Processing Digital Images

1
Processing Digital Images
2
Processing Digital Images

• Filtering
• Analysis
• Recognition
• Transmission

3
Filtering

• digital images are often processed using digital
  filters
• digital filters are based on mathematical
  functions that operate on the pixels of the image

4
Filtering

• there are two classes of digital filters global
  and local
• global filters transform each pixel uniformly
  according to the function regardless of its
  location in the image
• local filters transform a pixel depending upon
  its relation to surrounding ones

5
Global Filters

• Brightness and Contrast control
• Histogram thesholding
• Histogram stretching or equalization
• Color corrections
• Hue-shifting and colorizing
• Inversions

6
Local Filters

• Sharpening
• Blurring
• Unsharp Masking
• Edge and line detection
• Noise filters

7
Local Filters

• Edge and line detection filters subtract all
  parts of the image except edges or boundaries
  between two different regions
• edge detection is often used to recognized
  objects of interest in the image

edges and lines detected in an image of toy blocks
8
Analysis

• Image improvement
• Eliminating noise (due to external effects or
  missing pixels), or by increasing the contrast
• Pattern Discovery and Recognition
• OCR Optical Character Recognition
• Scene Analysis and Computer Vision
• Recognition and reconstruction of 3D models of
  the scene.
• Industrial robot that measures the relative
  sizes, shapes, positions, and color of the
  objects.

9
Image Properties

• Color
• Use color histogram
• Texture
• Surface structure
• Use gray-level representation
• Edge detection

10
Steps involved in image recognition
11
Formatting and Conditioning

• Image Formatting
• Image Formatting means capturing an image by
  bringing it into a digital form
• Conditioning
• In an image, there are usually features which are
  uninteresting, either because they were
  introduced into the image during the digitization
  process as noise, or because they form part of a
  background. An observed image is composed of
  informative patterns modified by uninteresting
  random variations. Conditioning suppresses, or
  normalizes, the uninteresting variations in the
  image, effectively highlighting the interesting
  parts of the image.

12
Labeling

• Informative patterns in an image have structure.
• Patterns are usually composed of adjacent pixels
  which share some property such that it can be
  inferred that they are part of the same structure
  (e.g., an edge).
• Edge detection techniques focus on identifying
  continuous adjacent pixels which differ greatly
  in intensity or colour, because these are likely
  to mark boundaries, between objects, or an object
  and the background, and hence form an edge. After
  the edge detection process is complete, many edge
  will have been identified. However, not all of
  the edges are significant.
• Thesholding filters out insignificant edges. The
  remaining edges are labeled. More complex
  labeling operations may involve identifying and
  labeling shape primitives and corner finding.

13
Grouping

• Grouping can turn edges into lines by determining
  that different edges belong to the same spatial
  event. The first 3 operations represent the image
  as a digital image data structure (pixel
  information), however, from the grouping
  operation the data structure needs also to record
  the spatial events to which each pixel belongs.
  This information is stored in a logical data
  structure.

14
Extracting

• Grouping only records the spatial event(s) to
  which pixels belong. Feature extraction involves
  generating a list of properties for each set of
  pixels in a spatial event.
• These may include a set's centroid, area,
  orientation, spatial moments, grey tone moments,
  spatial-grey tone moments, circumscribing circle,
  inscribing circle, etc. Additionally properties
  depend on whether the group is considered a
  region or an arc. If it is a region, then the
  number of holes might be useful. In the case of
  an arc, the average curvature of the arc might be
  useful to know.
• Feature extraction can also describe the
  topographical relationships between different
  groups. Do they touch? Does one occlude another?
  Where are they in relation to each other? etc.

15
Matching

• Finally, once the pixels in the image have been
  grouped into objects and the relationship between
  the different objects has been determined, the
  final step is to recognise the objects in the
  image.
• Matching involves comparing each object in the
  image with previously stored models and
  determining the best match template matching.

16
Transmission

• Transmission through network
• Formats
• Raw Digital Image
• Compressed Digital Image
• Symbolic Representation

17
Editing Images

• editing or retouching an image involves selecting
  a region of the digital image for processing
  using some special effect
• image compositing combines components of two or
  more images into a single image
• painting (or rotoscoping) an image is to edit the
  image by hand with graphic tools that alter color
  and details

18
Editing Images

• compositing images involves combining separate
  image layers into one image
• layers may be moved and arranged