Readings 18 to 25 - Project Readings

Overview

We have now completed the assigned readings portion of the course.  At this point, you should turn your attention to your final project and focus on finding reading materials to strengthen your work and project report.  To further this goal, all future reading assignments are self-directed.

Project Readings

You should select 8 papers related to your project and blog about them.  You may reuse some of the papers you explored in Assignment 6.  If your project plan has changed or your find more relevant works to include, you are encouraged to select those as well.

If you are on a team, it will be beneficial to find different papers than your teammates.  This is because your final report requires a minimum number of citations based on your team size and having the readings done for the blog assignment will simplify this task so long as each person has read their own papers.

Due Dates

The standard reading schedule is not impacted by the shift to project readings.  You will continue to post summaries to your blogs by Sundays; the only difference is that the readings are no longer pre-selected and you must choose your own.  The 8 project readings correspond directly to the typical M/W/F schedule we have been following for assigned readings.  The timeline is as follows:

11/11, 11/14, 11/16 (Readings 18, 19, and 20) due 11/20

11/18, 11/21, 11/23 (Readings 21, 22, and 23) due 11/27

11/28, 11/30 (Readings 24 and 25) due 12/04

Reading 17 - ChemInk

Paper
Ouyang, Tom Y., and Randall Davis. "ChemInk: a natural real-time recognition system for chemical drawings." Proceedings of the 16th international conference on Intelligent user interfaces. ACM, 2011.

Notes
Now that all of the homework assignments are complete, we are shifting the class focus towards the final project.  In line with that plan, we have several system-oriented papers which will be useful preparation for your own project development and final report.  In this work, Ouyang and Davis describe an interface for recognizing chemical diagrams.

Reading 16 - No Rubine?

Paper
Paulson, Brandon, et al. "What!?! no Rubine features?: using geometric-based features to produce normalized confidence values for sketch recognition." HCC Workshop: Sketch Tools for Diagramming. 2008.

Notes
This is another recognition paper which discusses a system based on a hybrid approach to achieve its recognition rates.

Reading 15 - Tahuti

Paper
Hammond, Tracy, and Randall Davis. "Tahuti: A geometrical sketch recognition system for uml class diagrams." ACM SIGGRAPH 2006 Courses. ACM, 2006.

Notes
Tahuti is a system for recognizing UML diagrams and automatically generating code.  It includes some very simple and intuitive geometric recognition methods, including an algorithm for arrow recognition.

Reading 14 - LADDER

Paper
Hammond, Tracy, and Randall Davis. "LADDER, a sketching language for user interface developers." Computers & Graphics 29.4 (2005): 518-532.

Notes
LADDER is a sketch language for defining geometric-based relationships that allow recognition of shapes from any domain.

Reading 13 - Paleosketch

Paper
Paulson, Brandon, and Tracy Hammond. "Paleosketch: accurate primitive sketch recognition and beautification." Proceedings of the 13th international conference on Intelligent user interfaces. ACM, 2008.

Notes
Paleosketch is a good primitive recognition engine which supports many different types of shapes.  Not only does this paper include a number of useful shape test algorithms, it also introduces two new features common in sketch recognition today -- the Normalized Distance between Direction Extremes (NDDE) and the Direction Change Ratio (DCR).

Reading 12 - Electronic Cocktail Napkin

Paper
Gross, Mark D. "Recognizing and interpreting diagrams in design." Proceedings of the workshop on Advanced visual interfaces. ACM, 1994.

Notes
This is another simple recognition method which relies on template codes against which to match.

Reading 11 - $1 Recognizer

Paper
Wobbrock, Jacob O., Andrew D. Wilson, and Yang Li. "Gestures without libraries, toolkits or training: a $1 recognizer for user interface prototypes." Proceedings of the 20th annual ACM symposium on User interface software and technology. ACM, 2007.

Notes
We have now finished the corner finding portion of readings and will be moving on to recognition in preparation for the next homework.  The recognition portion begins with the most simple recognition algorithm, which is often used as a baseline for error evaluation.  This is the $1 algorithm -- template matching.  In this paper, the authors present a method for finding the optimal matching shape/template using the distance between the drawn shape and the template.  There are many variants of $1, e.g. $N, $P, $3, etc., but all of them are based on the same idea of resampling into a cloud of points and finding the distances between drawn shapes and templates.  Dealing with rotation differs slightly between methods, such as using polar coordinates to handle minimizing rotation, but overall, the idea is the same.  Following this introduction into recognition, we'll start exploring more specific methods.

Reading 10 - Yu Corners

Paper
Yu, Bo, and Shijie Cai. "A domain-independent system for sketch recognition." Proceedings of the 1st international conference on Computer graphics and interactive techniques in Australasia and South East Asia. ACM, 2003.

Notes
Continuing on our readings in corner finding before we progress on to primitive recognition and other methods.

Reading 9 - Combining Corners

Paper
Wolin, Aaron, Martin Field, and Tracy Hammond. "Combining corners from multiple segmenters." Proceedings of the Eighth Eurographics Symposium on Sketch-Based Interfaces and Modeling. ACM, 2011.

Notes
Another paper in corner finding, we look at a method of combining multiple different techniques into a better, more flexible segmenter.

Reading 8 - ShortStraw

Paper
Wolin, A., Eoff, B., & Hammond, T. (2008, June). ShortStraw: A Simple and Effective Corner Finder for Polylines. In SBM (pp. 33-40).

Notes
Continuing on corner finding, we will now look at a very simple segmentation algorithm -- ShortStraw

Reading 7 - Sezgin and Stahovich

Paper
Sezgin, Tevfik Metin, Thomas Stahovich, and Randall Davis. "Sketch based interfaces: early processing for sketch understanding." ACM SIGGRAPH 2006 Courses. ACM, 2006.

Notes
Up to this point, we've been concerned with understanding and building features of strokes and using these features to describe and classify gestures.  With that background on machine learning and the familiarity gained with working on sketch data, we are now moving into more sketch-specific problems.  To begin with, we will look at corner detection for a few readings.  One of the more important original works in corner detection also helps to communicate the intuition behind the features that are often used, so we will be starting with the Sezgin/Stahovich paper shared in the class drive.

Reading 6 - Geometry Overview

Paper
Hammond, T. "Fundamentals of Geometry". Draft

Notes
In the shared folder for Readings, you can access the draft version of Dr. Hammond's paper on basic geometry.  This paper provides some background information on dealing with geometries, vector spaces, and matrices.  Not only is the knowledge applicable to a number of classification methods, such as our current linear classification discussion, but it is also a good review of trigonometry and functions that we often deal with in feature extraction.  As we move on to other methods of recognition, this intuition will be useful.

Reading 5 - Metrics Overview

Paper
Hammond, T. "Evalutation Methods and Metrics". Draft

Notes
In the shared folder for Readings, you can access the draft version of Dr. Hammond's paper on evaluation metrics.  This paper is a general overview of some common methods used in evaluation and accuracy reporting for machine learning problems.  In this class, we'll be dealing with features and classifiers in lectures, homeworks, and more, so having a good understanding of the basics of evaluation will be very helpful.

Reading 4 - Gesture Overview

Paper
Hammond, T. "Introduction to Gesture Recognition". Draft

Notes
In the shared folder for Readings, you can access the draft version of Dr. Hammond's paper on gesture recognition.  It is an overview of all the previous gesture work we've discussed and provides many practical explanations and examples to help cement these concepts before we move on into classification techniques and other types of recognizers.

Reading 3 - Long

Paper
Long Jr, A. Chris, et al. "Visual similarity of pen gestures." Proceedings of the SIGCHI conference on Human Factors in Computing Systems. ACM, 2000.

Notes
Long's analysis of gesture features builds further on Rubine's original work in the field.  The most important section of this paper is the discussion and results of the set of experiments measuring the most useful features of gesture similarity.  As a small reminder, while the Monday and Wednesday readings should have summary blog posts completed by this weekend, this reading and other Friday readings are not due until the next weekend.  The Reading Policy post has more details.

Reading 2 - Rubine

Paper
Rubine, Dean. Specifying gestures by example. Vol. 25. No. 4. ACM, 1991.

Notes
Here we begin to study the origins of modern sketch recognition from an algorithmic perspective.  The most important section to review from this work is part 4, which covers Rubine's features.  Rubine's features partially form the basis of many gesture-based recognizers today.  At the very least, familiarity with these sorts of feature constructs will help you gain an intuition for the type of information we can capture and use about a sketch.

Reading 1 - Dialectical Creativity

Paper
Hammond, Tracy. "Dialectical Creativity: Sketch-Negate-Create." Studying Visual and Spatial Reasoning for Design Creativity. Springer Netherlands, 2015. 91-108.

Notes
This is a good introductory reading in the field of general sketch recognition.  It should help motivate upcoming content in the course and encourage project ideas.

You may access the paper from the Google drive folder "CSCE624 Class Files" available to all students in the class.  If you did not receive access, let me know so you may be added to the class group.