CHAPTER2 Flashcards
(22 cards)
………….are a type of image capture device that utilize an image sensor to register visible light as an electronic signal.
CCD (couple-charged device)
cameras
T/F These types of cameras do not use
photochemical film to capture stills
or video.
T
T/F Instead, the electronic signal is
recorded to either an internal
memory or a remotely connected
device.
T
Two types of quantization:
- There are finite number of pixels. (Spatial resolution)
- The amplitude of pixel is represented by a finite number of bits. (Gray-scale resolution)
…………….Found on very cheap cameras, this resolution is so low that the picture quality is almost always unacceptable. This is 65,000 total pixels
256x256
………….This is the low end on most “real” cameras. This resolution is ideal for e-mailing pictures or posting pictures on a Web site.
640x480
…………This is a “megapixel” image size – 1,109,000 total pixels – good for printing pictures.
1216x912
…………With almost 2 million total pixels, this is “high resolution.” You can print a 4x5 inch print taken at this resolution with the same quality that you would get from a photo lab.
1600x1200
…………Found on 4 megapixel cameras – the current standard – this allows even larger printed photos, with good quality for prints up to 16x20 inches.
2240x1680
……………..- A top-of-the-line digital camera with 11.1 megapixels takes pictures at this resolution. At this setting, you can create 13.5x9 inch prints with no loss of picture quality.
4064x2704
notes: 2d array of color
Some range–
[0,255]
0.0 - 1.0
what is Hue and Saturation and value ?
Hue: what color
Saturation: how much color
Value: how bright
T/F Hue, Saturation, Value Allows easy image transforms
-Shift the hue
-Increase saturation
T
Video Frame Representation
~24 frames per second.
N1 = VERTICAL POSITION
N2 = horizontal position
n3 = frame number
Advantages of Digital Image Processing
*To facilitate their storage and transmission
*To prepare them for display or printing
*To enhance or restore them
*To extract information from them
*To hide information in them
Digital Image Processing Examples
*Image Restoration
*Noise Removal
*Image Enhancement
*Image Compression
*Edge Detection
Segmentation
Watermarking
* Face Recognition
*Fingerprint Matching
*Face Tracking
*Object Tracking
Low-Level
Resizing
Image Adjustments
Grayscale
Exposure
Saturation
Hue
Edges
Oriented Gradients
Segmentation (color
Low-Level Vision
Photo manipulation- Size- Color- Exposure- X-Pro II
Feature extraction- Edges- Oriented gradients- Segments
Low level vision is exciting!!! #latergram #nofilter
Mid-Level
Panorama Stitching
Multi-View Stereo
Structured Light Scan
Range Finding
Optical Flow
Time Lapse
Mid-Level Vision
Image <-> Image
Panoramas
Image <-> World—-
Multi-view stereo
Structure from motion
Structured light
LIDAR
Image <-> Time
Optical flow–
Time lapse
High-Level
Classification
Tagging
Detection
Semantic Segmentation
Instance Segmentation
High-Level Vision
Semantics!
Image classification–
Object detection
Segmentation
Applications–
Retrieval
Robots?
and…????
