Jerry Gao, Professor
San Jose State University, USA
Computer Engineering Department and Applied Data Science Department, San Jose State University
Director of Research Center of Smart Technology and Systems
Co-Funder and CTO of ALPS-Touchtone, Inc.
Dr. Jerry Gao is a professor at San Jose State University for Computer Engineering Department and Applied Data Science Department. Now, his research interest includes Smart Machine Cloud Computing and AI, Smart Cities, Green Energy Cloud and AI Services, and AI Test Automation, Big Data Cyber Systems and Intelligence. He has published three technical books, one of the books is the first book on object-oriented software testing (1998), and his second book is titled as Testing and Quality Assurance for Component-based Software, which is the first book on component-based software systems. hundreds (320) publications in IEEE/ACM journals, magazines, international conferences. His research work has received over 88K+ citations (in Google Scholar), and reached to over 330K+ readings on ResearchGate. Since 2020, Dr. Gao has served as the chair of the steering committee board for IEEE International Congress on Intelligent Service-Oriented Systems Engineering (IEEECISOSE), and Steering Committee Board for IEEE Smart World Congress. He had over 25 years of academic research and teaching experience and over 10 years of industry working and management experience on software engineering and IT development applications.
Background:
According to the recent market analysis by Global Market Insight (GMI), the global automation testing market size will be anticipated to cross USD 80 billion in 2032. With the fast advances in machine learning models and AI technologies, more and more intelligent systems and applications, including smart computer vision systems, are being developed for real deployment and applications.
Before the deployment of these intelligent systems, it is important and critical for intelligent system testers, quality assurance engineers, and young generations to understand the issues, challenges, and needs as well as state-of-the-art AI testing tools and solutions in testing and quality assurance for modern intelligent systems and smart mobile apps, and smart machines (smart Robots, driverless AVs, and intelligent UAVs). With the big heat of ChatGTP in the business market, many people have started to pay attention to the quality of AI applications systems and deployment.
Why quality AI testing and automation of Computer Vision is import?
Today, many intelligent computer vision systems have been trained based on computer vision big data and developed using data-driven computer vision models. There are two types of computer vision data: a) object-oriented computer vision photos and b) document-based images. Testing engineers and quality assurance people have encountered many challenges in testing and automation of computer vision systems and applications: intelligent features and AI-powered functions bring new issues and challenges to testing intelligent computer vision applications and quality assurance due to the following reasons:
How to establish test requirements, validation models, and quality assurance standards for computer vision systems/applications?
- Lack of well-defined quality testing and analysis models and quality requirement specification approaches.
- Lack of well-defined quality assurance standards for computer vision system analysis and modeling methods
Where are the cost-effective quality validation methods for computer vision systems/applications?
- Current software validation methods are not good enough to support computer vision systems because these methods are not designed to address the demands and needs of computer vision systems.
- There is a lack of well-defined quality validation methods for computer vision systems.
High costs to define and generate adequate test sets for computer vision
- Lack of well-defined test models and methods to help testers and QA engineers to define and select adequate test sets because most AI-powered system functions (or components) are trained based on big data using diverse machine learning.
- Most existing software system test methods were developed for conventional software without considering special features and needs in intelligent systems.
How to validate large-scale test results in automatic ways?
- AI-based functions may bring uncertainty in system results.
- The highly diversity of test results and system outputs bring the new challenges and needs in test automation.
Hard to find systematic test tools supporting rich-media input/outputs
- AI-powered intelligent systems usually accept multiple-mode inputs in text, image, audio, and video.
- Current software testing tools and solutions do not support rich media input data, and rich media output data validation.
Who should attend this tutorial?
Test engineers, quality assurance engineers, and managers who are responsible for quality testing and assurance for modern intelligent systems and AI-powered smart computer vision systems, including mobile and online applications built-in based on modern computer vision models and techniques. In addition, researchers and students are encouraged if they are interested in AI system testing, automation, and quality assurance.
What you learned from this tutorial? What is the coverage of this tutorial?
Table of contents (outline):
- Introduction on computer vision and applications
o Test automation market for computer vision and intelligent applications
o An overview of computer vision and applications
o A classification of diverse computer vision and applications - What to test for computer vision and applications?
o Major test focuses and intelligence validation
o Major challenges, issues, and needs in computer vision validation
Adequate quality needs - Quality testing process and validation methods
o Computer vision quality process
o Different computer vision approaches
o Model-based quality testing methods for computer vision - AI test modeling for intelligent computer vision systems
o Intelligence-oriented test modeling and analysis for computer vision
o Intelligence-oriented multiple dimension test models
o Intelligence-oriented multiple dimension decision test tables - Test generation and AI-based test data generation for computer vision applications
o AI-based test case generation for computer vision images
o AI-based test data generation and augmentation for computer vision images
o AI-based test generation for document-based computer vision intelligence
o AI-based test augmentation for document-based computer vision intelligence - Test result validation for intelligent computer vision systems
- Quality computer vision system validation for QoS system parameters
- Test automation for intelligent computer vision and applications
- Quality evaluation metrics and test coverage for computer vision
In addition, Dr. Gao will provide two show-cases and project demos on sample computer vision test automation.