Supervisors: James Elder and Vida Movahedi The ultimate goal of Computer Vision is to enable a machine to see and understand an image or scene, at least as well as a human. An important step towards this goal is to partition an image into regions, each corresponding to an object or entity. This is referred to as image segmentation in the computer vision community. Segmentation is an important step towards image understanding and can enhance the performance of many applications such as object detection, object tracking, surveillance, medical imaging, etc. Our framework for Salient Object Segmentation consists of four stages (see Figure): 1- Finding a set of line segments in the image that represent color or texture discontinuities (edges) 2- Representing the line segments in a sparse graph model 3- Extracting simple closed contours (cycles) in the above graph 4- Ranking the set of closed contours for output

The goal of the proposed project is to research and develop an automated method for ranking object hypotheses (stage 4 in the above framework). Given a set of closed contours found in an image, the problem under consideration is to rank these contours for output, based on how well they bound the salient object in the image. This ranking stage is important since it defines the final output of the object segmentation method. In particular, working with a senior graduate student or postdoctoral fellow, the successful applicant will: 1. Conduct a literature review of the state of the art ranking methods. These methods can include general ranking methods as well as those specifically designed to perform best for top ranked output such as those used for web searches (e.g. Google or Bing). 2. Develop and implement an efficient method for ranking closed contours. 3. Identify the quantity and distribution of data required for training above method, and prepare training data accordingly. 4. Compare ranking results with the currently available (and implemented) ranking method.

Other possible extensions to this project can include: 5. Study of ranking feature, and their inferential power 6. Study of the distribution of contour hypotheses and their power in representing whole objects or parts

Required skills: 1. Good programming skills 2. Good math skills 3. Knowledge of MATLAB programming language

For more information about the lab, visit www.elderlab.yorku.ca.

Supervisors: James Elder and Vida Movahedi What do you see in this image? The ultimate goal of Computer Vision is to enable a machine to see and understand an image or scene, at least as well as a human. An important step towards this goal is to partition an image into regions, each corresponding to an object or entity. This is referred to as image segmentation in the computer vision community. Segmentation is an important step towards image understanding and can enhance the performance of many applications such as object detection, object tracking, surveillance, medical imaging, etc. Our framework for Salient Object Segmentation consists of four stages (see Figure): 1- Finding a set of line segments in the image that represent color or texture discontinuities (edges) 2- Representing the line segments in a sparse graph model 3- Extracting simple closed contours (cycles) in the above graph 4- Ranking the set of closed contours for output

The goal of the proposed project is to research and develop a hierarchical method for extracting object hypotheses (stage 3 in the above framework). Given a set of open paths of arbitrary length in the graph, the problem under consideration is to group them to find plausible closed contours bounding the salient object in the image. This grouping stage is important, since i) the performance of the final product depends on the quality of the hypotheses formed in this stage, and ii) lowering the computational complexity of this stage results in significant speed up of the solution. In particular, working with a senior graduate student or postdoctoral fellow, the successful applicant will: 1. Run our current method for collecting open paths at different lengths. 2. Develop a method for finding intersections of paths at a certain length (or up to a certain length) with lower complexity than simple line intersection methods 3. Analyze the open paths for completeness- given paths of a certain length (or up to a certain length), what is the lowest achievable error of object contour hypotheses that can be formed by them? 4. Develop a method for combining short open paths for obtaining longer ones, or closed contours 5. Compare results with the currently available (and implemented) greedy method.

Required skills: 1. Good programming skills 2. Good math skills 3. Knowledge of MATLAB programming language

For more information about the lab, visit www.elderlab.yorku.ca.

Supervisor: Hui Jiang

Required Background: General EECS4080 prerequisites

Deep neural networks (DNNs) have achieved huge successes in many pattern classification tasks, including speech recognition and computer vision. In this project, the student will study DNN-based models for an interesting natural language processing (NLP) task, selecting from word embedding, language modelling, paraphrase detection or others. More specifically, the student will implement text pre-processing, neural model training and performance evaluation for the selected NLP task using some standard corpora.

Supervisor: Jarek Gryz

Required Background: EECS2031 and general EECS4080 prerequisites

We have a large project in data visualization projects and may have a couple of projects for 4080 this summer. Some of the projects will require knowledge of SQL and database application programming while some others may require a good deal of graphics design skills. If interested in learning more details about what a project in this area would involve, please contact Professor Gryz by emai. jarek at eecs.yorku.ca

Supervisor: Zhen Ming (Jack) Jiang (zmjiang at cse dot yorku dot ca)

Required Background: General CSE408x prerequisites; Good programming skills in Java; Good analytical and communication skills; Knowledge in AI and statistics; Interested in large scale software analysis

Short Description: Software engineering data (e.g., source code repositories and bug databases) contains a wealth of information about a project's status and history. The research on Mining Software Repositories (MSR) aims to transform the data from static record-keeping repositories into knowledge, which can guide the software development process. For example, one can derive correct API usage patterns and flag anomalous (and potentially buggy) API usages by mining the source code across many projects in GitHub and Google Code. In this project, the student(s) will research and develop an efficient infrastructure, where MSR researchers and practitioners can share and analyze such data.

Supervisor: Eric Ruppert

Required Background: EECS2031 and general EECS4080 prerequisites

Desirable Background: EECS3221

A traditional data structure is designed so that one operation can be performed on it at a time. This is no longer sufficient for the multicore architectures that have become prevalent in the past few years. A concurrent data structure is designed so that many threads can access it simultaneously. This requires some care in ensuring that concurrent operations do not interfere with one another.

The goal of this project is to implement concurrent data structures in C so that performance testing can be carried out on them. In particular, we would like to look at throughput and scalability of the data structures when large numbers of threads access them concurrently. Ultimately, we would also like to examine the possibility of designing special-purpose hardware to make concurrent data structures run faster.

Additional proposals for Summer 2015 will be added here by the first week of the summer term.

Meantime you may wish to look at Previously Proposed Projects for projects proposed in Winter 2015.