A technology that automatically quantifies and evaluates the quality of images.
Information and Communication Technology (Saitama University Research Seed Collection 2025-27 p.79)
Keywords: abnormal sound, normal sound, deep learning, signal processing, statistical signal processing, audio processing, image processing, communication systems, noise countermeasures, quality assessment
In our society, digital images are used in various places. There are many types, but now it has become possible to automatically evaluate the quality of each image simply by inputting the image itself. This is the technology called Image Quality Assessment (IQA). Until now, the quality of an image could not be evaluated without the original reference image, because the machine needed to know what the best image quality was. However, now machines can learn. When they demonstrate their learning ability, the quality of a degraded image can be quantified and output simply by inputting the degraded image. This numerical value is almost the same as the values evaluated by up to 1,000 people. Reference images are no longer necessary. This IQA technology can also be used to search for similar images. If processing speeds up, it could be implemented in various systems.
Inquire About This Product
basic information
Tetsuya Shimamura, Professor Graduate School of Science and Engineering, Department of Mathematical and Electronic Information, Information Area 【Recent Research Themes】 ● Signal processing techniques for efficient data transmission methods in wireless sensor networks ● Fast image restoration processes such as noise removal and edge enhancement ● Facial expression recognition using deep learning ● Voice enhancement, voice analysis, image understanding, and modulation estimation using deep learning ● Quality improvement of bone-conducted sound, signal analysis, etc.
Price range
Delivery Time
Applications/Examples of results
【Appeal Points to the Industry】 ● Conducted joint research with over 25 companies ● Well-regarded research content, with numerous awards for best papers ● Extensive track record in addressing various signal, noise issues, quality evaluation, and anomaly detection ● Multiple patent applications resulting from joint research outcomes 【Examples of Practical Use, Applications, and Utilization】 ● Development of a system to predict the time just before a motor fails by listening to its sound ● Technical development of an image completion method for cases where there are blank areas in images ● Development of a system to automatically evaluate image quality without reference images ● Development of technology to enhance voice in environments like intersections and train platforms without being affected by noise ● Development of adaptive modulation in MIMO systems and modulation estimation technology on the receiving side
catalog（1）
Download All Catalogs
Company information
The Saitama University Open Innovation Center is a center that functions as a liaison office for industry-academia-government collaboration. It consists of three departments: the Industry-Academia-Government Collaboration Department, the Intellectual Property Department, and the Startup Support Department, each staffed with coordinators well-versed in various fields. The center's activities include solving technical challenges in companies, supporting the implementation of joint research, and conducting technology transfer aimed at introducing and utilizing Saitama University's intellectual property.