – Texture features – Position features • Algorithm: Select an appropriate scale for each pixel and extract features for that pixel at the selected scale Original image feature extraction Pixel Features Polarity Anisotropy Texture contrast

Geometry Feature Extraction (Fingerprint)

Geometry Feature Extraction (Fingerprint)

Image Enhancement - Gabor Filtering

Image Enhancement - Gabor Filtering

Image Processing Raw Image Enhanced Image Skeleton Image (2. 2)

Image Processing Raw Image Enhanced Image Skeleton Image (2. 2)

Fingerprint Feature : Minutia Ending Point Bifurcation Point

Fingerprint Feature : Minutia Ending Point Bifurcation Point

Minutia Extraction

Minutia Extraction