Ch. 5 pt. 1&2

• Computer Vision: Object recognition; detection of objects in an image and then matching those objects to existing, stored representations of what those objects are to create a scene.
• Other computer systems: Learn how to recognize objects and determine not a description of a scene, but rather, the precise locations of objects in that scene.
• Autonomous vehicles: Require fast and precise identification of objects in order to smoothly navigate the environment.
• Cellphones: Rely on object recognition to recognize faces across different angles and lighting conditions to unlock your device.
• Computers becoming more accurate: In some situations, their object detection performance sometimes matches or exceeds that of humans.
• However, they often fall short in identifying objects under degraded conditions.
• The stimulus on the receptors is ambiguous: An image on the retina can be caused by an infinite number of objects.
• Objects can be hidden or blurred: Occlusions are common in the environment.
• Objects look different from different viewpoints
• Perceptual Organization Approach established by Wundt (late 1800s): States that perceptions are created by combining elements called sensations.
• The whole differs from the sum of its parts: Perception is not built up from sensations but is a result of perceptual organization.
• Structuralism: Distinguished between sensations and perceptions.
• Apparent Movement: Illusion of movement.
• Illusory Contours: Appear real but have physical edge.
• Good continuation: Connected points resulting in straight or smooth curves belong together.
• Pragnanz: a gestalt principle of perceptual organization that states that every stimulus pattern is seen in such a way that is as simple as possible

  • aka principle of good figure or simplicity
• Similarity: Similar things are grouped together.
• Figure-ground segregation: Determining what part of the environment is the figure, so that it “stands out” from the background.
• Proximity: Things that are grouped together belong together.
• Common Fate: Things moving in the same direction are grouped together.
• Common Region: Elements in the same region of space appear to be grouped together.
• Uniform Connectedness: A connected region of the same visual properties, such as lightness, color, texture, or motion, is perceived as a single unit.
• Perceptual Segregation: Figure-ground segregation, determining what part of the environment is the figure, so that it “stands out” from the background.
• Common Fate: Things that move together belong together.
• Common Region: Elements that are within the same region of space appear to be grouped together.
• Rapid Scene Recognition: Humans can understand the gist of a scene within milliseconds, a capability demonstrated by experiments showing that observers can identify a scene or an action

  • This skill is crucial for survival, allowing for quick responses to environmental cues
  • E.g.; "girl clapping" from a rapid sequence of images
• Masking Stimuli: Used in experiments to study visual perception and sensory memory

  • By presenting a masking stimulus immediately after the main visual stimulus, researchers can investigate the persistence of visual information and its influence on scene recognition
• Sensory Memory and Image Persistence: The phenomenon where an image continues to appear in one's vision after the stimulus is removed, highlighting the brain's ability to retain visual information briefly
• Mary Potter's Experiment (1976): Demonstrated rapid scene recognition by asking participants to identify a target picture from a sequence of images presented briefly

  • This study supports the notion that humans can process and recognize scenes quickly and efficiently
• Priming with Verbal Descriptions: Enhances the ability to detect specific scenes in a rapid sequence of images, indicating that expectations can influence visual perception
• Evolutionary Importance of Scene Recognition: Quick recognition of scenes is vital for survival, allowing for rapid assessment of environmental situations
• Visual Perception Experiments by LIFE FAE (2004): Investigated the minimum exposure time required for scene recognition

  • Revealing that even brief glimpses (as short as 27 milliseconds) can convey some information about a scene, with longer exposures improving recognition accuracy
• Global Image Features for Scene Analysis: Studies by Oliva and Torralba identified key visual features (e.g., naturalness, openness, roughness, expansion, color) that the brain uses to quickly identify scenes, demonstrating how certain characteristics can cue the brain into recognizing specific types of scenes (e.g., natural vs. urban)
• The Role of Experience (Priors): Our past experiences shape our ability to recognize and interpret scenes, influencing our expectations and perceptions
• Scene Schema and Unconscious Inference: The brain uses schemas and unconscious inferences based on past experiences to interpret scenes

  • highlighting the complex interplay between sensory input and cognitive processes in visual perception
• Perceptual Organization (approach established by Wundt): states that perceptions are created by combinging elements called sensations
• Structuralism: distinguished between sensations and perceptions
• Apparent Movement: illusion of movement
• Illusory Contours: appear real but have physical edge
• Good Continuation: connected points resulting in straight or smooth curves belong together

  • lines are seen as following the smoothest path