Given the exponentially increasing amount of data from cameras, webcams, or other optical or radar sensors, etc., a substantial number of images or videos of different nature can be used for different applications. For instance, the problem of high-performance target recognition, anomaly detection, etc. plays an important role in both military and civil fields. In the military field, image processing can be used for intelligence interpretation and battlefield surveillance. In the civil field, image or video processing can be used for face recognition, driver assistance systems, geological survey, etc.

However, it is still challenging to achieve high performance in image classification, target detection & recognition, video tracking, etc. because of the complex scenarios of the real world (e.g., noise, occlusion, deformation, etc.). Recently, the advances in the machine learning computer vision domain have shown their potential in practical applications. Deep neural network methodologies are commonly used in image and video processing, including segmentation, classification, recognition, etc.

The aim of this Special Issue is to highlight research discussing advanced machine learning approaches in image and video processing. The Issue will provide novel guidance for machine learning researchers and broaden the perspectives of machine learning and computer vision researchers. Original research and review articles are welcome.

Potential topics include but are not limited to the following:

• Scientific programming for image and video processing
• Scientific programming tools in machine learning
• Machine learning in image interpretation
• Machine learning in video interpretation
• Deep learning in image classification/target recognition
• Deep learning in video detection/tracking