DOC PREVIEW
GT PSYC 3041 - VISUAL FORM AND PATTERN RECOGNITION

This preview shows page 1 out of 4 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 4 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 4 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

Psychology 3041/6014 Spring, 2014 1 of 4 VISUAL FORM AND PATTERN RECOGNITION • We have focused on the detection of features (points of light, edges, lines, colors) • Now consider some slightly more sophisticated shapes • What aspects of the visual system allow us to extract shapes? • The key to recognizing objects is to see the foreground from the background, and a big clue is contrast differences 1. Contours via contrast a) Areas of center-surround fields i. Enhance contrast b) Lateral inhibition i. Fields beside one another inhibit each other ii. Sharpens the differences between them (increases contrast) iii. Mach bands 1. Example of edges being sharpened iv. Hermann grid 1. 2D set of edges 2. competition of large peripheral black fields and smaller, central white fields v. Lightness contrast 1. inhibition across an area causes a region’s lightness to be perceived as differentPsychology 3041/6014 Spring, 2014 2 of 4 2. Stimulus change a) Movement of the image is important for edge detection 3. Spatial frequency a) Visual system has spatial frequency detectors b) Fourier analysis occurs on visual scene c) Contrast sensitivity function i. Our ability to detect a given spatial frequency depends on contrast between backgrounds and foreground ii. Optimal spatial frequency 1. Higher or lower sp. freq. requires more contrast 2. Implications? 4. Perceptual processing a) Bottom-up vs./and top-down processes b) Attention i. Focus processing detail in an “area” ii. Can be disk-shaped (a region) or even ring-shaped iii. Allows detailed extraction of features in a smaller region iv. Attention both selects and suppresses environmental stimulationPsychology 3041/6014 Spring, 2014 3 of 4 c) Feature Integration Theory (FIT) i. Describes processing of light (visual stimuli) into information ii. Preattentive stage (before attending) 1. Bottom-up, automatic 2. Extracts perceptual primitives 3. Parallel processing of all elements of a display 4. Leads to detection of textures, shapes, and objects • Textons a) Specific 2D characteristics of a texture • Geons a) 2D or 3D primitives that combine to make up object shapes b) combination of geons leads to recognition/distinction of objects c) more geons leads to… iii. Focused attention stage 1. Not instantaneous 2. Requires effort and conscious scrutiny 3. Often requires serial search to examine all elements of a display 4. Allows you to group (and separate) the immediate results of the preattentive stage 5. Use expectancies and knowledge to put the primitives togetherPsychology 3041/6014 Spring, 2014 4 of 4 5. Processing “Philosophies” a) Computation (e.g., Marr) i. Serial process ii. Data driven computation iii. Primal sketch iv. 2.5D sketch v. 3D model representation vi. stages seen as “computer routines” vii. active problem solving routine at each stage b) Connectionist model i. aka parallel distributed processing (PDP) or neural networks ii. large but finite set of neurons (“nodes”) in a network iii. accept inputs and “settle” into a pattern of activation iv. biologically plausible v.


View Full Document

GT PSYC 3041 - VISUAL FORM AND PATTERN RECOGNITION

Download VISUAL FORM AND PATTERN RECOGNITION
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view VISUAL FORM AND PATTERN RECOGNITION and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view VISUAL FORM AND PATTERN RECOGNITION 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?