Computer Vision
and
Image Processing
By Martha M.
Contents
What is a computer vision?
What is image?
Related fields in CV
Computer Vision Vs. image processing
Application of CV and IP
Different Image processing examples
Fundamental steps in image processing
1.1 What is Computer Vision?
Computer Vision (CV) is a field of artificial intelligence (AI) that
enables machines and systems to interpret, understand, and analyze
visual data from the world, such as images and videos, in a way similar
to human vision.
Continue…
The goal of Computer Vision is to replicate or enhance human vision
capabilities through computational algorithms, enabling tasks such as
object detection, image recognition, motion tracking, and scene
understanding.
1.2 What is an Image?
• An image is a two-dimensional array of pixel values that represent
visual information.
• Pixel is the smallest element of an image. Each pixel correspond to
any one value. The value of the pixel between 0 and 255.
• It can be captured using various devices such as cameras, sensors, or
scanners.
• Types of Images:
• Grayscale Images: Each pixel contains a single value representing intensity
(brightness).
• Color Images: Each pixel is composed of multiple values, usually
corresponding to the Red, Green, and Blue (RGB) color channels.
• Binary Images: An image with only two colors, typically black and white.
1.3 Computer Vision vs. Image Processing
• Image Processing:
• Focuses on improving the quality of an image or extracting useful information from it.
• Techniques include filtering, edge detection, image enhancement, and noise reduction.
• Works at the pixel level, manipulating raw data for visual improvement or feature extraction.
• Computer Vision:
• Goes a step further by interpreting and understanding the content of images, not just processing
them.
• It involves recognizing objects, understanding scenes, and making high-level decisions based on
image data.
• Works with features, patterns, and objects rather than pixels.
Key Differences between them
• Image Processing: More about improving images and
transforming them into a usable format.
• Computer Vision: Focuses on interpreting what is in
the image (e.g., detecting objects, faces, and
understanding scenes).
Image processing
Computer vision
1.4 Different Image Processing:
• Image Enhancement: Improving the visual appearance of an image (e.g., contrast adjustment,
sharpness enhancement).
Continue….
Edge Detection:
• Identifying boundaries within an image (e.g., using the Sobel operator
or Canny edge detector).
Segmentation:
• Dividing an image into distinct regions for easier analysis (e.g.,
separating foreground from background).
Continue…
• Noise Reduction: Removing unwanted artifacts from images, like
graininess or distortion.
• Image Compression: Reducing the size of an image file while
maintaining its quality (e.g., JPEG compression).
1.5 Fundamental Steps in Image Processing
• Image Acquisition: The first step is to obtain an image through a
camera, sensor, or scanner.
• Preprocessing: Preparing the image for analysis by removing noise,
correcting brightness, and resizing the image.
• Image Segmentation: Dividing the image into meaningful parts or
objects (e.g., separating the sky from the ground in a landscape image).
Continue…
• Feature Extraction: Identifying and extracting key characteristics or patterns
within the image (e.g., edges, textures, or corners).
• Image Recognition: Identifying objects, people, or patterns within the image
(e.g., classifying whether an image contains a cat or dog).
• Postprocessing: Final adjustments to improve the output of the processed
image, such as applying filters or performing transformations.
• Interpretation/Decision Making: The final step involves interpreting the
processed image to make decisions or take action based on the findings.
1.6 Applications of Computer Vision and Image Processing
• Healthcare:
• Medical image analysis (e.g., X-rays, MRIs) for diagnosis and treatment
planning.
• Automated image-based screening for diseases like cancer.
• Autonomous Vehicles:
• Object detection, road sign recognition, and lane tracking.
• Real-time interpretation of the environment for safe navigation.
• Retail:
• Automated checkout systems, object detection, and inventory management.
• Customer behavior analysis using camera feeds.
Continue…
• Security and Surveillance:
• Face recognition and motion detection for monitoring public and private spaces.
• Agriculture:
• Crop monitoring, pest detection, and precision farming using aerial or satellite images.
• Industrial Automation:
• Quality control and defect detection in manufacturing processes.
• Robot vision systems for object manipulation
