440 likes | 589 Views
Vision in Humans and Machines. Visible light is just a part of the electromagnetic spectrum. 2. Cross Section of the Human Eye. 3. Anatomy of the Visual System The Eyes Cornea: Transparent outer covering of the eye that admits light Pupil:
E N D
Vision in Humans and Machines Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Visible light is just a part of the electromagnetic spectrum Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines 2
Cross Section of the Human Eye Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines 3
Anatomy of the Visual System • The Eyes • Cornea: • Transparent outer covering of the eye that admits light • Pupil: • Adjustable opening in the iris that regulates the amount of light that enters the eye • Iris: • Pigmented ring of muscles situated behind the cornea Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines 4
Anatomy of the Visual System • Photoreceptors • Retina: • The neural tissue and photoreceptive cells located on the inner surface of the posterior portion of the eye. • Rod: • Photoreceptor cells of the retina, sensitive to light of low intensity. • Cone: • Photoreceptor cells of the retina; maximally sensitive to one of three different wavelengths of light and hence encodes color vision.
Anatomy of the Visual System • The Eyes • Lens: Consists of a series of transparent, onion-like layers. Its shape can be changed by contraction of ciliary muscles. • Accommodation: • Changes in the thickness of the lens, accomplished by the ciliary muscles, that focus images of near or distant objects on the retina
Anatomy of the Visual System • The Eyes • Fovea: • Area of retina that mediates the most acute vision. Contains only color-sensitive cones. • Optic Disk: • Location on retina where fibers of ganglion cells exit the eye. Responsible for the blind spot.
Coding of Visual Information in the Retina • Coding of Light and Dark • Receptive field: • That portion of the visual field in which the presentation of visual stimuli will produce an alteration in the firing rate of a particular neuron.
Photoreceptor Bipolar Ganglion
Coding of Visual Information in the Retina • Photoreceptors: Trichromatic Coding • Peak wavelength sensitivities of the three cones:Blue cone: Short- Blue-violet (420 nm) Green cone: Medium- Green (530 nm)Red Cone: Long- Yellow-green (560nm)
Coding of Visual Information in the Retina • Retinal Ganglion Cells: • Opponent-Process Coding • Negative afterimage: • The image seen after a portion of the retina is exposed to an intense visual stimulus; consists of colors complimentary to those of the physical stimulus. • Complimentary colors: • Colors that make white or gray when mixed together.
Analysis of Visual Information • Anatomy of the Striate cortex • David Hubel and Torsten Wiesel • 1960’s at Harvard University • Discovered that neurons in the visual cortex did not simply respond to light; they selectively responded to specific features of the visual world.
Cat V1 (striate cortex) Orientation preference map Ocular dominance map
“Data Flow Diagram” of Visual Areas in Macaque Brain Blue:motion perception pathway Green:object recognition pathway Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Computer Vision • A typical computer vision applications are complex and consist of different levels of processing, from the low-level pixel-by-pixel analysis to the high-level creation of scene descriptions. • Generally, computer vision systems consist of an image processing stage, followed by a scene analysis stage. • The following slide outlines the structure of a computer vision system. Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Image processing Sceneanalysis Bitmap image feedback (tuning) Prepare image for scene analysis Build an iconic model of the world Computer Vision • A simple two-stage model of computer vision: Scene description Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Computer Vision • The image processing stage prepares the input image for the subsequent scene analysis. • Usually, image processing results in one or more new images that contain specific information on relevant features of the input image. • The information in the output images is arranged in the same way as in the input image. For example, in the upper left corner in the output images we find information about the upper left corner in the input image. Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Computer Vision • The scene analysis stage interprets the results from the image processing stage. • Its output completely depends on the problem that the computer vision system is supposed to solve. • For example, it could be the number of bacteria in a microscopic image, or the identity of a person whose retinal scan was input to the system. Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
y’ [0, 0] [0, 1] [0, 2] [0, 3] [1, 0] [1, 1] [1, 2] [1, 3] [2, 0] [2, 1] [2, 2] [2, 3] x’ Digitizing Visual Scenes • With regard to spatial resolution, we will map the intensity in our image onto a two-dimensional finite array: Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Thresholding • Here, the right image is created from the left image by thresholding, assuming that object pixels are darker than background pixels. • As you can see, the result is slightly imperfect (dark background pixels). Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Geometric Properties Computer Vision Lecture 1: Digital Images/Binary Image Processing
Geometric Properties • We could teach our program what the objects look like at different sizes and orientations, and let the program search all possible positions in the input. • However, that would be a very inefficient and inflexible approach. • Instead, it is much simpler and more efficient to standardize the input before performing object recognition. • We can scale the input object to a given size, center it in the image, and rotate it towards a specific orientation. Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Noise Reduction • Here, a size filter perfectly removes all noise in the input image. Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Noise Reduction • However, if our threshold is too high, “accidents” may happen. Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Edge Detection Calculating the magnitude of the brightness gradient with a Sobel filter. Left: original image; right: filtered image. Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Texture Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Texture • Texture is an important cue for biological vision systems to estimate the boundaries of objects. • Also, texture gradient is used to estimate the orientation of surfaces. • For example, on a perfect lawn the grass texture is the same everywhere. • However, the further away we look, the finer this texture becomes – this change is called texture gradient. • For the same reasons, texture is also a useful feature for computer vision systems. Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Texture Gradient Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Texture • The most fundamental question is: How can we “measure” texture, i.e., how can we quantitatively distinguish between different textures? • Of course it is not enough to look at the intensity of individual pixels. • Since the repetitive local arrangement of intensity determines the texture, we have to analyze neighborhoods of pixels to measure texture properties. Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Stereo Vision • Geometry of binocular stereo vision Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Statistical Pattern Recognition Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
Object Recognition • This algorithm learns to recognize 25 different chairs: It is shown each chair from 25 different viewing angles. Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines
The Algorithm Introduction to Cognitive Science Lecture 2: Vision in Humans and Machines