Welcome to CS 675 – Computer Vision Spring 2018 Instructor: Marc Pomplun January 23, 2018 Computer Vision Lecture 1: Human Vision

Instructor – Marc Pomplun Office: S-3-171 Lab: S-3-135 Office Hours: Tuesdays 4:30-5:30, 7:00-8:00 Thursdays 4:30-5:30 Phone: 287-6443 (office) E-Mail: marc@cs.umb.edu Website: http://www.cs.umb.edu/~marc/cs675/ January 23, 2018 Computer Vision Lecture 1: Human Vision

The Visual Attention Lab Cognitive Science, esp. eye movements January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision A poor guinea pig: January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision January 23, 2018 Computer Vision Lecture 1: Human Vision

Modeling of Brain Functions January 23, 2018 Computer Vision Lecture 1: Human Vision

Modeling of Brain Functions unit and connection l a y e r l + 1 in the interpretive network unit and connection in the gating network unit and connection in the top-down bias network l a y e r l l a y e r l - 1 January 23, 2018 Computer Vision Lecture 1: Human Vision

Example: Distribution of Visual Attention January 23, 2018 Computer Vision Lecture 1: Human Vision

Selectivity in Complex Scenes January 23, 2018 Computer Vision Lecture 1: Human Vision

Selectivity in Complex Scenes January 23, 2018 Computer Vision Lecture 1: Human Vision

Selectivity in Complex Scenes January 23, 2018 Computer Vision Lecture 1: Human Vision

Selectivity in Complex Scenes January 23, 2018 Computer Vision Lecture 1: Human Vision

Selectivity in Complex Scenes January 23, 2018 Computer Vision Lecture 1: Human Vision

Selectivity in Complex Scenes January 23, 2018 Computer Vision Lecture 1: Human Vision

Human-Computer Interfaces: January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision Your Evaluation 6 sets of exercises (individual work) paper-and-pencil questions: 10% programming tasks: 30% midterm (75 minutes) 25% final exam (2.5 hours) 35% January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision Grading For the assignments, exams and your course grade, the following scheme will be used to convert percentages into letter grades:  95%: A  90%: A-  86%: B+  82%: B  78%: B-  74%: C+  70%: C  66%: C-  62%: D+  56%: D  50%: D-  50%: F January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision Academic Dishonesty You are allowed to discuss problems regarding your homework with other students in the class. However, you have to do the actual work (computing values, writing algorithms, drawing graphs, etc.) by yourself. You cannot copy anything from other sources (Wikipedia, other students’ work, etc.) The first violation will result in zero points for the entire homework or exam (and official notification). The second violation will result in failing the course. January 23, 2018 Computer Vision Lecture 1: Human Vision

Complaints about Grading If you think that the grading of your homework was unfair, please talk to the TA, Shaohua Jia. If you are still unhappy afterwards, please talk to me. If you think that the grading of your midterm exam was unfair, please indicate your concerns by putting sticky notes or attaching an extra sheet and give it to me or put it into my mailbox. January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision Computer Vision is the science of building systems that can extract certain task-relevant information from a visual scene. Such systems can be used for applications such as optical character recognition, analysis of satellite and microscopic images, magnetic resonance imaging, surveillance, identity verification, quality control in manufacturing etc. January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision In a way, Computer Vision can be considered the inversion of Computer Graphics. A computer graphics systems receives as its input the formal description of a visual scene, and its output is a visualization of that scene. A computer vision system receives as its input a visual scene, and its output is a formal description of that scene with regard to the system’s task. Unfortunately, while a computer graphics task only allows one solution, computer vision tasks are often ambiguous, and it is unclear what the correct output should be. January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision Digital Images Binary Image Processing Color Image Filtering Basic Image Transformation Edge Detection Image Segmentation Shape Representation Texture Object Recognition Image Understanding Depth Motion January 23, 2018 Computer Vision Lecture 1: Human Vision

Visible light is just a part of the electromagnetic spectrum January 23, 2018 Computer Vision Lecture 1: Human Vision

Cross Section of the Human Eye January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision Photoreceptor Bipolar Ganglion January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision Major Cell Types of the Retina January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision Receptive Fields January 23, 2018 Computer Vision Lecture 1: Human Vision

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) January 23, 2018 Computer Vision Lecture 1: Human Vision

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. January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision January 23, 2018 Computer Vision Lecture 1: Human Vision

Computer Vision Lecture 1: Human Vision January 23, 2018 Computer Vision Lecture 1: Human Vision