The Journal of Electronic Imaging (JEI), copublished with IS&T, publishes papers in all technology areas that make up the field of electronic imaging and are normally considered in the design, engineering, and applications of electronic imaging systems.

Contributed papers cover the following research areas that apply directly to electronic imaging or focus on applied electronic imaging technology:

• Adaptive image processing
• AI algorithms
• Color image processing
• Compressive sensing
• Computer vision
• Computational imaging
• Deep learning processing
• Digital and computational photography
• Electronic imaging applications
• Human-vision-based computational models
• Hypothesis-driven evaluation
• Image acquisition, display, and print
• Image and video compression
• Image and video data communication and storage
• Image and video processing and analysis
• Image and video quality estimation
• Image and video restoration
• Image classification and clustering
• Image segmentation
• Image visualization
• Light field and integral imaging
• Low level vision
• Machine learning
• Multimedia and imaging security
• Natural language processing
• Neural networks
• Noise reduction, denoising algorithms
• Nonlinear image processing
• Optical data processing
• Pattern analysis and recognition
• Perceptual and cognitive issues in imaging
• Phase retrieval
• Polarimetric imaging
• Spectral imaging
• Super resolution
• 3D sensing and visualization
• Virtual and augmented reality

Due to the large number of submissions received by JEI, the Senior and Associate Editors prescreen all manuscripts for required basic criteria. Paper that fail to meet these criteria will be rejected without review:

• Out of scope: In particular, papers that are about data processing, but not related to images or advances in imaging, will be rejected.
• Poor structure, methodology, and presentation: Examples include poor paper structure, low-quality figures, lack of comparisons with SotA, excessive self-citation, and unsound methodology.
• Poor validation: Examples include poor quality or obscure datasets and marginal comaprison of performance.